Skip to content
TILens What matters today in tech
Theme
Topics - AI
Browse
Calendar · AUG 2026
‹ Aug 2026 ›
  1. JAN
  2. FEB
  3. MAR
  1. APR
  2. MAY
  3. JUN
  1. JUL
  2. AUG
  3. SEP
  1. OCT
  2. NOV
  3. DEC
2
18 19 20 21 22 23
24 25 26 27 28 29 30
31

Daily edition · AI

The daily ledger

TILens turns technical updates into a focused daily brief: official releases, trusted reporting, and practitioner analysis, deduplicated and organized by topic.

14 Aug 2026 edition
Python AI Django

Don't classify. Hallucinate!

Don't classify. Hallucinate! I still have quite a bit of older content on my blog that I never got round to tagging. My blog has 1,856 tags - likely too many to feed to an LLM in one go and say "which of these tags…

Source: Simon Willison's Weblog
AI GitHub

langchain-ai/langchain: langchain-openrouter==0.2.8

Changes since langchain-openrouter==0.2.7 release(openrouter): 0.2.8 (#39658) chore(model-profiles): refresh model profile data (#39646) chore(model-profiles): refresh model profile data (#39625) fix(openrouter):…

Source: LangChain Releases github-actions[bot]
AI GitHub

langchain-ai/langchain: langchain-core==1.5.5

Changes since langchain-core==1.5.4 release(core): 1.5.5 (#39655) fix(core): make abatch_iterate consistent with batch_iterate for None and zero size (#39367) fix(core): respect pydantic aliases when validating tool…

Source: LangChain Releases github-actions[bot]
AI GitHub

langchain-ai/langchain: langchain-openai==1.5.1

Changes since langchain-openai==1.5.0 release(openai): 1.5.1 (#39653) fix(openai): preserve streamed encrypted reasoning (#39635) chore(infra): support langsmith gateway in CI (#39651)

Source: LangChain Releases github-actions[bot]
AI

Annealed Softmax Greedy in Many-Armed Bayesian Bandits

arXiv:2605.31034v2 Announce Type: replace Abstract: Reinforcement learning with verifiable rewards (RLVR) and group-based policy optimization methods such as GRPO update a stochastic policy by sampling multiple…

Source: arXiv cs.LG William Overman, Mohsen Bayati
AI

What Makes a Peer? Valuation-Anchored Similarity in Private Markets

arXiv:2608.12594v1 Announce Type: cross Abstract: As more investors contemplate private markets and contend with limited transparency, sparse disclosures, and infrequent transactions, identifying economically meaningful…

Source: arXiv cs.LG Sebastian Frank, Jingrao Lyu, Max Jarmey, Preetha Saha, Mingshu Li, Sweet Kaur, Sola Akinola, Dhagash Mehta
AI

Training and Benchmarking Code Generation for Physics-Inspired Animations

arXiv:2602.10840v2 Announce Type: replace Abstract: Large language models (LLMs) have been widely studied in areas such as mathematical reasoning, complex coding, and scientific problem solving. However, their ability…

Source: arXiv cs.LG Yanan Wang, Renxi Wang, Yongxin Wang, Xuezhi Liang, Fajri Koto, Timothy Baldwin, Xiaodan Liang, Haonan Li
AI

SEAR: Sample Efficient Action Chunking Reinforcement Learning

arXiv:2603.01891v2 Announce Type: replace Abstract: Action chunking improves exploration and accelerates value propagation in long-horizon reinforcement learning, but naively applying off-policy methods to the…

Source: arXiv cs.LG C. F. Maximilian Nagy, Onur Celik, Emiliyan Gospodinov, Florian Seligmann, Weiran Liao, Aryan Kaushik, Gerhard Neumann
AI

Training Non-Differentiable Networks via Optimal Transport

arXiv:2605.01928v2 Announce Type: replace Abstract: We optimize losses that jump: spiking thresholds, quantized layers, and discrete routing put jumps in the forward pass, where backpropagation does not apply. Finite…

Source: arXiv cs.LG An T. Le
AI

Demand Transfer Estimation at Scale via Restricted Logit Modeling

arXiv:2608.12680v1 Announce Type: new Abstract: Item demand forecasting is an integral component of store assortment optimization. Existing literature focuses on learning a suitable customer choice model and using this…

Source: arXiv cs.LG Lakshya Garg, Deep Narayan Mishra, Swapnil Yadav, Haoan Wang, Sujal Alugubelli, Karthik Kumaran, Anupriya Sharma
AI

Dimensional Balance Improves Large Scale Spatiotemporal Prediction Performance

arXiv:2605.18793v3 Announce Type: replace Abstract: Accurate spatiotemporal pattern analysis is critical in fields such as urban traffic, meteorology, and public health monitoring. However, existing methods face…

Source: arXiv cs.LG Jing Chen, Shixiang Pan, Yujie Fan, Haocheng Ye, Haitao Xu, Wenqiang Xu
AI

VALG: An Agentic System for ML Theory Research

arXiv:2608.13060v1 Announce Type: cross Abstract: Machine learning theory studies learning procedures through mathematical setups in which the data model, training protocol, oracle access, loss, metric, and randomness…

Source: arXiv cs.LG Dechen Zhang, Xuan Tang, Xinxiang Yin, Xingwu Chen, Jian Qian, Difan Zou
AI

Latent Fact-Checking: Detecting Misinformation through Activation Engineering

arXiv:2608.06417v3 Announce Type: replace Abstract: The proliferation of misinformation online has driven demand for scalable detection systems. While most existing approaches rely on surface-level linguistic features…

Source: arXiv cs.LG Pedro T. Barcelos, Ot\'avio Parraga, Marcelo M. Mussi, Lucas M. Fraga, Lucas S. Kupssinsk\"u, Rodrigo C. Barros
AI

Vero: Can AI Agents Build Formally Verified Software Repositories?

arXiv:2608.13522v1 Announce Type: new Abstract: AI agents are increasingly used for programming, but do not provide any guarantee on the correctness of generated code. Verified code generation, in which an agent…

Source: arXiv cs.LG Zhe Ye, Hantao Lou, Yuechun Sun, Peiyang Song, Zhengxu Yan, Timothe Kasriel, Qingyang Zhang, Kaiyu Yang, Soonho Kong, Jingxuan He, Dawn Song
AI

Yes, Q-learning Helps Offline In-Context RL

arXiv:2502.17666v5 Announce Type: replace Abstract: Existing offline in-context reinforcement learning (ICRL) methods have predominantly relied on supervised training objectives, which are known to have limitations in…

Source: arXiv cs.LG Denis Tarasov, Alexander Nikulin, Ilya Zisman, Albina Klepach, Andrei Polubarov, Nikita Lyubaykin, Alexander Derevyagin, Igor Kiselev, Vladislav Kurenkov
AI

Black-Box Knowledge Transfer across Distinct Feature Sets

arXiv:2608.12403v1 Announce Type: cross Abstract: Pre-trained black-box predictive functions encode knowledge distilled from massive datasets and extensive computation. However, when the available input features differ…

Source: arXiv cs.LG Oh-Ran Kwon, Daeyoung Ham
AI

Embedding networks with the random walk first return time distribution

arXiv:2512.02694v3 Announce Type: replace-cross Abstract: We propose the first return time distribution (FRTD) of a random walk as an interpretable and mathematically grounded node embedding. The FRTD assigns a…

Source: arXiv cs.LG Vedanta Thapar, Renaud Lambiotte, George T. Cantwell
AI

Gradient-Free Warm-Start Library Recovery: an Amortized-Regret Separation

arXiv:2606.21253v2 Announce Type: replace Abstract: Continual learning that is gradient-free, local, online, and append-only is attractive for edge and streaming deployment, but its value is usually argued informally.…

Source: arXiv cs.LG Jianwei Lou (RailMind Systems, Neuss, Germany)
AI

MAG: MAnifold Guided Semi-Supervised Multi-modal In-Context Learning

arXiv:2608.12724v1 Announce Type: new Abstract: Few-shot in-context learning (ICL) with multi-modal large language models (MLLMs) enables task adaptation without parameter updates, but its performance is highly…

Source: arXiv cs.LG Zirui Cheng, Xun Xu, Tiankai Chen, Fady Rezk, Bowen Zheng, Xiaodong Shi, Shijie Li, Kangkang Lu, Bharadwaj Veeravalli, Nancy F. Chen
AI

Scaling Automatic Research Agents via World Models

arXiv:2608.12564v1 Announce Type: new Abstract: Automating empirical research is a long-standing direction of AI. Recent automatic research (AutoResearch) agents bring this goal within reach, as modern LLMs show the…

Source: arXiv cs.LG Xiyuan Yang, Sheikh Sarwar, Jingru Cheng, Zhan Shi, Duanshun Li, Huiyuan Chen, Haiyang Zhang, Chenlei Guo, Jingrui He, Zhenyu Liao
AI

Efficient Image Restoration with State-Dependent Forward Diffusion

arXiv:2505.16733v3 Announce Type: replace Abstract: This paper proposes to perform image restoration through a state-dependent mean-reverting forward diffusion (FoD) process. In contrast to traditional diffusion-based…

Source: arXiv cs.LG Ziwei Luo, Fredrik K. Gustafsson, Jens Sj\"olund, Thomas B. Sch\"on
AI

DARTree: Speculative Diffusion Decoding with Autoregressive Draft Trees

arXiv:2608.13524v1 Announce Type: new Abstract: Speculative decoding losslessly accelerates autoregressive language models by verifying multiple draft tokens in parallel. Diffusion-based drafters further reduce proposal…

Source: arXiv cs.LG Tianyi Li, Yaxin Luo, Xinyi Shang, Zhiqiang Shen
AI

Regulatory Approval Is Not Enough: Gaps in Trustworthy AI Reporting in FDA-Cleared Medical Devices

arXiv:2608.12360v1 Announce Type: cross Abstract: Background: AI/ML-enabled medical devices are increasingly deployed in healthcare under evolving regulatory frameworks. As these systems become more integrated into…

Source: arXiv cs.LG Ahmed M Salih, Oliver D\'iaz, Alejandro Guzman, Noah Marquez Vara, Fotios Avgoustidis, Rituraj Singh, Saman Barakat, Zahra Raisi-Estabragh, Karim Lekadir
AI

Scaling Time Series Classification via XAI-Driven Data Reduction

arXiv:2607.15774v3 Announce Type: replace Abstract: Explainable AI (XAI) for time series has seen significant algorithmic growth, but its utility in providing measurable performance gains for downstream tasks remains…

Source: arXiv cs.LG Davide Italo Serramazza, Thach Le Nguyen, Georgiana Ifrim
AI

Designing AI Pipelines for Decision-Ready ITSM Intelligence

arXiv:2608.12670v1 Announce Type: cross Abstract: IT service management (ITSM) systems accumulate large volumes of heterogeneous ticket data that are difficult for sales and executive stakeholders to convert into…

Source: arXiv cs.LG Archan Dutta, Yash Dharmadhikari, Marat Valiullin, Rahul Guha, Alexander Liss
AI

TabSOM: A tabular-to-image encoding method based on self-organizing maps

arXiv:2608.13513v1 Announce Type: cross Abstract: Tabular-to-image methods have emerged as novel approaches to leverage the high predictive performance of convolutional neural networks and vision transformers. They…

Source: arXiv cs.LG David Chushig-Muzo, Mar\'ia \'Angeles Rodr\'iguez de Cara, Eva Milara, Francisco J. Lara-Abelenda, Luis Zhinin-Vera, Diego H. Peluffo-Ord\'o\~nez
AI

Thermalizing Stochastic Programs

arXiv:2608.01615v2 Announce Type: replace-cross Abstract: We present a set of tools for mapping general stochastic programs to thermodynamic hardware designed for energy-efficient stochastic sampling. Given a target…

Source: arXiv cs.LG Mirko Amico, Andra\v{z} Jelin\v{c}i\v{c}, Colin Oscar Nancarrow, Leo Tyrpak, David Roberts, Seth Morton, Dalton Sakthivadivel, Ashwin Gopal, Guillaume Verdon
AI

Multi-perspective Imbalance-Conscious 6G Beamforming Optimization and Performance

arXiv:2608.12929v1 Announce Type: new Abstract: The study presents a systematic machine learning (ML) study of 6G-IoT beamforming optimization (6GBO) using supervised and unsupervised approaches. We compared the…

Source: arXiv cs.LG Chukwunonso Henry Nwokoye, Blessing Oluchi Iloka, Chikwue V. Umeugoji, Christopher Anene Egemba, Nnenna D. Duroha
AI

Exploring Oversmoothing with Householder Matrices

arXiv:2608.12514v1 Announce Type: new Abstract: Deep graph neural networks(GNNs) suffer from oversmoothing- a progressive collapse of node representation towards a low information subspace as network depth increases…

Source: arXiv cs.LG Bhaskar Karol
AI

Branch and Bound for Relational Verification of Neural Networks

arXiv:2608.13118v1 Announce Type: new Abstract: Verification of neural networks against relational specifications, such as global robustness, is crucial for safety-critical applications of cyber-physical systems (CPS),…

Source: arXiv cs.LG Kota Fukuda, Zhenya Zhang, Guanqin Zhang, Jianjun Zhao
AI

The Boolean Power of ReLU

arXiv:2608.12617v1 Announce Type: new Abstract: We prove that, on finite simple undirected graphs equipped with a single Boolean node feature, the Boolean queries expressible in $\Sigma$-MPLang, for any collection…

Source: arXiv cs.LG Pablo Barcel\'o, Floris Geerts, Matthias Lanzinger, Klara Pakhomenko, Jan Van den Bussche
AI

Learning Discrete Decisions for MIPs with Constraint-Aware Diffusion

arXiv:2608.13079v1 Announce Type: new Abstract: This paper proposes a novel learning-based approach to approximately solve instances of mixed-integer optimization problems. These problems are computationally…

Source: arXiv cs.LG Vincenzo Di Vito, Mehdi Taghizadeh, Deepjyoti Deka, Kaarthik Sundar, Ferdinando Fioretto
AI

Statistical Properties of Robust Learning under Distributional Shifts

arXiv:2608.13133v1 Announce Type: cross Abstract: Distributional shifts arise when the target deployment environment differs from the source environment that generated the training data. Robust learning frameworks such…

Source: arXiv cs.LG Zhiyi Li, Xiaojie Mao, Yunbei Xu, Ruohan Zhan
AI

A Compositional Theory of Curvature in Probabilistic Circuits

arXiv:2608.12869v1 Announce Type: new Abstract: Probabilistic Circuits (PCs) are generative models that support exact inference and, unlike deep neural networks, admit an exact and tractable measure of loss-surface…

Source: arXiv cs.LG Hrithik Suresh, Sahil Sidheekh, Shelar Parth Vijay, Yasir Z, Sriraam Natarajan, Narayanan Chatapuram Krishnan
AI

Exploring Sparsity for Parameter Efficient Fine Tuning Using Wavelets for Vision

arXiv:2505.12532v3 Announce Type: replace-cross Abstract: Efficiently adapting large pretrained models is critical under tight compute and memory budgets. While Parameter-Efficient Fine-Tuning (PEFT) methods like LoRA…

Source: arXiv cs.LG Ahmet Bilican, M. Ak{\i}n Y{\i}lmaz, A. Murat Tekalp, R. G\"okberk Cinbi\c{s}
AI

Recursive Synthesis for Long-Horizon Terminal Tasks

arXiv:2608.05466v3 Announce Type: replace-cross Abstract: High-quality long-horizon training data for terminal agents is expensive to produce, often costing hundreds to thousands of dollars per task, because each task…

Source: arXiv cs.LG Zhongzhi Li, Yucheng Shi, Zongxia Li, Ruhan Wang, Anhao Li, Zixun Huang, Junyao Yang, Lei Ke, Ninghao Liu, Haitao Mi, Leowei Liang
AI

Stochastic Neural Networks for Quantum Devices

arXiv:2602.22241v2 Announce Type: replace-cross Abstract: This work presents a formulation to express and optimize stochastic neural networks as quantum circuits in gate-based quantum computing. Motivated by a classical…

Source: arXiv cs.LG Bodo Rosenhahn, Tobias J. Osborne, Christoph Hirche
AI

Training AI Scientists to Replicate Research

arXiv:2608.13331v1 Announce Type: new Abstract: The replicability of papers is a cornerstone of scientific knowledge, ensuring the reliability of existing results and providing a base for further experiments. The act of…

Source: arXiv cs.LG Damon Falck, Samer Sabri, Anja Surina, Thom Foster, Anya Sims, Sam Devlin, Dylan Rogers, Tantum Collins, Kaloyan Aleksiev, Louis Kirsch, Edward Hughes
AI

MBA: Multimodal Benchmark and Agents for Real-World Business Ideation

arXiv:2608.11616v2 Announce Type: replace-cross Abstract: Agentic systems powered by large language models (LLMs) have opened new opportunities for business ideation. Yet existing approaches remain confined to a…

Source: arXiv cs.LG Hojun Choi, Jaeyo Shin, Suin Lee, Hyunjung Shim
AI

A Cloud-Edge System for Multimodal Clinical Screening in Resource-Constrained Rural Settings

arXiv:2608.12745v1 Announce Type: new Abstract: Medical AI has demonstrated specialist-level diagnostic accuracy, yet these capabilities remain largely inaccessible in resource-constrained rural settings where bandwidth…

Source: arXiv cs.LG Hei Ting (Una), Chan, Chenwei Wu, Xueshen Liu, Zesen Zhao, Boyuan Zheng, Luis Filipe Nakayama, Michael G. Morley, Liyue Shen, Jiasi Chen, Z. Morley Mao
AI

Synthetic Persona Pretraining: Alignment from Token Zero

arXiv:2608.13482v1 Announce Type: new Abstract: As language-model-based AI is increasingly deployed in autonomous settings, aligning its goals and values with those of humans becomes critical. Today, alignment, and the…

Source: arXiv cs.LG Julian Minder, Viktor Moskvoretskii, Raghav Singhal, Difan Jiao, Andy Arditi, Shaobo Cui, Yiderigun Borjigin, Kartik Bali, Stefan Krsteski, Harsh Raj, Huu Nguyen, Jannik Brinkmann, Ashton Anderson, R…
AI

Defensive Boosting for Online Probabilistic Forecasting

arXiv:2608.13554v1 Announce Type: new Abstract: We study online probabilistic forecasting of binary outcomes chosen by an adaptive adversary. Given an online learning algorithm for a weak hypothesis class $H$, we would…

Source: arXiv cs.LG Georgy Noarov, Aaron Roth
AI

How Do VLMs Behave When Blind or Misled? Behavioral Evaluation of VLMs on Scientific Figures

arXiv:2608.13267v1 Announce Type: cross Abstract: Existing vision-language model (VLM) benchmarks emphasize perception and reasoning accuracy (how well VLMs describe and reason about what they see in an image), with…

Source: arXiv cs.LG Paul Osemudiame Oamen, Owusu-Banahene Osei, Ananya Mukherjee, Christian Greisinger, Steffen Eger, Pius Onobhayedo, Wei Zhao
AI

MARCH: Scaling Recurrent Memory with Content-Routed State Anchors

arXiv:2608.12435v1 Announce Type: new Abstract: Transformers owe much of their strong long-context retrieval capability to a token-level memory that grows with context length. This flexibility, however, incurs a…

Source: arXiv cs.LG Ming Zhang, Kaisen Yang, Shu Yu, Ermo Hua, Ning Ding, Xia Hu, Bowen Zhou, Chaochao Lu, Youbang Sun
AI

Incremental Evaluation and Training in Relational Deep Learning

arXiv:2608.13023v1 Announce Type: new Abstract: Relational Deep Learning (RDL) models multi-tabular databases as temporal heterogeneous graphs to enable end-to-end representation learning. However, prevailing RDL…

Source: arXiv cs.LG Jakub Pele\v{s}ka, Gustav \v{S}\'ir
AI

Fine-tuned Normalizing Flows for ALICE Zero Degree Calorimeter Fast Simulation

arXiv:2608.12795v1 Announce Type: cross Abstract: Simulating the ALICE Zero Degree Calorimeter (ZDC) neutron detector responses at the LHC is computationally expensive, requiring complex Monte Carlo chains. We develop a…

Source: arXiv cs.LG Emilia Majerz, Jacek Otwinowski, Witold Dzwinel, Jacek Kitowski
AI

Position: Reasoning is a Learnable Rule-Based Process

arXiv:2608.12325v1 Announce Type: cross Abstract: Autonomous reasoning is among the most scientifically and economically motivating topics in AI today. Historically the purview of symbolic AI, recent advances have…

Source: arXiv cs.LG Rachel Lawrence, Jacqueline Maasch
AI

SE(3)-MeanFlow: Few-Step Protein Backbone Generation on Lie Groups

arXiv:2607.27431v4 Announce Type: replace Abstract: Generative modeling of protein backbones promises the de novo design of proteins with prescribed structural and functional properties. Existing diffusion and…

Source: arXiv cs.LG Yikun Bai, Binghang Lu, Yikai Liu, Elaheh Akbari, Soheil Kolouri, Linxuan Wang, Ping He, Shuchan Wang, Ruqi Zhang, Guang Lin
AI

EEG Decoding Using CNN and LSTM Network

arXiv:2608.13285v1 Announce Type: new Abstract: Motor imagery (MI) brain--computer interfaces (BCIs) have emerged as a promising approach for establishing flexible communication pathways between the human brain and…

Source: arXiv cs.LG Athanasios Karagounis
AI

Perturbation-based Regional Interpretability through Subtraction Mapping (PRISM): naming-error dissociations in language models and post-stroke aphasia

arXiv:2608.12717v1 Announce Type: new Abstract: Mechanistic interpretability of large language models lacks spatially resolved, falsifiable tools for testing whether internal components are specialized for distinct…

Source: arXiv cs.LG Xiang Guan, Roger D. Newman-Norlund, Yong Yang, Saeed Ahmadi, Regan Willis, Nadra Salman, Kalil Warren, Srihari Nelakuditi, Chris Rorden, Leonardo Bonilha, Julius Fridriksson
AI

General Bayesian Policy Learning

arXiv:2602.23672v2 Announce Type: replace-cross Abstract: This study proposes a General Bayes framework for policy learning. We consider decision problems in which a decision-maker chooses an action from a given set to…

Source: arXiv cs.LG Masahiro Kato
AI

Unified Multi-Dimensional Benchmark for Complex Graph Reasoning in Large Language Models

arXiv:2608.12391v1 Announce Type: cross Abstract: Graph reasoning provides a promising testbed for evaluating the reasoning ability of large language models (LLMs), as graph instances can be programmatically generated,…

Source: arXiv cs.LG Fali Wang, Ali Al-Lawati, Iliyas Bektas, Jinxuan Fang, Alek Melenski, Tianxiang Zhao, Yao Ma, Suhang Wang
AI

SAF3R: Dynamic Sparse Attention for Feed-Forward 3D Reconstruction Transformers

arXiv:2607.03612v2 Announce Type: replace-cross Abstract: Feed-forward 3D reconstruction (F3R) transformers have recently achieved remarkable success. However, scaling them to long image sequences remains challenging,…

Source: arXiv cs.LG Jianing Deng, Yuanzhe Li, Jialu Wang, Song Wang, Tianlong Chen, Huanrui Yang, Jingtong Hu
AI

DiG-bench: Discovery in Games

arXiv:2608.12593v1 Announce Type: cross Abstract: Discovery---formulating novel generalizations---is a central part of the scientific process. Despite its importance, there is a gap in the current AI benchmark…

Source: arXiv cs.LG Ruairidh M. Battleday, Kai Sandbrink, Jimi Cullen-Drohan, Zihan Yan, Timothy Muller, Clare Maguire, Ales Kubicek, Fraser Greenlee-Scott, Sukrit Sumant, Tri Dao, J\"urgen Schmidhuber, Michal Valko, Jo…
AI

Novel Knowledge-Guided Generative Methods for Synthetic Transcriptomic Data

arXiv:2608.13256v1 Announce Type: new Abstract: As biomedical research increasingly relies on data-intensive tools, the quality and utility of datasets are critical. Challenges such as imbalances, biases, and ethical or…

Source: arXiv cs.LG Francesca Pia Panaccione, Sofia Mongardi, Marco Masseroli, Pietro Pinoli
AI

Diagnosing JEPA World Models with Action-Conditioned Predictive Consistency

arXiv:2608.12939v1 Announce Type: new Abstract: Joint-embedding predictive architectures (JEPAs) learn world models that predict in a compact latent space rather than in pixels, reducing the pressure to model nuisance…

Source: arXiv cs.LG Guo An, Zijing Wu, Honghua Dong, Yuhao Yan, Zixuan Gui, Haochong Chen, Shanzhao Ruan, Xiang Wang, Yurong Ling, Qi Tian
AI

LittleLearner: Language Models Under Pedagogically Controlled Knowledge Exposure

arXiv:2608.13545v1 Announce Type: cross Abstract: Modern language models are trained on heterogeneous web-scale text corpora. Consequently, studying knowledge and skill acquisition is difficult, as prior exposure to…

Source: arXiv cs.LG Fanfei Li, Jana Zeller, Manuel Prada-Corral, Thadd\"aus Wiedemer, Prasanna Mayilvahanan, Ryan Cotterell, Wieland Brendel
AI

Do Transformers Need Three Projections? Systematic Study of QKV Variants

arXiv:2606.04032v3 Announce Type: replace Abstract: Transformers have become the standard solution for various AI tasks, with the query, key, and value (QKV) attention formulation playing a central role. However, the…

Source: arXiv cs.LG Ali Kayyam, Anusha Madan Gopal, M Anthony Lewis
AI

REOPD: Reliability-Adaptive Reward Extrapolation for On-Policy Distillation

arXiv:2608.11698v2 Announce Type: replace Abstract: On-policy distillation (OPD) trains a student on its own trajectories under dense token-level supervision from a teacher. Reward-extrapolation methods such as ExOPD…

Source: arXiv cs.LG Yang Sun, Lichao Ma, Houyuan Qin, Yuxin Liu, Hanyang Lu, Yao Zhu, Pinlong Cai, Guohang Yan
AI

Exponential quantum advantage for learning signals with a single qubit

arXiv:2608.13521v1 Announce Type: cross Abstract: Quantum technology has the potential to transform scientific discovery, but quantum advantages often require processing capabilities well beyond the reach of…

Source: arXiv cs.LG Ishaan Kannan, Sridhar Prabhu, Saeed A. Khan, Mandar M. Sohoni, Xingrui Song, Saswata Roy, Alen Senanian, Valla Fatemi, Peter L. McMahon, Jordan Cotler
AI

Constitutional On-Policy Safe Distillation

arXiv:2606.03089v3 Announce Type: replace Abstract: On-policy self-distillation (OPSD) has emerged as an efficient post-training paradigm by using a teacher conditioned on privileged information to provide dense…

Source: arXiv cs.LG Ming Wen, Yuxuan Liu, Kun Yang, Yunhao Feng, Zhuoer Xu, Yuhao Sun, Shiwen Cui, Xiang Zheng, Yi Liu, Xingjun Ma, Yu-Gang Jiang
AI

TabH2O: A Unified Foundation Model for Tabular Prediction

arXiv:2605.18383v2 Announce Type: replace Abstract: We present TabH2O, a foundation model for tabular data that performs classification and regression in a single forward pass via in-context learning. TabH2O builds on…

Source: arXiv cs.LG Pascal Pfeiffer, Dmitry Gordeev, Mathias M\"uller, Laura Fink, Joan Salv\`a Soler, Mark Landry, Branden Murray, Marcos V. Conde, Sri Satish Ambati
AI

The Time Value of Evolution

arXiv:2608.13297v1 Announce Type: new Abstract: In evolutionary search, a weak child can be a valuable ancestor that makes high-fitness regions reachable. Immediate-return control is blind to this delayed utility,…

Source: arXiv cs.LG Matthew Siper, Ahmed Khalifa, Julian Togelius
AI

I-SDPO: Instance-Level Adaptive Self-Distillation Policy Optimization

arXiv:2608.12957v1 Announce Type: new Abstract: Group Relative Policy Optimization (GRPO) learns from reward differences within a rollout group, but receives no useful relative signal when every sampled response is…

Source: arXiv cs.LG Yubo Zhang, Xinhong Ma, Zezhong Tan, Ziqiang Dong
AI

Beyond Simulated Benchmarks: Evaluating Motion Representations for Fall Detection Under Real-World Data Scarcity

arXiv:2608.13197v1 Announce Type: new Abstract: Falls are a major health concern for older adults, and wearable sensors have been widely explored for detecting falls and enabling timely intervention. However, real-world…

Source: arXiv cs.LG Timilehin B. Aderinola, Ilaria D'Ascanio, Luca Palmerini, Lorenzo Chiari, Jochen Klenk, Clemens Becker, Brian Caulfield, Georgiana Ifrim
AI

Foundation models for movement data: Are they ready for prime-time?

arXiv:2608.13316v1 Announce Type: cross Abstract: Foundation models (FMs) trained on large-scale accelerometer data have been proposed as general-purpose feature extractors for health monitoring, but systematic evidence…

Source: arXiv cs.LG Alexander Br\"auer, Benjamin Cauchi, Nils Strodthoff
AI

Concept Drift Detection and Adaptive Retraining of Malware Classification Models

arXiv:2608.13465v1 Announce Type: new Abstract: Concept drift refers to changes over time in the statistical properties of data, as compared to the data that was used to train a learning model. Machine learning models…

Source: arXiv cs.LG Christofer Washington Berruz Chungata, Martin Jurecek, Katerina Potika, William B. Andreopoulos, Mark Stamp
AI

Unifying Generative Models with Path Integrals

arXiv:2608.12438v1 Announce Type: new Abstract: We formulate generative modeling as a path integral in which flow-based, diffusion-based, variational, and adversarial models arise as different evaluation principles for…

Source: arXiv cs.LG Ramon Winterhalder
AI

From Visual Widgets to UI Code: Efficient Tool-Grounded Generation

arXiv:2608.12611v1 Announce Type: cross Abstract: Existing screenshot-to-code systems face a trade-off between flexibility and controllability. Direct multimodal generation can hallucinate visible details, whereas…

Source: arXiv cs.LG Houston H. Zhang, Tao Zhang, Li Gu, Linfeng Ye, Yuanhao Yu, Xinxin Zuo, Yang Wang, Zhixiang Chi
AI

A Simple State Space Model Excels at Multivariate Time Series Classification

arXiv:2605.27406v2 Announce Type: replace Abstract: Structured state space models (SSMs) have recently emerged as a promising foundation for sequence modeling, with Mamba-based architectures demonstrating strong…

Source: arXiv cs.LG Hassan Saadatmand, Geoffrey I. Webb, Hamid Rezatofighi, Mahsa Salehi
AI

SteerBench-Work: A Benchmark for Agent Steering at Action Boundaries

arXiv:2608.12654v1 Announce Type: cross Abstract: Long-running LLM agents act through tools, and a single step can send an email, merge a pull request, or wire a payment. The steering decision is the pre-commit choice…

Source: arXiv cs.LG Oguz Serdar, Cuneyt Mertayak
AI

Simulation-to-real transfer learning for infrared spectroscopic chemical sensing and analysis from molecules to complex samples

arXiv:2608.13341v1 Announce Type: new Abstract: Infrared (IR) spectroscopy is widely used for chemical sensing, but extracting reliable chemical information from spectra remains challenging. Conventional interpretation…

Source: arXiv cs.LG Yusen Tan, Yixuan Chen, Zheng Fang, Pan Liu, Yifan Li, Qinyu Guo, Zhedong Lin, Yuqiang Li, Xiangxiang Zeng, Tong Wang, Jun Xia
AI

Tight Nonasymptotic Local Convergence of Sinkhorn-Knopp

arXiv:2608.11760v2 Announce Type: replace-cross Abstract: We revisit the Sinkhorn-Knopp (SK) algorithm for the matrix scaling problem. Despite extensive literature on the global convergence of SK and its variants, its…

Source: arXiv cs.LG Wenzhi Gao, Zhaonan Qu, Yinyu Ye, Madeleine Udell
AI

ReconSpan: Reconstruction-Guided Adaptive Latent Tokenization

arXiv:2608.12756v1 Announce Type: cross Abstract: Adaptive latent tokenization maps a fine-grained input to a shorter sequence of continuous representations associated with input-dependent spans. We introduce ReconSpan,…

Source: arXiv cs.LG Lixing Li
AI

The Noise Premium in Adversarial Training for Kernel Regression

arXiv:2607.27995v2 Announce Type: replace-cross Abstract: Adversarial training can improve the robustness of predictive models to bounded perturbations, often at the cost of statistical efficiency. We study this…

Source: arXiv cs.LG Yiling Xie, Xiaoming Huo
AI

MatchMiner-AI: Open-source, Privacy-preserving Cancer Clinical Trial Matching using Artificial Intelligence

arXiv:2412.17228v4 Announce Type: replace-cross Abstract: Background: Clinical trials are essential to advancing cancer treatments, but fewer than 10% of adults with cancer enroll in therapeutic trials. Open-source AI…

Source: arXiv cs.LG Jennifer Altreuter, Pavel Trukhanov, Morgan A. Paul, Michael J. Hassett, Irbaz B. Riaz, Muhammad Umar Afzal, Arshad A. Mohammed, Ayub Umair, Huan He, Chueh Husan Hsu, Sarah Sammons, James Lindsay, Em…
AI

GENADA: efficient generative time series adversarial attack framework

arXiv:2608.12535v1 Announce Type: new Abstract: Deep learning models are widely used for time series analysis in domains such as healthcare, finance, energy systems, and environmental monitoring. However, these models…

Source: arXiv cs.LG Michael Baronov, Denis Vorobev, Margarita Rusanova, Petr Sokerin, Alexey Zaytsev
AI

Knowledge-guided Pattern Discovery via Coupled Tensor Factorizations

arXiv:2608.13234v1 Announce Type: new Abstract: In order to understand complex systems such as the human metabolome or human brain, different sensing technologies are used, generating complex data. These datasets are…

Source: arXiv cs.LG Gaute Johannessen, Geert Roelof van der Ploeg, Evrim Acar
AI

Prof-K: Probabilistic One-Pass Filtering for Efficient Top-k Selection

arXiv:2608.12573v1 Announce Type: new Abstract: Top-k selection is a fundamental computational primitive with applications spanning databases, information retrieval, signal processing, and modern machine learning…

Source: arXiv cs.LG Tadeusz Dziarmaga, Witold Sikora, {\L}ukasz Struski, Jacek Tabor, Marcin Mazur
AI

CAKE: Compiler-Agent Co-Design for Frontier Kernel Evolution

arXiv:2608.12629v1 Announce Type: new Abstract: GPU kernel agents and GPU programming languages have advanced separately, leaving expert kernels difficult to reproduce. Agents usually treat the compiler as a fixed black…

Source: arXiv cs.LG Zihao Ye, Yingyi Huang, Hongyi Jin, Bohan Hou, Junru Shao, Zhongming Yu, Jinqi Chen, Meghan Cowan, Shiyi Cao, Shanli Xing, Hanfeng Chen, Vinod Grover, Tianqi Chen, Luis Ceze
AI

A Probe Direction Is a Property of Its Prompt

arXiv:2608.13329v1 Announce Type: new Abstract: A model that behaves differently when it senses it is being tested would undermine the evaluations we rely on, so recent work has sought to read that sense directly from a…

Source: arXiv cs.LG Valentin No\"el
AI

Cueless EEG imagined speech for subject identification: dataset and benchmarks

arXiv:2501.09700v2 Announce Type: replace Abstract: Electroencephalogram (EEG) signals have emerged as a promising modality for biometric identification. While previous studies have explored the use of imagined speech…

Source: arXiv cs.LG Ali Derakhshesh, Zahra Dehghanian, Reza Ebrahimpour, Hamid R. Rabiee
AI

Regularization can make diffusion models more efficient

arXiv:2502.09151v4 Announce Type: replace Abstract: Diffusion models are one of the key architectures of generative AI. Their main drawback, however, is the computational costs. This study indicates that the concept of…

Source: arXiv cs.LG Mahsa Taheri, Johannes Lederer
AI

The Optimal Sample Complexity of Multiclass and List Learning

arXiv:2604.24749v2 Announce Type: replace Abstract: While the optimal sample complexity of binary classification in terms of the VC dimension is well-established, determining the optimal sample complexity of multiclass…

Source: arXiv cs.LG Chirag Pabbaraju
AI

Which Decisions Low-Bit Quantization Breaks, and How to Predict Them

arXiv:2608.06564v3 Announce Type: replace Abstract: Quantization is known to hurt below four bits, but nobody can say which of a model's decisions will change at a given bit-width. This matters most where a model acts…

Source: arXiv cs.LG Zekun Wu, Swati Dhiman, Adriano Koshiyama
AI

Intern-S2-Preview: Scientific Agentic Foundation Model

arXiv:2608.13505v1 Announce Type: new Abstract: Scientific discovery increasingly requires AI systems that can reason over scientific evidence of heterogeneous modalities, interact with scientific tools and…

Source: arXiv cs.LG Lei Bai, Jiaqi Cao, Chiyu Chen, Guanzhou Chen, Kai Chen, Guangran Cheng, Erfei Cui, Xuanlang Dai, Shengyuan Ding, Shangheng Du, Yanhui Duan, Yue Fan, Youqing Fang, Quan Gan, Yuanyuan Gao, Jiaye Ge, L…
AI

Beckmann Transport Models: From Autonomous Flows to One-Step Maps

arXiv:2608.01692v3 Announce Type: replace Abstract: We propose an instantiation of flow matching that relies on a time-independent velocity field (an \emph{autonomous flow}) to exactly map between two distributions, so…

Source: arXiv cs.LG Lee Cheuk-Kit, Florentin Coeurdoux, Yuyuan Chen, Sophia Tang, Peter Potaptchik, Yilun Du, Michael Samuel Albergo, Eric Vanden-Eijnden
AI

Bagging Robustly Learns VC Classes with Linear Sample Complexity

arXiv:2608.13514v1 Announce Type: cross Abstract: We revisit the problem of learning predictors robust to adversarial examples at test-time. We prove that VC classes are adversarially robustly learnable with sample…

Source: arXiv cs.LG Omar Montasser
AI

Interpretable Causal Discovery via Causal-Effect Constraints

arXiv:2608.12640v1 Announce Type: new Abstract: Causal discovery aims to uncover the underlying causal relationships given data generated from a system. The goal, however, is not merely to predict causal edges given…

Source: arXiv cs.LG Cixuan Zhang, Guy Van den Broeck, Benjie Wang
AI

History-informed Lagrangian Neural Networks

arXiv:2608.13215v1 Announce Type: new Abstract: Forecasting the long-horizon evolution of mechanical systems from position-only observations is a pivotal yet difficult task, as hidden velocities and trajectory-specific…

Source: arXiv cs.LG Tianshuo Zhang, Xianglei Xing, Wenzhe Zhai, Jia Gao, He Cao
AI

Task- and dataset-specific information in protein language models

arXiv:2608.12090v2 Announce Type: replace Abstract: Protein language models (PLMs) have transferred the latest advances from natural language processing to computational biology. These models, trained on large corpora…

Source: arXiv cs.LG Roman Joeres, Ilya Senatorov, Anastasia Kolchina, Dietrich Klakow, Olga V. Kalinina
AI

DiffGRM: Diffusion-based Generative Recommendation Model

arXiv:2510.21805v2 Announce Type: replace-cross Abstract: Generative recommendation (GR) is an emerging paradigm that represents each item via a tokenizer as an n-digit semantic ID (SID) and predicts the next item by…

Source: arXiv cs.LG Zhao Liu, Yichen Zhu, Yiqing Yang, Xiao Lv, Guoping Tang, Rui Huang, Qiang Luo, Ruiming Tang, Kun Gai, Guorui Zhou
AI

Intervention-Aware Clinical World Model for Post-Op Outcome Forecasting in Cardiology

arXiv:2608.13518v1 Announce Type: new Abstract: Many clinical prediction models treat post-intervention outcomes as a one-step mapping from baseline measurements to a future endpoint. However, recovery after a procedure…

Source: arXiv cs.LG Yunsung Chung, Yingshuo Liu, Abboud F. Hassan, Han Feng, Mary M. Maleckar, Nassir Marrouche, Jihun Hamm
AI

Federated Compositional Muon Optimizer for Matrix-Wise Models

arXiv:2608.12710v1 Announce Type: new Abstract: Muon, a more recently developed optimizer, is useful for matrix-wise models in AI areas. Although many works have studied Muon and its variants, these methods are still…

Source: arXiv cs.LG Wang Yan, Feihu Huang
AI

Reinforcement Learning with Pairwise Preferences in Long-Term Decision Problems

arXiv:2606.00367v2 Announce Type: replace Abstract: Reinforcement learning with scalar rewards is widely used for aligning machine-learning systems with user preferences. But, pairwise preferences are often more natural…

Source: arXiv cs.LG Jonathan Cola\c{c}o Carr, Prakash Panangaden, Doina Precup, Benjamin Van Roy
AI

MLLM-Routed Heterogeneous Ensembles for Robust Cross-Dataset Image Classification

arXiv:2608.13463v1 Announce Type: cross Abstract: Modern image classification models excel when trained on single task-specific datasets but often struggle to generalize across domains and difficulty levels. We propose…

Source: arXiv cs.LG Daniel Perkins, John Squires, Janou Milligan, Chandra Raskoti, Linda Ungerboeck
AI

Bayesian Distributional Models of Executive Functioning

arXiv:2510.00387v4 Announce Type: replace Abstract: This study uses controlled simulations with known ground-truth parameters to evaluate how Distributional Latent Variable Models (DLVM) and Bayesian Distributional…

Source: arXiv cs.LG Robert Kasumba, Zeyu Lu, Dom CP Marticorena, Mingyang Zhong, Paul Beggs, Anja Pahor, Geetha Ramani, Imani Goffney, Susanne M Jaeggi, Aaron R Seitz, Jacob R Gardner, Dennis L Barbour
AI

Foundations of Independent Component Analysis

arXiv:2608.13229v1 Announce Type: cross Abstract: We present the mathematical foundations of linear independent component analysis (ICA) models based on standard literature in a self-contained note. It is aimed at…

Source: arXiv cs.LG Patrick Forr\'e
AI

Fast Length-Squared Sampling for Positive-Semidefinite Matrices

arXiv:2608.12503v1 Announce Type: cross Abstract: We describe a simple rejection-sampling-based algorithm to perform length-squared sampling on an $n \times n$ positive-semidefinite (psd) matrix: that is, to sample a…

Source: arXiv cs.LG Rajarshi Bhattacharjee, Ethan N. Epperly, Cameron Musco, Aaron Tian
AI

Variance Reduction Based Experience Replay for Policy Optimization

arXiv:2602.05379v2 Announce Type: replace-cross Abstract: Effective reinforcement learning (RL) for complex stochastic systems requires leveraging historical data to improve sample efficiency and accelerate policy…

Source: arXiv cs.LG Hua Zheng, Wei Xie, M. Ben Feng, Keilung Choy
AI

Liquidity-Based Audit of Algorithmic Trading Strategies

arXiv:2606.29018v2 Announce Type: replace-cross Abstract: We show that net demand for liquidity by algo strategies is identifiable from its trade and price history alone, with no knowledge of its signal or optimization…

Source: arXiv cs.LG Irene Aldridge
AI

SDS-LoRA: Overcoming Anisotropic Gradient Scaling in Low-Rank Adaptation

arXiv:2606.16454v2 Announce Type: replace Abstract: Low-Rank Adaptation (LoRA) enables efficient adaptation of large pretrained models to downstream tasks by parameterizing weight updates with low-rank matrices. In this…

Source: arXiv cs.LG Junghun Oh, Sungyong Baik, Kyoung Mu Lee
AI

Accelerated Markov Chain Monte Carlo Algorithms on Discrete States

arXiv:2505.12599v3 Announce Type: replace-cross Abstract: We propose a class of discrete state sampling algorithms based on Nesterov's accelerated gradient method, which extends the classical Metropolis-Hastings (MH)…

Source: arXiv cs.LG Bohan Zhou, Shu Liu, Xinzhe Zuo, Wuchen Li
AI

Distribution Steering via Sliced Optimal Transport Control

arXiv:2608.12828v1 Announce Type: cross Abstract: Distribution steering seeks feedback laws that drive the state law of a dynamical system between prescribed initial and terminal distributions. Optimal transport…

Source: arXiv cs.LG Kaito Ito, Anqi Dong
AI

Adaptive $k$ Nearest Neighbors Classifier via Granular Ball Computing

arXiv:2608.12903v1 Announce Type: new Abstract: The $k$-Nearest Neighbor~(KNN) algorithm is widely used across various tasks. The selection of the $k$ value is a key issue because it significantly impacts performance.…

Source: arXiv cs.LG Xiaoyu Lian, Shuyin Xia, Hongxuan He, Lifeng Shen, Guoyin Wang, Xinbo Gao
AI

TraVEL: Trajectory-Guided Video Embedding Learning for Driving-Video Retrieval

arXiv:2608.13495v1 Announce Type: cross Abstract: Efficiently retrieving relevant clips from large-scale driving logs is essential for data curation, model development, and safety analysis. Structured and rule-based…

Source: arXiv cs.LG Yi-Chung Chen, Philip Jacobson, Tom Lampo, Yiren Lu, Jin Yao, David I. Inouye, Jing Gao, Danhua Guo, Burhan Yaman
AI

Unifying Depth and Width Pruning for LLMs via Binary Knapsack Optimization

arXiv:2608.12953v1 Announce Type: cross Abstract: Structured pruning is a promising approach for compressing large language models (LLMs), yet existing methods rely heavily on greedy heuristics that produce myopic…

Source: arXiv cs.LG Palaash Goel, Ayan Sengupta, Akshay Nambi, Tanmoy Chakraborty
AI

Into the ORBIT for Time Series: Training Regimes for Foundation Models

arXiv:2608.13262v1 Announce Type: new Abstract: Time series foundation models (TSFMs) have advanced primarily through architectural innovation, while training regimes for large-scale heterogeneous corpora remain…

Source: arXiv cs.LG Hongjie Xia, Yiding Liu, Yifan Hu, Peiyuan Liu, Zewei Dong
AI

Trajectory First: A Curriculum for Discovering Diverse Policies

arXiv:2506.01568v4 Announce Type: replace Abstract: Being able to solve a task in diverse ways makes agents more robust to task variations and less prone to local optima. In this context, constrained diversity…

Source: arXiv cs.LG Cornelius V. Braun, Sayantan Auddy, Marc Toussaint
AI

MergeOver: Post-Training Token Merging for Recursive Vision Transformers

arXiv:2608.13141v1 Announce Type: cross Abstract: Vision Transformers (ViTs) demonstrate exceptional performance in computer vision but suffer from large parameter counts and quadratic computational complexity, severely…

Source: arXiv cs.LG Junseo Kim, Uraz Odyurt, Amirreza Yousefzadeh
AI

Latent On-Policy Self-Distillation

arXiv:2608.13040v1 Announce Type: new Abstract: Enabling agents to learn from experience and internalize it into their policy has become a central problem in self-evolving AI. On-policy self-distillation (OPSD) offers…

Source: arXiv cs.LG Guibin Zhang, Jiayang Lyu, Ran Sun, Xinlei Yu, Haoyu Zhao, Qibing Ren, Shuicheng Yan
AI

Safe Exploration via Policy Priors

arXiv:2601.19612v4 Announce Type: replace Abstract: Safe exploration is a key requirement for reinforcement learning (RL) agents to learn and adapt online, beyond controlled (e.g. simulated) environments. In this work,…

Source: arXiv cs.LG Manuel Wendl, Yarden As, Manish Prajapat, Anton Pollak, Stelian Coros, Andreas Krause
AI

RadarGen: Automotive Radar Point Cloud Generation from Cameras

arXiv:2512.17897v2 Announce Type: replace-cross Abstract: We present RadarGen, a diffusion model for synthesizing realistic automotive radar point clouds from multi-view camera imagery. RadarGen adapts efficient…

Source: arXiv cs.LG Tomer Borreda, Fangqiang Ding, Sanja Fidler, Shengyu Huang, Or Litany
AI

Learning Latency-Aware Orchestration for Multi-Agent Systems

arXiv:2601.10560v2 Announce Type: replace-cross Abstract: Multi-agent systems (MAS) coordinate multiple LLM-powered agents through structured workflows, gaining reasoning power but incurring high inference latency from…

Source: arXiv cs.CL Xi Shi, Mengxin Zheng, Qian Lou
AI

GEM: A Generative Embedding Model Bridging Reasoning and Retrieval

arXiv:2608.13200v1 Announce Type: new Abstract: Modern LLMs excel at reasoning and instruction following, enabling users to express complex and diverse information needs. However, conventional retrievers largely rely on…

Source: arXiv cs.CL Zhili Shen, Craig Macdonald
AI

When Large Language Models are More PersuasiveThan Incentivized Humans, and Why

arXiv:2505.09662v4 Announce Type: replace Abstract: Large Language Models (LLMs) have been shown to be highly persuasive, but when and why they outperform humans is still an open question. We compare the persuasiveness…

Source: arXiv cs.CL Jiacheng Liu, Francesco Salvi, Philipp Schoenegger, Xiaoli Nan, Ramit Debnath, Barbara Fasolo, Evelina Leivada, Gabriel Recchia, Fritz G\"unther, Ali Zarifhonarvar, Joe Kwon, Zahoor Ul Islam, Marco D…
AI

StorySpark: Module-wise Evolutionary Search for Story Premise Generation

arXiv:2608.12336v1 Announce Type: new Abstract: A story premise is the creative spark from which a full narrative can grow. Yet LLM-based story generation has mostly emphasized later-stage planning, controllability,…

Source: arXiv cs.CL Yang Yang, Zining Zhong, Qian Cao, Jindong Li, Boyun Xu, Kaishen Yuan, Menglin Yang, Yutao Yue
AI

Intensional Anaphora

arXiv:2608.12598v1 Announce Type: new Abstract: Intensional operators are often treated as quantifiers over possible worlds, parallel to the treatment of determiners as quantifiers over individuals. Yet individuals…

Source: arXiv cs.CL Ezra Keshet, Steven Abney
AI

Refusing Intent, Not Form: Wrapper-Based Intent-Group Supervision for LLM Safety

arXiv:2608.13304v1 Announce Type: new Abstract: Safety tuning can improve harmful refusal, but models may learn surface-form shortcuts: wrapped harmful prompts bypass safety, while similarly wrapped benign prompts are…

Source: arXiv cs.CL Ping Wu, Haibo Tong, Feifei Zhao, Han Shen, Yu Shi, Yilin Zhao, Sicheng Shen, Guobin Shen, Yun Luo, Yi Zeng
AI

Query Timing Produces Opposite Positional Biases Between LLMs and Humans

arXiv:2608.12387v1 Announce Type: new Abstract: Positional biases such as recency and primacy effects have been documented in large language models (LLMs), yet the underlying mechanism by which these models make their…

Source: arXiv cs.CL Jasin Cekinmez, Addison J. Wu, Thomas L. Griffiths
AI

Comparing Architectures for Supervised Political Scaling

arXiv:2607.01464v2 Announce Type: replace Abstract: Text scaling, the task of positioning political actors on an ideological scale, is a fundamental task in political analysis. To ease the need for manual analysis,…

Source: arXiv cs.CL Anna Golub, Sebastian Pad\'o
AI

It's How You Ask: Gender-Associated Linguistic Bias in LLMs

arXiv:2608.13328v1 Announce Type: new Abstract: Professional communication is increasingly mediated by LLMs - but do these models serve all users equally? We show that when prompts contain linguistic features more…

Source: arXiv cs.CL Katherine Van Koevering, Anjalie Field
AI

Vision-Language Models are Fragile Multilingual Associators

arXiv:2608.12333v1 Announce Type: new Abstract: Vision-language models must associate visual entities with textual attributes. Whether these associations or concept bindings remain stable when the language of the input…

Source: arXiv cs.CL Ritabrata Chakraborty, Rajatsubhra Chakraborty, Shivakumara Palaiahnakote, Angelo Cangelosi, Umapada Pal
AI

Is this Citation on Point?

arXiv:2608.12571v1 Announce Type: cross Abstract: In 2023, a New York judge sanctioned two attorneys in Mata v. Avianca for filing a brief with hallucinated citations generated by ChatGPT. Such failures are largely…

Source: arXiv cs.CL Apurv Verma
AI

PatientAct: Theory-Grounded Mental Health Client Simulation

arXiv:2608.12750v1 Announce Type: new Abstract: LLM-based simulated clients are increasingly used to train novice counselors, evaluate LLM therapists, and generate synthetic data. However, current simulators produce…

Source: arXiv cs.CL Sahand Sabour, TszYam NG, Yaqian Chen, Guanqun Bi, Jialu Zhao, Minlie Huang
AI

Diagnostic Foundation for Evaluating LLMs' Research Integrity as Co-Scientists

arXiv:2608.12345v1 Announce Type: cross Abstract: Language models are increasingly deployed as co-scientists, yet their ability to uphold research integrity under institutional pressure remains unmeasured. We introduce…

Source: arXiv cs.CL Yash Tripathi, Silu Sharma, Sai Sidhanth Manoharan Jayanthi, Shivank Garg, Lin Li
AI

The Embedder's Dilemma: LLMs Are Better, but at What Cost?

arXiv:2608.12875v1 Announce Type: new Abstract: Should you replace your text-embedding pipeline with a large language model? We answer this with a controlled, cost-aware comparison of ten LLMs across six families and 26…

Source: arXiv cs.CL Adnan El Assadi, Niklas Muennighoff, Jinhyuk Lee
AI

Pandora: Leveraging Code-driven Knowledge Transfer for Unified Structured Knowledge Reasoning

arXiv:2508.17905v2 Announce Type: replace Abstract: Unified Structured Knowledge Reasoning (USKR) aims to answer natural language questions by using structured sources such as tables, databases, and knowledge graphs in…

Source: arXiv cs.CL Yongrui Chen, Junhao He, Linbo Fu, Shenyu Zhang, Rihui Jin, Xinbang Dai, Jiaqi Li, Dehai Min, Nan Hu, Yuxin Zhang, Guilin Qi, Yi Huang, Tongtong Wu
AI

Agentic Aggregation for Parallel Scaling of Long-Horizon Agentic Tasks

arXiv:2604.11753v2 Announce Type: replace Abstract: We study parallel test-time scaling for long-horizon agentic tasks such as agentic search and deep research, where multiple rollouts are generated in parallel and…

Source: arXiv cs.CL Yoonsang Lee, Howard Yen, Xi Ye, Danqi Chen
AI

SEMA: Simple yet Effective Learning for Multi-Turn Jailbreak Attacks

arXiv:2602.06854v2 Announce Type: replace Abstract: Multi-turn jailbreaks capture the real threat model for safety-aligned chatbots, where single-turn attacks are merely a special case. Yet existing approaches break…

Source: arXiv cs.CL Mingqian Feng, Xiaodong Liu, Weiwei Yang, Jialin Song, Xuekai Zhu, Chenliang Xu, Jianfeng Gao
AI

OmniScientist: An Omni-Modal Omni-Discipline AI Scientist

arXiv:2608.13558v1 Announce Type: cross Abstract: Recent advances in foundation models have enabled AI scientists to automate increasingly complete research workflows, from hypothesis generation and code execution to…

Source: arXiv cs.CL Bobo Li, Hao Fei, Tianjie Ju, Mong-Li Lee, Wynne Hsu
AI

AutoDesign: Meta-Harness Optimization for Long-Horizon Agentic Design

arXiv:2608.13560v1 Announce Type: cross Abstract: Transforming multimodal sources into condensed and structured media outputs can be fundamentally conceptualized as a long-horizon agentic process centered on a…

Source: arXiv cs.CL Yaxin Luo, Haobin Jiang, Jialv Zou, Xu Huang, Wenhao Yan, Haodong Li, Zhengrong Yue, Jing Li, Xiaofu Chen, Xiaohan Zhao, Jiacheng Liu, Jiacheng Cui, Zhiqiang Shen, Xiaotong Li
AI

QUIETT: Query-Independent Table Transformation for Robust Reasoning

arXiv:2602.20017v2 Announce Type: replace Abstract: Real-world tables often contain schema inconsistencies, heterogeneous value formats, and implicit relational structures that degrade table reasoning and question…

Source: arXiv cs.CL Gaurav Najpande, Tampu Ravi Kumar, Manan Roy Choudhury, Neha Valeti, Yanjie Fu, Vivek Gupta
AI

SLAyiNG: A Diverse and Community-validated Dataset of Queer Slang

arXiv:2509.17449v2 Announce Type: replace Abstract: Queer vernacular is rarely studied in NLP, despite advancements in resources and evaluation for other sociolects and informal language. Because of this, NLP systems…

Source: arXiv cs.CL Leonor Veloso, Lea Hirlimann, Lucija Mihi\'c Zidar, Philipp Wicke, Valentin Hofmann, Hinrich Sch\"utze
AI

TCS-BENCH: Benchmarking State-of-the-Art Generative AI Theoretical Computer Science Research Ability

arXiv:2608.09538v2 Announce Type: replace Abstract: We introduce TCS-Bench, a benchmark for evaluating Large Language Models (LLMs) on research-level Theoretical Computer Science (TCS) proof generation. TCS-Bench…

Source: arXiv cs.CL Vincent Cohen-Addad, Dimitris Paparas, Ernest van Wijland, Max Springer, Julien Canitrot-Paradis, Honghao Lin, David Woodruff, Adarsh Kumarappan, Rajesh Jayaram, Rudrajit Das, Lalit Jain, Ola Svensso…
AI

Mawqif-XT: An Arabic Benchmark Dataset for Cross-Target Stance Detection

arXiv:2608.09539v2 Announce Type: replace Abstract: Publicly available Arabic datasets for target-specific stance detection remain limited, particularly for evaluating cross-target generalization. This paper presents…

Source: arXiv cs.CL Rasha Albalawi, Nuha Albadi, Hamzah Luqman, Maram Kurdi, Saad Ezzini, Asma Yamani, Ahmed Ashraf
AI

Measuring Task-Agnostic Training Data Influence Across Language Model Pretraining

arXiv:2608.13515v1 Announce Type: new Abstract: Measuring training data influence consistently across language model pretraining is challenging. It is difficult to select downstream tasks or validation sets…

Source: arXiv cs.CL Yuto Nishida, Hirokazu Kiyomaru, Yusuke Oda, Takashi Kodama, Chaoran Liu, Daisuke Kawahara, Yusuke Miyao, Max M\"uller-Eberstein, Masaru Isonuma
AI

On Measuring Semantic Preservation in Legal Ontology Learning

arXiv:2608.12326v1 Announce Type: new Abstract: Ontology learning transforms unstructured text into structured representations for automated reasoning. Yet structuring information risks losing it, and current evaluation…

Source: arXiv cs.CL Albert Sadowski, Jaros{\l}aw A. Chudziak
AI

Beyond Retrieval: Query-Conditioned Reuse of Long-Horizon Agent Trajectories

arXiv:2608.12847v1 Announce Type: cross Abstract: Retrieval can identify a past trajectory that may matter, yet it does not specify how an acting agent should use that trajectory after users, entities, constraints, or…

Source: arXiv cs.CL Yifei Li, Heng Wang, Lingling Zhang, Muye Huang, Xinyu Zhang, Jiashuai Liu, Hang Yan, Rongman Xu
AI

Unmasking Conversational Bias in AI Multiagent Systems

arXiv:2501.14844v3 Announce Type: replace Abstract: Detecting biases in the outputs produced by generative models is essential to reduce the potential risks associated with their application in critical settings.…

Source: arXiv cs.CL Erica Coppolillo, Giuseppe Manco, Luca Maria Aiello
AI

From Observation to Intervention: Memory in Brains and Large Language Models

arXiv:2608.12377v1 Announce Type: cross Abstract: Brains and large language models (LLMs) are fundamentally different memory systems, but they can be compared through shared functional questions: where memory-related…

Source: arXiv cs.CL Morteza Salehjahromi, Shayan A. Zadegan, Amgad Muneer, Jia Wu
AI

ERSkill: Evolving for Skill-Guided Adaptive Memory Retrieval

arXiv:2608.12720v1 Announce Type: new Abstract: While Large Language Model (LLM) agents increasingly rely on long-term memory for persistent interactions, the retrieval mechanisms governing this memory are rarely…

Source: arXiv cs.CL Haolong Chen, Liang Zhang, Zhuo Li, Lei Xue, Guanrxu Zhu
AI

Decoupled Contrastive Decoding via Expert-Aligned Drafting

arXiv:2608.12913v1 Announce Type: new Abstract: Contrastive Decoding (CD) improves generation quality, but its amateur-model pass makes decoding expensive. Accelerating CD with speculative decoding raises a…

Source: arXiv cs.CL Zhixuan Liu, Zhichen Dong, Yuanfu Wang, Chao Yang
AI

Revolutionizing Finance with LLMs: An Overview of Applications and Insights

arXiv:2401.11641v5 Announce Type: replace Abstract: In recent years, Large Language Models (LLMs) like ChatGPT have seen considerable advancements and have been applied in diverse fields. Built on the Transformer…

Source: arXiv cs.CL Huaqin Zhao, Zhengliang Liu, Zihao Wu, Yiwei Li, Tianze Yang, Peng Shu, Shaochen Xu, Haixing Dai, Lin Zhao, Hanqi Jiang, Yi Pan, Junhao Chen, Yifan Zhou, Zheyuan Zhang, Zeyu Zhang, Ruitong Sun, Gengc…
AI

AQuA: Recursively Self-Improving Quantitative Trading Research Agents

arXiv:2608.12841v1 Announce Type: new Abstract: We study recursive self-improvement at the level of quantitative-investment research: whether an autonomous system can use evidence from earlier experiments to improve the…

Source: arXiv cs.CL Jiacheng Guo, Suozhi Huang, Yunlong Gao, Zihao Li, Jian Ge, Xu Kuang, Mengdi Wang
AI

SDAM: Structure-Difference-Aware Memory Evolution for Complex Text-to-SQL

arXiv:2608.12338v1 Announce Type: new Abstract: Text-to-SQL aims to convert natural language questions into executable SQL queries. While memory-based agent system improves complex SQL generation, existing memory design…

Source: arXiv cs.CL Keyan Xu, Dingzirui Wang, Xuanliang Zhang, Qingfu Zhu, Wanxiang Che
AI

MARC v1: An Open-Source Multi-Agent Framework for Clinical AI Reasoning and Coordination

arXiv:2608.13476v1 Announce Type: cross Abstract: We present Multi-Agent Reasoning and Coordination (MARC), an open-source framework that replaces monolithic LLM prompting with deterministic multi-agent orchestration…

Source: arXiv cs.CL Saisha Shetty, Satvik Tripathi, Austin Lin, Colin Zhao, Theodore Kim, Don Enwerem, Jacinta Arnold, Shahriar Faghani, Tessa S Cook
AI

Large Language Models Persuade Without Planning Theory of Mind

arXiv:2602.17045v2 Announce Type: replace Abstract: A growing body of work attempts to evaluate the theory of mind (ToM) abilities of humans and large language models (LLMs) using static, non-interactive…

Source: arXiv cs.CL Jared Moore, Rasmus Overmark, Ned Cooper, Beba Cibralic, Nick Haber, Cameron R. Jones
AI

The "Knowledge-Behavior Gap" in Cultural Taboo Safety of Large Language Models

arXiv:2608.12341v1 Announce Type: new Abstract: Cultural taboo safety is essential for deploying large language models (LLMs), as culturally insensitive outputs may cause offense or even social harm. However, existing…

Source: arXiv cs.CL Ying He, Sihang Jiang, Xingzhou Chen, Zhouhong Gu, Yiwei Gu, Minggui He, Shimin Tao, Hongxia Ma, Yanghua Xiao
AI

Token Reduction Is Not Cost Reduction

arXiv:2607.12161v5 Announce Type: replace Abstract: Token-reduction tools for coding agents are often evaluated by the number of tokens they remove, but token count alone does not determine end-to-end inference cost. We…

Source: arXiv cs.CL Sarel Weinberger, Amir Hozez
AI

CoLA: Cross-Modal Low-rank Adaptation for Multimodal Downstream Tasks

arXiv:2604.03314v3 Announce Type: replace-cross Abstract: Foundation models have revolutionized AI, but adapting them efficiently for multimodal tasks, particularly in dual-stream architectures composed of unimodal…

Source: arXiv cs.CL Wish Suharitdamrong, Tony Alex, Muhammad Awais, Sara Atito
AI

Toward Federated Large Language Models in Medicine: A Parameter-Efficient Framework for Privacy-Preserving, Multi-Institutional Adaptation

arXiv:2601.22124v3 Announce Type: replace Abstract: Large language models (LLMs) are increasingly adapted for medical applications, but most are trained using data from a single institution because privacy and…

Source: arXiv cs.CL Anran Li, Yuanyuan Chen, Wenjun Long, Yu Yin, Yan Hu, Hyunjae Kim, Weipeng Zhou, Yujia Zhou, Hongyi Peng, Yang Ren, Xuguang Ai, Zhenyue Qin, Ming Hu, Xiaoxiao Li, Han Yu, Yih-Chung Tham, Lucila Ohno-…
AI

Predicting consumer-technology ownership without a diffusion history

arXiv:2608.12344v1 Announce Type: new Abstract: We test whether the perceived attributes of a consumer technology predict how widely it is owned. In a 2022 Prolific survey of US adults (n = 678), respondents rated 65…

Source: arXiv cs.CL Irina Vartanova, Niels Selling, Jennifer Viberg Johansson, Pontus Strimling
AI

AnchorSIPS: A Synthetic Dataset and Evaluation Resource for Evidence-Supported Psychosis-Risk Symptom Measurement

arXiv:2608.12329v1 Announce Type: new Abstract: Progress on AI for psychosis-risk assessment is limited by a data-access bottleneck. Real clinical interviews are difficult to share because of privacy, governance, and…

Source: arXiv cs.CL Guilherme C. Oliveira, Stephanie Fong, Zimu Wang, Clarice Lee, Xiangyu Zhao, Duy Khoa Pham, Duong Nhu, Yiwen Jiang, Jiahe Liu, Zhongxing Xu, Dwarikanath Mahapatra, Dominic Dwyer, Zongyuan Ge
AI

Beyond Local Accuracy: A Protocol-Level Identifiability Audit for Controlled LLM Reasoning Evaluation

arXiv:2608.13326v1 Announce Type: new Abstract: LLM benchmark scores can be precise even when the observation protocol does not identify the behavioral property they are intended to measure. In a controlled,…

Source: arXiv cs.CL Junhao Luo (School of Statistics,Data Science, Southwestern University of Finance,Economics), Ning Huang (School of Statistics,Data Science, Southwestern University of Finance,Economics), Ziqi Sha (S…
AI

Cat-DPO: Category-Adaptive Safety Alignment

arXiv:2604.17299v3 Announce Type: replace Abstract: Aligning large language models with human preferences must balance two competing goals: responding helpfully to legitimate requests and reliably refusing harmful ones.…

Source: arXiv cs.CL Tiankai Yang, Yi Nian, Xinyuan Li, Ruiyao Xu, Henry Peng Zou, Kaize Ding, Xiyang Hu, Yan Liu, Yue Zhao
AI

Novels generated by language models show compressed formal variation

arXiv:2608.12630v1 Announce Type: new Abstract: While large language models can generate entire novels, there is little information about the level of formal variation in their output over many generations. Rather than…

Source: arXiv cs.CL Mehdy Sedaghat Payam, Justin Quinn
AI

Masked diffusion LLMs can use EoS tokens for hidden reasoning

arXiv:2603.05197v2 Announce Type: replace Abstract: Diffusion LLMs have been proposed as an alternative to autoregressive LLMs. Curiously, they are especially capable if the generation length, i.e., the number of tokens…

Source: arXiv cs.CL Sarah Breckner, Sebastian Schuster
AI

LigBench: A Unified and Human-Aligned Benchmark for LLM-based Research Idea Generation

arXiv:2608.13136v1 Announce Type: new Abstract: With the rapid advancement of large language models (LLMs), research idea generation has attracted increasing attention. Existing approaches enable LLMs to retrieve…

Source: arXiv cs.CL Chenrun Wang, Mingxuan Zhu, Tiancheng Huang, Wenjie Li, Yujie Zhang, Zichen Zhu, Zhiying Zou, Kai Yu, Lu Chen
AI

Tracing Provenance and Detecting Tampering with Complementary LLM Watermarks

arXiv:2608.12713v1 Announce Type: cross Abstract: Watermarking LLM-generated text is an important task for tracing its provenance. Existing LLM watermarks preserve provenance under editing, but this same robustness…

Source: arXiv cs.CL Xiaoyan Feng, Yanjun Zhang, He Zhang, Leo Yu Zhang, Shirui Pan
AI

CASA: Content-Acoustic Speaking Assessment with Speech Encoder and Large Language Model

arXiv:2608.13101v1 Announce Type: new Abstract: Research on automatic speaking assessment (ASA) has increasingly adopted multimodal speech large language models to assess learners' speaking performance. However,…

Source: arXiv cs.CL Nhan Phan, Ilona L\"ahteenm\"aki, Anna von Zansen, Olli-Pekka Pauna, Yaroslav Getman, Tam\'as Gr\'osz, Mikko Kurimo