Latest in AI and developer tools

Today's trail

updated 11m ago

Last hour Today

Pulse · easternherald.com

easternherald.com · Oct 31

PageLens Launches Agency Model, Letting Agencies Sell AI Search Visibility Under Their Own Brand

Pulse · datacenters.economictimes.indiatimes.com

datacenters.economictimes.indiatimes.com · Oct 31

DSCI releases India-specific agentic AI liability guide

The Data Security Council of India (DSCI) has published an India-focused guide on artificial intelligence (AI) liability for agentic AI systems. This guide clarifies how responsibility is allocated across the AI value chain if an agent operates autonomously or deviates from its tasks.

Pulse

Top picks this weekarXiv

arXiv

Oct 29

Elucidating the Design Space of LM Data Attribution

Data attribution methods for Language Models (LMs) are typically evaluated using downstream tasks like fact retrieval. However, existing evaluations vary multiple dataset properties simultaneously, making it impossible to isolate exactly why an attribution algorithm fails. To diagnose these failures, we explore the design space of LLM data attribution, with a primary focus on evaluation. We introduce the Controlled Attribution Benchmark (CATT) for fact tracing, in which we fine-tune LLMs on entirely fictitious knowledge, providing unambiguous ground truth for attribution. This synthetic setup allows us to systematically alter one dataset configuration at a time, such as document redundancy and lexical distractors. With this configurable evaluation, we demonstrate that redundancy and distractors consistently degrade attribution performance. Rather than proposing a new estimator, we examine two design choices that are underexplored: the loss used to compute gradients and how per-token attribution scores are aggregated into a document score. We find that the true causal evidence within a training document is highly localized, but standard methods dilute this evidence into noise by…

Top picks

All arXiv Hugging Face GitHub Hacker News

Latest Top this week

arXiv

Sep 18

Visual Navigation Transformer with Pose Attention

Learned navigation policies typically consume observations as a temporally ordered history, with positional encodings tying each observation to when it was seen, making it difficult to reuse experience from earlier traversals of an environment. Systems that do reuse such…

arXiv

Sep 18

Improving scoring functions for protein-protein docking with LambdaLoss

Modeling protein-protein interactions requires accurate scoring functions that can rank potential poses (conformations) of a protein-protein complex to differentiate near-native poses from incorrect ones. Here, we propose a general framework for improving protein-protein pose…

arXiv

Sep 18

Information-Gain Rewards over Diversity-Pruned Tests: GT-Anchored Verifier Co-Training for Reliable Code Generation

Self-play methods that co-train a single language model as both coder and test author promise to move code-generation RL beyond fixed test suites, but they suffer from two coupled pathologies: permissiveness collapse, where pass-rate rewards are maximised by trivial,…

arXiv

Sep 18

Hand-Aware Transition Modeling for Bimanual Procedural Anomaly Detection

Procedural anomaly detection in bimanual assembly requires judging each hand action against the execution so far. A corrective action may look unusual in isolation, while a visually plausible action can violate the order of the procedure. We present HACT, a transition model…

This week in Multimodal

This week

Get the morning digest

Today's trail

Pulse

Top picks

Today's trail

This week in Multimodal

Most active this week

Rising tools