Cheers: Decoupling Patch Details from Semantic Representations Enables Unified Multimodal Comprehension and Generation
Paper • 2603.12793 • Published • 38
Jiale Zhao
Heisenburger2000
AI & ML interests
None yet
Recent Activity
upvoted a paper 15 days ago
LMEB: Long-horizon Memory Embedding Benchmark upvoted a paper 15 days ago
HybridStitch: Pixel and Timestep Level Model Stitching for Diffusion AccelerationOrganizations
upvoted 11
papers 15 days ago
LMEB: Long-horizon Memory Embedding Benchmark
Paper • 2603.12572 • Published • 73
HybridStitch: Pixel and Timestep Level Model Stitching for Diffusion Acceleration
Paper • 2603.07815 • Published • 10
Can Vision-Language Models Solve the Shell Game?
Paper • 2603.08436 • Published • 39
From Sparse to Dense: Multi-View GRPO for Flow Models via Augmented Condition Space
Paper • 2603.12648 • Published • 14
Video Streaming Thinking: VideoLLMs Can Watch and Think Simultaneously
Paper • 2603.12262 • Published • 30
Multimodal OCR: Parse Anything from Documents
Paper • 2603.13032 • Published • 40
MM-CondChain: A Programmatically Verified Benchmark for Visually Grounded Deep Compositional Reasoning
Paper • 2603.12266 • Published • 19
V-Bridge: Bridging Video Generative Priors to Versatile Few-shot Image Restoration
Paper • 2603.13089 • Published • 13
Visual-ERM: Reward Modeling for Visual Equivalence
Paper • 2603.13224 • Published • 21
OmniForcing: Unleashing Real-time Joint Audio-Visual Generation
Paper • 2603.11647 • Published • 31
upvoted a paper 27 days ago
upvoted a paper about 1 month ago
upvoted a paper about 2 months ago
upvoted a paper 4 months ago
upvoted 3
papers 5 months ago
IterResearch: Rethinking Long-Horizon Agents via Markovian State Reconstruction
Paper • 2511.07327 • Published • 80
ReForm: Reflective Autoformalization with Prospective Bounded Sequence Optimization
Paper • 2510.24592 • Published • 17
Tongyi DeepResearch Technical Report
Paper • 2510.24701 • Published • 103