Hierarchical SVG Tokenization: Learning Compact Visual Programs for Scalable Vector Graphics Modeling
Paper • 2604.05072 • Published • 1
GuoLiangTang
Tommy930
AI & ML interests
LLM，NLP，ML
Recent Activity
upvoted a paper about 2 hours ago
Hierarchical SVG Tokenization: Learning Compact Visual Programs for Scalable Vector Graphics Modeling upvoted a paper about 2 hours ago
You Only Judge Once: Multi-response Reward Modeling in a Single Forward Pass upvoted a paper about 2 hours ago
Towards Long-horizon Agentic Multimodal SearchOrganizations
None yet
upvoted 3
papers about 2 hours ago
upvoted 11
papers about 3 hours ago
Lightning OPD: Efficient Post-Training for Large Reasoning Models with Offline On-Policy Distillation
Paper • 2604.13010 • Published • 2
Lyra 2.0: Explorable Generative 3D Worlds
Paper • 2604.13036 • Published • 9
Nemotron 3 Super: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning
Paper • 2604.12374 • Published • 4
Rethinking the Diffusion Model from a Langevin Perspective
Paper • 2604.10465 • Published • 6
Toward Autonomous Long-Horizon Engineering for ML Research
Paper • 2604.13018 • Published • 15
Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe
Paper • 2604.13016 • Published • 33
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 • 2
Efficient RL Training for LLMs with Experience Replay
Paper • 2604.08706 • Published • 11
Agentic Aggregation for Parallel Scaling of Long-Horizon Agentic Tasks
Paper • 2604.11753 • Published • 11
The Past Is Not Past: Memory-Enhanced Dynamic Reward Shaping
Paper • 2604.11297 • Published • 85
upvoted a paper about 22 hours ago
upvoted 5
papers 1 day ago
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
Zero-shot World Models Are Developmentally Efficient Learners
Paper • 2604.10333 • Published • 6
Solving Physics Olympiad via Reinforcement Learning on Physics Simulators
Paper • 2604.11805 • Published • 13