TimesFM-3: A zero-shot foundation model for multivariate forecasting
Data Management
Topic - Edition
AI Research
Your LLM Can Return Perfect JSON and Still Be Wrong
What I learned after thinking more carefully about Structured Outputs on messy, incomplete data The post Your LLM Can Return Perfect JSON and Still Be Wrong appeared first on Towards Data Science.
FAQ as RAG: When You Get to Design the Corpus
Enterprise Document Intelligence [Vol.1 #B2] - The FAQ inverts every brick of the standard RAG pipeline. Parsing is trivial, retrieval doubles as a cache, and few-shot prompting becomes a retrieval problem too The post…
Why RAG Complexity Should Be Earned
A framework for building RAG pipelines that introduces complexity in response to observed failure modes, from lexical and hybrid search to reranking and agentic information seeking The post Why RAG Complexity Should Be…
AgentOps Is Not MLOps: What Breaks in Your Monitoring Stack When Agents Go to Production
The five MLOps monitoring assumptions agents break, and which inherited signals now pass failed runs as healthy. The post AgentOps Is Not MLOps: What Breaks in Your Monitoring Stack When Agents Go to Production appeared…
EXPOSE: Explainable and Domain-Robust Embeddings from Pathology Vision Foundation Models using Sparse Autoencoders
arXiv:2608.28191v1 Announce Type: cross Abstract: Vision Foundation Models (VFMs) are widely used in computational pathology but remain sensitive to domain shifts arising from variations in staining, tissue preparation,…
Localizing Global Discrepancies: Marginal Contributions and Contextual Anomaly Detection
arXiv:2608.28375v1 Announce Type: cross Abstract: Global goodness-of-fit and discrepancy statistics can establish that a sample departs from a reference distribution without identifying which observations drive the…
Biases in Expected Goals Models Confound Finishing Ability
arXiv:2401.09940v2 Announce Type: replace Abstract: Expected Goals (xG) has emerged as a popular tool for evaluating finishing skill in soccer analytics. It involves comparing a player's cumulative xG with their actual…
More Expressive Feedforward Layers: Part I. Token-Adaptive Mixing of Activations
arXiv:2605.26647v2 Announce Type: replace Abstract: Feedforward network (FFN) layers account for a large fraction of parameters and nonlinear expressivity in Transformer-based large language models (LLMs). Despite the…
VISTA: Verifier-Informed Student-to-Teacher Adaptation for On-Policy Self-Distillation
arXiv:2608.28306v1 Announce Type: new Abstract: On-policy self-distillation (OPSD) improves reasoning by training a problem-only student on its own rollouts using dense token-level supervision from a privileged teacher…
Aero Hand Open: A Simulation-Ready Tendon-Driven Hand for Dexterous Manipulation Learning
arXiv:2608.28578v1 Announce Type: cross Abstract: Tendon-driven hands are anthropomorphic, and moving the actuators off the joints is what makes a hand of this capability affordable to build. Two effects produce that…
An Enclosed Mode Is a Gauge Choice: Topology Relative to Reach in Certified Code World Models
arXiv:2608.28541v1 Announce Type: new Abstract: A code world model accepted by a sampling gate can be exactly right on everything the gate can see and arbitrarily wrong beyond it. We characterize what a certified model…
Parser States Already Know: Structure-Conditioned KV Persistence for Structured Generation
arXiv:2608.28276v1 Announce Type: new Abstract: Structured generation underpins large language model (LLM) agents that produce JSON, SQL, and function calls, where a single wrong field can cause the downstream action to…
Optimal Transport for Network Comparison: A Review with Machine Learning Applications
arXiv:2608.27500v1 Announce Type: cross Abstract: Network comparison using optimal transport is a growing area of research in network science. Unlike standard graph metrics, optimal transport computes both network…
RealSWE: A Compositional Evaluation of Coding Agents under Realistic User Requests
arXiv:2608.27831v1 Announce Type: cross Abstract: Coding agents are now commonly evaluated on the SWE-bench family of benchmarks, whose tasks are built from curated GitHub issues--long, structured, and information-rich.…
On the Depth Scalability of Logic Gate Networks
arXiv:2607.21633v3 Announce Type: replace Abstract: Logic Gate Networks (LGNs) compute through compositions of Boolean operations, yet existing LGNs do not reliably benefit from increased depth. We identify two causes:…
FedEHR-Agents: Federated Agentic Optimization for Automated EHR Modeling
arXiv:2608.27856v1 Announce Type: new Abstract: Recent advances in large language models are enabling autonomous clinical agents to perform increasingly complex electronic health record (EHR) modeling workflows.…
A Method for Layer Bit-Width Allocation in LLM Quantization via Performance Maximization Under a Quality-Degradation Constraint
arXiv:2608.28003v1 Announce Type: new Abstract: This paper proposes a layer bit allocation method for Gemma-3-1B, formulating the problem as performance maximization (latency decrease) given a degradation budget…
GRACE:Gradient-guided Coreset Selection for LLM Unlearning
arXiv:2608.28361v1 Announce Type: cross Abstract: Machine Unlearning methods for Large Language Models typically assume pre-specified forget and retain sets. In realistic settings, however, requests may provide only a…
Class Incremental Continual Learning with Self-Organizing Maps and Synthetic Replay
arXiv:2508.21240v2 Announce Type: replace Abstract: This work introduces a novel generative continual learning framework based on self-organizing maps (SOMs), a brain-inspired natural computing model, extended with…
Loading more...
342 items available