MMFlash: Faster Speculative Decoding for Vision-Language Models Paper • 2611.18482 • Published 6 days ago • 41
AB-Attention: Accurate Block Attention for Accelerating Video Diffusion Transformers Paper • 2610.39663 • Published 21 days ago • 9
EdgeKernelBench: Unified LLM-Driven Kernel Generation for Edge Backends Paper • 2610.24648 • Published Oct 17 • 13
EVOKE: Eliciting World Knowledge in Agents for Transferable Decision-Making Paper • 2609.38334 • Published Oct 1 • 32
APM-Bench: Benchmarking Cross-session Persistent Memory for Egocentric Streaming Video Assistants Paper • 2609.37559 • Published Sep 29 • 30
H3-World: Turning Language Understanding into World Control Paper • 2609.01560 • Published Sep 1 • 54
AdvFD: Boosting Visual Generation via Adversarial Fr'echet Distance Loss Paper • 2608.11205 • Published Aug 11 • 21
MergeDNA: Context-aware Genome Modeling with Dynamic Tokenization through Token Merging Paper • 2511.14806 • Published Nov 17, 2025 • 12
RankE: End-to-End Post-Training for Discrete Text-to-Image Generation with Decoder Co-Evolution Paper • 2605.21195 • Published May 20 • 18
MergeMix: A Unified Augmentation Paradigm for Visual and Multi-Modal Understanding Paper • 2510.23479 • Published Oct 27, 2025 • 18
RankE: End-to-End Post-Training for Discrete Text-to-Image Generation with Decoder Co-Evolution Paper • 2605.21195 • Published May 20 • 18
RankE: End-to-End Post-Training for Discrete Text-to-Image Generation with Decoder Co-Evolution Paper • 2605.21195 • Published May 20 • 18 • 3
RankE: End-to-End Post-Training for Discrete Text-to-Image Generation with Decoder Co-Evolution Paper • 2605.21195 • Published May 20 • 18
LVOmniBench: Pioneering Long Audio-Video Understanding Evaluation for Omnimodal LLMs Paper • 2603.19217 • Published Mar 19 • 30
The Trinity of Consistency as a Defining Principle for General World Models Paper • 2602.23152 • Published Feb 26 • 173
Thinking with Drafting: Optical Decompression via Logical Reconstruction Paper • 2602.11731 • Published Feb 12 • 36
OmniZip: Audio-Guided Dynamic Token Compression for Fast Omnimodal Large Language Models Paper • 2511.14582 • Published Nov 18, 2025 • 19
MergeMix: A Unified Augmentation Paradigm for Visual and Multi-Modal Understanding Paper • 2510.23479 • Published Oct 27, 2025 • 18