r PRO

oceansweep's activity

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

upvoted 9 papers 3 days ago

MotionCLR: Motion Generation and Training-free Editing via Understanding Attention Mechanisms

Paper • 2410.18977 • Published 4 days ago • 12

Why Does the Effective Context Length of LLMs Fall Short?

Paper • 2410.18745 • Published 4 days ago • 15

Distill Visual Chart Reasoning Ability from LLMs to MLLMs

Paper • 2410.18798 • Published 4 days ago • 18

Unleashing Reasoning Capability of LLMs via Scalable Question Synthesis from Scratch

Paper • 2410.18693 • Published 4 days ago • 35

Framer: Interactive Frame Interpolation

Paper • 2410.18978 • Published 4 days ago • 29

Unbounded: A Generative Infinite Game of Character Life Simulation

Paper • 2410.18975 • Published 4 days ago • 29

Can Knowledge Editing Really Correct Hallucinations?

Paper • 2410.16251 • Published 7 days ago • 45

Breaking the Memory Barrier: Near Infinite Batch Size Scaling for Contrastive Loss

Paper • 2410.17243 • Published 6 days ago • 76

DynamicCity: Large-Scale LiDAR Generation from Dynamic Scenes

Paper • 2410.18084 • Published 5 days ago • 12

upvoted 7 papers 4 days ago

Math Neurosurgery: Isolating Language Models' Math Reasoning Abilities Using Only Forward Passes

Paper • 2410.16930 • Published 6 days ago • 4

EvoPress: Towards Optimal Dynamic Model Compression via Evolutionary Search

Paper • 2410.14649 • Published 10 days ago • 5

Mitigating Object Hallucination via Concentric Causal Attention

Paper • 2410.15926 • Published 7 days ago • 11

JMMMU: A Japanese Massive Multi-discipline Multimodal Understanding Benchmark for Culture-aware Evaluation

Paper • 2410.17250 • Published 6 days ago • 12

xGen-MM-Vid (BLIP-3-Video): You Only Need 32 Tokens to Represent a Video Even in VLMs

Paper • 2410.16267 • Published 7 days ago • 13

SpectroMotion: Dynamic 3D Reconstruction of Specular Scenes

Paper • 2410.17249 • Published 6 days ago • 36

PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction

Paper • 2410.17247 • Published 6 days ago • 41

upvoted 4 papers 5 days ago

CBT-Bench: Evaluating Large Language Models on Assisting Cognitive Behavior Therapy

Paper • 2410.13218 • Published 11 days ago • 4

Meta-Chunking: Learning Efficient Text Segmentation via Logical Perception

Paper • 2410.12788 • Published 12 days ago • 19

Pangea: A Fully Open Multilingual Multimodal LLM for 39 Languages

Paper • 2410.16153 • Published 7 days ago • 40

Baichuan Alignment Technical Report

Paper • 2410.14940 • Published 9 days ago • 45