Jiale Zhao

Heisenburger2000's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted 2 papers 2 days ago

Towards Long-horizon Agentic Multimodal Search

Paper • 2604.12890 • Published 3 days ago • 16

Toward Autonomous Long-Horizon Engineering for ML Research

Paper • 2604.13018 • Published 3 days ago • 30

upvoted 8 papers 3 days ago

Tracing the Roots: A Multi-Agent Framework for Uncovering Data Lineage in Post-Training LLMs

Paper • 2604.10480 • Published 5 days ago • 19

CodeTracer: Towards Traceable Agent States

Paper • 2604.11641 • Published 4 days ago • 38

Strips as Tokens: Artist Mesh Generation with Native UV Segmentation

Paper • 2604.09132 • Published 7 days ago • 50

Pseudo-Unification: Entropy Probing Reveals Divergent Information Patterns in Unified Multimodal Models

Paper • 2604.10949 • Published 4 days ago • 38

QuanBench+: A Unified Multi-Framework Benchmark for LLM-Based Quantum Code Generation

Paper • 2604.08570 • Published 23 days ago • 121

Uni-ViGU: Towards Unified Video Generation and Understanding via A Diffusion-Based Video Generator

Paper • 2604.08121 • Published 8 days ago • 42

OmniShow: Unifying Multimodal Conditions for Human-Object Interaction Video Generation

Paper • 2604.11804 • Published 4 days ago • 67

Attention Sink in Transformers: A Survey on Utilization, Interpretation, and Mitigation

Paper • 2604.10098 • Published 6 days ago • 73

liked a dataset 12 days ago

ianncity/KIMI-K2.5-1000000x

Viewer • Updated 10 days ago • 733k • 3.31k • 223

upvoted 9 papers about 1 month ago

Cheers: Decoupling Patch Details from Semantic Representations Enables Unified Multimodal Comprehension and Generation

Paper • 2603.12793 • Published Mar 13 • 38

LMEB: Long-horizon Memory Embedding Benchmark

Paper • 2603.12572 • Published Mar 13 • 73

HybridStitch: Pixel and Timestep Level Model Stitching for Diffusion Acceleration

Paper • 2603.07815 • Published Mar 8 • 10

Can Vision-Language Models Solve the Shell Game?

Paper • 2603.08436 • Published Mar 9 • 39

From Sparse to Dense: Multi-View GRPO for Flow Models via Augmented Condition Space

Paper • 2603.12648 • Published Mar 13 • 14

Video Streaming Thinking: VideoLLMs Can Watch and Think Simultaneously

Paper • 2603.12262 • Published Mar 12 • 31

Multimodal OCR: Parse Anything from Documents

Paper • 2603.13032 • Published Mar 13 • 43

MM-CondChain: A Programmatically Verified Benchmark for Visually Grounded Deep Compositional Reasoning

Paper • 2603.12266 • Published Mar 12 • 19

V-Bridge: Bridging Video Generative Priors to Versatile Few-shot Image Restoration

Paper • 2603.13089 • Published Mar 13 • 13