OmniCompass: A Holistic Benchmark for Omni-Modal Video Grounding and Understanding
Paper • 2610.18829 • Published • 84
Yuan Feng
yuanfengustc
·
AI & ML interests
LLM Long Context, MLLM
Recent Activity
upvoted a paper 28 days ago
OmniCompass: A Holistic Benchmark for Omni-Modal Video Grounding and Understanding submitted a paper about 1 month ago
VisionWeave: Weaving Elastic Visual Representations as a Native Capability of MLLMs authored a paper about 1 month ago
VisionWeave: Weaving Elastic Visual Representations as a Native Capability of MLLMsOrganizations
None yet
upvoted a paper 28 days ago
submitted a
paper to Daily Papers about 1 month ago
authored 6
papers about 1 month ago
VisionWeave: Weaving Elastic Visual Representations as a Native Capability of MLLMs
Paper • 2610.07987 • Published • 58
OmniVChat: Synthesizing, Benchmarking, and Training for Native Audio-Visual Dialogue
Paper • 2609.21465 • Published • 49
Identify Critical KV Cache in LLM Inference from an Output Perturbation Perspective
Paper • 2502.03805 • Published
CritiPrefill: A Segment-wise Criticality-based Approach for Prefilling Acceleration in LLMs
Paper • 2409.12490 • Published
Ada-KV: Optimizing KV Cache Eviction by Adaptive Budget Allocation for Efficient LLM Inference
Paper • 2407.11550 • Published
Taming the Fragility of KV Cache Eviction in LLM Inference
Paper • 2510.13334 • Published • 1
published a
model about 1 month ago
upvoted a paper about 1 month ago
upvoted a paper about 2 months ago
upvoted 2
papers 2 months ago
upvoted a paper 5 months ago
Update dataset card with task categories, paper links and usage info
#2 opened 6 months ago
by 
nielsr
updated a
dataset 8 months ago
published a
dataset 9 months ago
upvoted a paper 11 months ago
updated a
dataset over 1 year ago
published a
dataset over 1 year ago