Discord is making its public communities more searchable, and people have concerns
In December, messages from Discord's public discoverable servers will begin appearing in search engine results.
Daily edition · Information Retrieval
The daily ledger
TILens turns technical updates into a focused daily brief: official releases, trusted reporting, and practitioner analysis, deduplicated and organized by topic.
72 articles · 5 sources · 71 papers ·
Top topics: Information Retrieval · AI · AI Research
On the Runway Cascade of Transformers for Language Modeling
arXiv:2601.14522v2 Announce Type: replace Abstract: In decoder-only (causal) transformers, the computation graph created by causal masking routes information through both direct-path attention and indirect paths formed…
Head Dimension Matters in Language Models for Long-Context Retrieval
arXiv:2610.32213v1 Announce Type: new Abstract: Multi-head attention retrieves and combines context representations through query--key interactions and value aggregation, with head dimension constraining the per-head…
Novel or Not? PatEx-Gym: Agentic Prior-Art Search for Novelty Assessment in Patent Examination
arXiv:2610.33503v1 Announce Type: new Abstract: Patent examination is a challenging real-world task that requires agents to discover sparse prior art, iteratively refine queries, inspect technical evidence, and produce…
How Much Fresh Data Should CTR Recalibration Use? A Temporal Evaluation of Post-hoc Calibration
arXiv:2610.33168v1 Announce Type: cross Abstract: Offline evaluation of click-through rate (CTR) models still defaults to random splits, although deployed models score future traffic and downstream systems consume…
Theoretically Sound Item Similarity Measures for Recommender Systems
arXiv:2610.34402v1 Announce Type: new Abstract: Quantifying the similarity between items is fundamental to neighborhood-based collaborative filtering, yet many commonly used similarity measures are heuristics that lack…
DyHist: Query-Aware Historical Dynamics Modeling for Temporal Knowledge Graph Extrapolation
arXiv:2610.33473v1 Announce Type: new Abstract: Temporal Knowledge Graph (TKG) extrapolation aims to predict future facts from observed historical events. Existing methods usually achieve this goal by jointly modeling…
When Fusion Order Matters: Insights on Progressive Multimodal Representation Learning for Cross-modal Retrieval
arXiv:2610.35125v1 Announce Type: cross Abstract: Multimodal video retrieval combines visual, acoustic, and speech information, yet how their fusion order should depend on the data and the retrieval query remains…
HARP-LoRA: Hierarchy-Conditioned Rank Projection for Low-Rank Adaptation in Scientific Table Understanding
arXiv:2610.34589v1 Announce Type: cross Abstract: Tabular data is widely used in scientific applications, where complex layouts, including multi-level headers, merged cells, captions, and footnotes, make information…
LoopGR: Parameter-Efficient Scaling for Generative Recommendation via Recurrent Depth
arXiv:2610.34157v1 Announce Type: new Abstract: Generative recommendation formulates item recommendation as autoregressive generation rather than a discriminative scoring problem. Although empirical studies exhibit…
Learning to Remember: Advances in Memory Mechanisms for Large Language Models
arXiv:2610.35089v1 Announce Type: new Abstract: Memory has become a central mechanism for extending large language models (LLMs) beyond fixed context windows, stateless interaction, and static parametric knowledge. This…
Beyond "[at]": A Large-Scale Measurement of Email Address Presentation on Computer Science Scholars' Homepages
arXiv:2610.35499v1 Announce Type: new Abstract: Publishing an email address makes a scholar reachable, but also exposes it to automated collection. Yet how email addresses are presented on the Web has not been measured…
Towards a Unified Framework of Optimal Input-Side Dimensional Configuration for Deep CTR Prediction
arXiv:2610.35695v1 Announce Type: new Abstract: Deep click-through rate (CTR) prediction has achieved substantial success through increasingly expressive feature interaction architectures. However, predictive…
Lessons from Luck: Do LLM-Written Lessons Carry Chance into an Agent's Next Decision?
arXiv:2610.33029v1 Announce Type: cross Abstract: Self-improving agents write lessons from the outcomes of their runs; when outcomes are noisy, a lesson can carry chance into later decisions. We measure one link of this…
Factual Yet One-Sided: Stance Poisoning and Evidence Balancing in Retrieval-Augmented Generation
arXiv:2610.34294v1 Announce Type: cross Abstract: The stance expressed in responses from retrieval-augmented generation systems is significantly influenced by the stance distribution of the retrieved materials. Existing…
The Geometry of Agent Memory: Forecasting Retrieval-Bound Memory Failures, and Characterizing Its Limits
arXiv:2610.26433v2 Announce Type: replace-cross Abstract: We study whether geometric relationships between conversation turns, memory texts, and queries can predict answer correctness before generation. We evaluate four…
Good Scores, Bad Data: A Metric for Multimodal Coherence
arXiv:2603.25924v2 Announce Type: replace-cross Abstract: Multimodal AI systems are evaluated by downstream task accuracy, but high accuracy does not mean the underlying data is coherent. A model can score well on…
Discovering Topics from Linear Autoencoders
arXiv:2610.34739v1 Announce Type: new Abstract: Linear recommenders and topic models are similar in that they implicitly learn from co-occurrences of items. However, there has been little study of how these two model…
Agreement Between Reconstructed and Native GDELT GKG Records: A Field-Level Baseline
arXiv:2610.35358v1 Announce Type: cross Abstract: The Global Knowledge Graph (GKG) of the Global Database of Events, Language, and Tone (GDELT) characterizes news articles using named entities, topics, quantitative and…
$\Delta\tau$-Bench: Pushing Agents Toward a Moving Capability
arXiv:2610.34238v1 Announce Type: cross Abstract: In this paper, we introduce $\Delta\tau$-Bench, an executable agent benchmark that models the structural evolution of large tool ecosystems. In $\Delta\tau$-Bench,…
Loading more...
Showing 1 day · 72 items available