Xin Jin

Xin1118's activity

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

upvoted a paper about 12 hours ago

SO-Arena: Benchmarking the Capability Spectrum and Reliability of System One Models

Paper • 2611.15777 • Published 3 days ago • 72

upvoted 3 papers about 1 month ago

Jeva: System One Models from First Principles

Paper • 2610.18773 • Published Oct 13 • 140

MetaKernelBench: Measuring GPU Kernel Knowledge Transfer Beyond Code

Paper • 2610.05014 • Published Oct 4 • 23

SparseDecoding: Decoding-Aware Pruning for Accurate and Efficient LLM Inference

Paper • 2610.12327 • Published Oct 8 • 29

upvoted 2 papers 3 months ago

EchoWM: Open and Enterable Omnimodal World Models

Paper • 2608.23189 • Published Aug 24 • 82

FreeToken: Efficient Edge-Native MoE Serving with Bandwidth-Adaptive Execution

Paper • 2608.16157 • Published Aug 17 • 112

upvoted a paper 4 months ago

Sol-Attn: Accelerating Video Generation Inference via On-the-Fly Attention Sparsification

Paper • 2607.24027 • Published Jul 27 • 39

authored 3 papers 4 months ago

OmniOpt: Taxonomy, Geometry, and Benchmarking of Modern Optimizers

Paper • 2607.04033 • Published Jul 4 • 50

AGVBench: A Reliability-Oriented Benchmark of Data Augmentation for Vein Recognition

Paper • 2607.02271 • Published Jul 2 • 15

EarlyTom: Early Token Compression Completes Fast Video Understanding

Paper • 2605.30010 • Published May 28 • 29

upvoted 3 papers 4 months ago

AGVBench: A Reliability-Oriented Benchmark of Data Augmentation for Vein Recognition

Paper • 2607.02271 • Published Jul 2 • 15

BadWAM: When World-Action Models Dream Right but Act Wrong

Paper • 2607.15207 • Published Jul 16 • 43

OmniOpt: Taxonomy, Geometry, and Benchmarking of Modern Optimizers

Paper • 2607.04033 • Published Jul 4 • 50

submitted a paper to Daily Papers 4 months ago

AGVBench: A Reliability-Oriented Benchmark of Data Augmentation for Vein Recognition

Paper • 2607.02271 • Published Jul 2 • 15

updated a dataset 5 months ago

Xin1118/Palm-Vein-Corruption

Updated Jun 25 • 456

published a dataset 5 months ago

Xin1118/Palm-Vein-Corruption

Updated Jun 25 • 456

upvoted a paper 6 months ago

EarlyTom: Early Token Compression Completes Fast Video Understanding

Paper • 2605.30010 • Published May 28 • 29

authored 3 papers 6 months ago

MergeMix: A Unified Augmentation Paradigm for Visual and Multi-Modal Understanding

Paper • 2510.23479 • Published Oct 27, 2025 • 18

LVOmniBench: Pioneering Long Audio-Video Understanding Evaluation for Omnimodal LLMs

Paper • 2603.19217 • Published Mar 19 • 30

RankE: End-to-End Post-Training for Discrete Text-to-Image Generation with Decoder Co-Evolution

Paper • 2605.21195 • Published May 20 • 18