VDE Bench: Evaluating The Capability of Image Editing Models to Modify Visual Documents Paper • 2602.00122 • Published 27 days ago • 11
ScaleNav: Scalable Internet Video Pretraining for Language-Conditioned Local Navigation Paper • 2610.25690 • Published 23 days ago • 39
EmbodiedCLBench: Evaluating Continual Learning for Self-Evolving Embodied Agents Paper • 2610.13021 • Published Oct 9 • 30
On-Policy Parameter Update Direction Underlies Generalization in LLM Post-Training Paper • 2609.36659 • Published Sep 29 • 15
A Missing Piece for Trustworthy AI Reviewers: From Benchmarking Rhetorical Robustness to SciCore Review Paper • 2609.39027 • Published Sep 30 • 20
Raven: The Harness of Harnesses for Composable Agentic Intelligence Paper • 2609.33439 • Published Sep 27 • 100
CoWindow Attention: Full Causal Coverage Is a Collective Property Paper • 2609.32704 • Published Sep 26 • 18
MassAlloc Attention: Let Attention Allocate Its Own Compute Paper • 2609.32712 • Published Sep 26 • 26
Random Attention: Rethinking KV Cache Eviction for Efficient Reasoning Paper • 2609.03430 • Published Sep 3 • 98
It Takes Two to Match: Co-Evolving Generative Retriever with Reinforcement Learning Paper • 2609.00638 • Published Sep 1 • 39
SMELT: Scaling Laws for Compute-Matched MoE Looped Transformers Paper • 2609.01343 • Published Sep 1 • 63
UrbanGround: From Local Perception to Spatial Agency in a Real-Scale City Paper • 2608.27456 • Published Aug 27 • 54
Running Featured 563 Agent Memory Leaderboard 🧠 563 Unified memory evaluation · Results expected August 12.
Agentic ESOpt: Fine-Tuning Long-Horizon LLM Agents with Minimal GPU Requirements Paper • 2608.17310 • Published Aug 18 • 70
How Can Rhetoric Reward-Hack AI Reviewers? Dissecting Rhetorical Sensitivity in AI-Based Peer Review Paper • 2608.08975 • Published Aug 10 • 21
Search Beyond What Can Be Taught: Evolving the Knowledge Boundary in Agentic Visual Generation Paper • 2607.05382 • Published Jul 9 • 43