Persistent Visual Memory: Sustaining Perception for Deep Generation in LVLMs
Paper • 2605.00814 • Published • 11
GuoLiangTang
Tommy930
AI & ML interests
LLM，NLP，ML
Recent Activity
upvoted a paper about 8 hours ago
Persistent Visual Memory: Sustaining Perception for Deep Generation in LVLMs upvoted a paper about 11 hours ago
T^2PO: Uncertainty-Guided Exploration Control for Stable Multi-Turn Agentic Reinforcement Learning upvoted a paper about 12 hours ago
Motion-Aware Caching for Efficient Autoregressive Video GenerationOrganizations
None yet
upvoted a paper about 8 hours ago
upvoted a paper about 11 hours ago
upvoted 7
papers about 12 hours ago
Motion-Aware Caching for Efficient Autoregressive Video Generation
Paper • 2605.01725 • Published • 1
AcademiClaw: When Students Set Challenges for AI Agents
Paper • 2605.02661 • Published • 7
Perceptual Flow Network for Visually Grounded Reasoning
Paper • 2605.02730 • Published • 1
PhysicianBench: Evaluating LLM Agents in Real-World EHR Environments
Paper • 2605.02240 • Published • 3
ComboStoc: Combinatorial Stochasticity for Diffusion Generative Models
Paper • 2405.13729 • Published • 6
MolmoAct2: Action Reasoning Models for Real-world Deployment
Paper • 2605.02881 • Published • 115
From Context to Skills: Can Language Models Learn from Context Skillfully?
Paper • 2604.27660 • Published • 116
upvoted 3
papers 1 day ago
End-to-End Autoregressive Image Generation with 1D Semantic Tokenizer
Paper • 2605.00503 • Published • 4
UniVidX: A Unified Multimodal Framework for Versatile Video Generation via Diffusion Priors
Paper • 2605.00658 • Published • 74
From Skill Text to Skill Structure: The Scheduling-Structural-Logical Representation for Agent Skills
Paper • 2604.24026 • Published • 15
upvoted 4
papers 4 days ago
Learning from Noisy Preferences: A Semi-Supervised Learning Approach to Direct Preference Optimization
Paper • 2604.24952 • Published • 4
Step-level Optimization for Efficient Computer-use Agents
Paper • 2604.27151 • Published • 14
Nemotron 3 Nano Omni: Efficient and Open Multimodal Intelligence
Paper • 2604.24954 • Published • 18
Claw-Eval-Live: A Live Agent Benchmark for Evolving Real-World Workflows
Paper • 2604.28139 • Published • 33
upvoted 4
papers 5 days ago
Efficient Training on Multiple Consumer GPUs with RoundPipe
Paper • 2604.27085 • Published • 36
Length Value Model: Scalable Value Pretraining for Token-Level Length Modeling
Paper • 2604.27039 • Published • 21
Leveraging Verifier-Based Reinforcement Learning in Image Editing
Paper • 2604.27505 • Published • 30
The Last Human-Written Paper: Agent-Native Research Artifacts
Paper • 2604.24658 • Published • 16