MetaKernelBench: Measuring GPU Kernel Knowledge Transfer Beyond Code
Paper • 2610.05014 • Published • 21
AI & ML interests
Efficient AI, AI Evaluation, Computer Vision, Machine Learning System
Recent Activity
View all activity
Papers
SparseDecoding: Decoding-Aware Pruning for Accurate and Efficient LLM Inference
MetaKernelBench: Measuring GPU Kernel Knowledge Transfer Beyond Code
Huan-WhoRegisteredMyName
authored a
paper 4 days ago
YIGE24
submitted a
paper to Daily Papers 4 days ago
Huan-WhoRegisteredMyName
submitted a
paper to Daily Papers 4 days ago
Huan-WhoRegisteredMyName
authored a
paper 6 days ago
Huan-WhoRegisteredMyName
authored 12
papers 7 days ago
SparseDecoding: Decoding-Aware Pruning for Accurate and Efficient LLM Inference
Paper • 2610.12327 • Published • 38
Poison as Cure: Visual Noise for Mitigating Object Hallucinations in LVMs
Paper • 2501.19164 • Published
CGGS: Consistency-Augmented Geometric Gaussian Splatting for Ego-centric 3D Scene Generation
Paper • 2607.03819 • Published • 11
EarlyTom: Early Token Compression Completes Fast Video Understanding
Paper • 2605.30010 • Published • 30
RankE: End-to-End Post-Training for Discrete Text-to-Image Generation with Decoder Co-Evolution
Paper • 2605.21195 • Published • 19
LVOmniBench: Pioneering Long Audio-Video Understanding Evaluation for Omnimodal LLMs
Paper • 2603.19217 • Published • 29
AIMER: Calibration-Free Task-Agnostic MoE Pruning
Paper • 2603.18492 • Published
ConCuR: Conciseness Makes State-of-the-Art Kernel Generation
Paper • 2510.07356 • Published • 2
OmniAgent: Audio-Guided Active Perception Agent for Omnimodal Audio-Video Understanding
Paper • 2512.23646 • Published • 15
TARS: MinMax Token-Adaptive Preference Strategy for Hallucination Reduction in MLLMs
Paper • 2507.21584 • Published • 11
MNN: A Universal and Efficient Inference Engine
Paper • 2002.12418 • Published
ERC-SVD: Error-Controlled SVD for Large Language Model Compression
Paper • 2505.20112 • Published • 1
Huan-WhoRegisteredMyName
submitted a
paper to Daily Papers 7 days ago
Huan-WhoRegisteredMyName
authored 3
papers about 1 year ago
OBS-Diff: Accurate Pruning For Diffusion Models in One-Shot
Paper • 2510.06751 • Published • 22
RewardMap: Tackling Sparse Rewards in Fine-grained Visual Reasoning via Multi-Stage Reinforcement Learning
Paper • 2510.02240 • Published • 19
When Tokens Talk Too Much: A Survey of Multimodal Long-Context Token Compression across Images, Videos, and Audios
Paper • 2507.20198 • Published • 28