ShallowStream: Index Shallow then Answer Deep for Streaming Video Understanding
Paper • 2609.02780 • Published • 2
GuoLiangTang
Tommy930
AI & ML interests
LLM，NLP，ML
Recent Activity
upvoted a paper about 8 hours ago
ShallowStream: Index Shallow then Answer Deep for Streaming Video Understanding upvoted a paper about 8 hours ago
The Attention Triangle in Audio-Video Models upvoted a paper about 11 hours ago
RISE: Recursive Improvement via Self-Extrapolating Policy DistillationOrganizations
None yet
upvoted 2
papers about 8 hours ago
upvoted 3
papers about 11 hours ago
upvoted a paper 1 day ago
upvoted 3
papers 2 days ago
VeriPhy: Agentic Physical Reasoning for World Model Evaluation and Refinement
Paper • 2609.03153 • Published • 12
RoboTok: An Internet-Scale Data Engine for Human Demonstration Retrieval and Dexterous Manipulation Learning
Paper • 2609.03199 • Published • 116
Compile by Training: Turning Natural-Language Specifications into Local Neural Functions
Paper • 2609.04199 • Published • 374
upvoted 11
papers 4 days ago
The Missing Temporal Link: Temporal Context Routing for Script-Driven Audio-Video Generation
Paper • 2609.02367 • Published • 33
FlashRender: Few-Step Generative Rendering via Camera-Controlled Video MeanFlow
Paper • 2609.03563 • Published • 19
Principia: Relational Physics Tests for Video Models
Paper • 2609.04200 • Published • 16
WorldReward: Reward Modeling for Camera-Conditioned World Models
Paper • 2609.03952 • Published • 24
Terminal-Universe: Turning Agent Trajectories into Scalable Terminal Environments
Paper • 2609.04148 • Published • 276
CORE: Improving Compositional Reasoning in MLLM Embedding via Reranker Distillation
Paper • 2609.04083 • Published • 25
Rethinking On-Policy Distillation of Large Language Models II: One Training Example
Paper • 2609.04172 • Published • 81
Random Attention: Rethinking KV Cache Eviction for Efficient Reasoning
Paper • 2609.03430 • Published • 166
LLaDA-Image: Building Strong Image Generators with Fully Open Training Recipes
Paper • 2609.03796 • Published • 228
EarlyEval: Cheaper Agent Evaluation via Early Outcome Prediction
Paper • 2609.02783 • Published • 115
VibeVoice-ASR-Streaming Technical Report
Paper • 2609.02812 • Published • 16