History Replays Itself: Unleashing Long-Context Capability in Linear Attention Paper • 2610.15715 • Published Oct 11 • 21
APEX-Harm: Evaluating Agent Safety in Shared Professional Workspaces Paper • 2610.13623 • Published Oct 9 • 23
Self-Generated Feedback Destabilizes Test-Time Training: A Causal Decomposition of Long-Horizon Adaptation Paper • 2610.05076 • Published Oct 4 • 23
Architect-Ant: Editable Automatic Furnishing of Architectural Floor Plans Paper • 2606.10953 • Published Sep 30 • 29
DiSCO: Defending text-to-image generation through distribution-guided contrastive prompt optimization Paper • 2608.17067 • Published Aug 17 • 23
TAPS: Task Aware Proposal Distributions for Speculative Sampling Paper • 2603.27027 • Published Mar 27 • 146
Running on CPU Upgrade Agents 1.04k Open VLM Leaderboard 🌎 1.04k VLMEvalKit Evaluation Results Collection
TTRV: Test-Time Reinforcement Learning for Vision Language Models Paper • 2510.06783 • Published Oct 8, 2025 • 13