Light-Omni: Reflex over Reasoning in Agentic Video Understanding with Long-Term Memory
Paper • 2607.05511 • Published • 21
Chengsong Huang
ChengsongHuang
AI & ML interests
None yet
Recent Activity
upvoted a paper 5 days ago
PACE: A Proxy for Agentic Capability Evaluation upvoted a paper 11 days ago
TUA-Bench: A Benchmark for General-Purpose Terminal-Use AgentsOrganizations
upvoted a paper 4 days ago
upvoted a paper 5 days ago
upvoted a paper 11 days ago
upvoted 9
papers about 1 month ago
Agents' Last Exam
Paper • 2606.05405 • Published • 377
LatentSkill: From In-Context Textual Skills to In-Weight Latent Skills for LLM Agents
Paper • 2606.06087 • Published • 67
AffordanceVLA: A Vision-Language-Action Model Empowering Action Generation through Affordance-Aware Understanding
Paper • 2606.06155 • Published • 10
Neural Networks Provably Learn Spectral Representations for Group Composition
Paper • 2606.02993 • Published • 6
Small RL Controller, Large Language Model: RL-Guided Adaptive Sampling for Test-Time Scaling
Paper • 2606.03102 • Published • 14
Speculative Pipeline Decoding: Higher-Accruacy and Zero-Bubble Speculation via Pipeline Parallelism
Paper • 2605.30852 • Published • 10
ZeroUnlearn: Few-Shot Knowledge Unlearning in Large Language Models
Paper • 2605.18879 • Published • 8
Agent Explorative Policy Optimization for Multimodal Agentic Reasoning
Paper • 2605.28774 • Published • 93
Share More, Search Less: Collaborative Parallel Thinking for Efficient Test-Time Scaling
Paper • 2605.27030 • Published • 32
upvoted 5
papers about 2 months ago
Language Models Need Sleep
Paper • 2605.26099 • Published • 13
SkillOpt: Executive Strategy for Self-Evolving Agent Skills
Paper • 2605.23904 • Published • 254
You Only Need Minimal RLVR Training: Extrapolating LLMs via Rank-1 Trajectories
Paper • 2605.21468 • Published • 51
The Unlearnability Phenomenon in RLVR for Language Models
Paper • 2605.16787 • Published • 6
Process Rewards with Learned Reliability
Paper • 2605.15529 • Published • 53
upvoted 3
papers 2 months ago