Suppressing the Shortcut Hidden Behind the Gains of VideoLLM Fine-Tuning Paper • 2611.25776 • Published 4 days ago • 5
A CPU Inside an LLM: Zero-Gradient Compilation of Exact Circuits into Pretrained Weights Paper • 2611.26450 • Published 4 days ago • 7
Do Probing and Steering Favor the Same Directions Within and Across Language Models? Paper • 2611.19499 • Published 9 days ago • 6
MInfoVisQA: A Multilingual Benchmark for Information-Rich Visual Question Answering Paper • 2611.21644 • Published Oct 14 • 6
RL Post-Training in Diffusion Transformers Is Activation Steering Paper • 2611.26627 • Published 4 days ago • 19
Squoosh Bench: Evaluating UX-1 on 318 Historical Website A/B Tests Paper • 2611.25200 • Published 5 days ago • 3
In Situ Training of Optical Neural Networks by Coding Agents Paper • 2611.23875 • Published 5 days ago • 4
Training Vision Models for LLM-Driven Weight-Space Programming Paper • 2611.26408 • Published 4 days ago • 15
Twice-Told Critiques: Claim-Level Homogenization of Peer Review in the LLM Era Paper • 2611.26286 • Published 4 days ago • 10
Accelerating Mixture of Block Attention via Dynamic Routing, KV-Centric Execution and Runtime Pipelining Paper • 2611.26268 • Published 4 days ago • 18
TwinLab-Bench: Evaluating AI Scientists in Agentic Twins of Real Labs Paper • 2611.26248 • Published 4 days ago • 5
System 1 agents: a method for local, reliable and fast agentic AI Paper • 2611.21053 • Published 7 days ago • 6
AltRA-Test: An Alternative Annotator Test for LLM Judges Without Shared Annotators Paper • 2611.26073 • Published 4 days ago • 23
Phantom Success, Silent Failure: Auditing the Success Checkers of Simulated Manipulation Benchmarks Paper • 2611.25179 • Published 5 days ago • 5
Mind2Act World: A Diagnostic Benchmark for Embodied Mind, Physical Action, and Mind-Action Composition in Robotic Manipulation Paper • 2611.26444 • Published 4 days ago • 53
S1CogBench: What System One Decision Models Can and Cannot Do on Cognitive Experiments Paper • 2611.00911 • Published 9 days ago • 5
DailySafe: Benchmarking Dynamic Safety Awareness in Everyday Multi-Turn Multimodal Interactions Paper • 2611.26298 • Published 4 days ago • 5