Generative Refinement Networks for Visual Synthesis
Paper • 2604.13030 • Published • 4
GuoLiangTang
Tommy930
AI & ML interests
LLM，NLP，ML
Recent Activity
upvoted a paper about 8 hours ago
Generative Refinement Networks for Visual Synthesis upvoted a paper about 8 hours ago
Accelerating Speculative Decoding with Block Diffusion Draft Trees upvoted a paper about 13 hours ago
Hierarchical SVG Tokenization: Learning Compact Visual Programs for Scalable Vector Graphics ModelingOrganizations
None yet
upvoted 2
papers about 8 hours ago
upvoted 3
papers about 13 hours ago
Hierarchical SVG Tokenization: Learning Compact Visual Programs for Scalable Vector Graphics Modeling
Paper • 2604.05072 • Published • 1
You Only Judge Once: Multi-response Reward Modeling in a Single Forward Pass
Paper • 2604.10966 • Published • 5
Towards Long-horizon Agentic Multimodal Search
Paper • 2604.12890 • Published • 14
upvoted 11
papers about 15 hours ago
Lightning OPD: Efficient Post-Training for Large Reasoning Models with Offline On-Policy Distillation
Paper • 2604.13010 • Published • 4
Lyra 2.0: Explorable Generative 3D Worlds
Paper • 2604.13036 • Published • 17
Nemotron 3 Super: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning
Paper • 2604.12374 • Published • 13
Rethinking the Diffusion Model from a Langevin Perspective
Paper • 2604.10465 • Published • 7
Toward Autonomous Long-Horizon Engineering for ML Research
Paper • 2604.13018 • Published • 22
Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe
Paper • 2604.13016 • Published • 54
IceCache: Memory-efficient KV-cache Management for Long-Sequence LLMs
Paper • 2604.10539 • Published • 1
Audio-Omni: Extending Multi-modal Understanding to Versatile Audio Generation and Editing
Paper • 2604.10708 • Published • 33
Efficient RL Training for LLMs with Experience Replay
Paper • 2604.08706 • Published • 15
Agentic Aggregation for Parallel Scaling of Long-Horizon Agentic Tasks
Paper • 2604.11753 • Published • 12
The Past Is Not Past: Memory-Enhanced Dynamic Reward Shaping
Paper • 2604.11297 • Published • 89
upvoted 4
papers 1 day ago
Uni-ViGU: Towards Unified Video Generation and Understanding via A Diffusion-Based Video Generator
Paper • 2604.08121 • Published • 40
Pseudo-Unification: Entropy Probing Reveals Divergent Information Patterns in Unified Multimodal Models
Paper • 2604.10949 • Published • 36
Strips as Tokens: Artist Mesh Generation with Native UV Segmentation
Paper • 2604.09132 • Published • 46
TorchUMM: A Unified Multimodal Model Codebase for Evaluation, Analysis, and Post-training
Paper • 2604.10784 • Published • 5