new

Get trending papers in your email inbox once a day!

Get trending papers in your email inbox!

Daily Papers

byAK and the research community

Jul 23

Submitted by

luohy

Beyond Context Limits: Subconscious Threads for Long-Horizon Reasoning

·
10 authors

Submitted by

skicy

Step-Audio 2 Technical Report

·
109 authors

Submitted by

Vfrz

MegaScience: Pushing the Frontiers of Post-Training Datasets for Science Reasoning

·
3 authors

Submitted by

Agorium

Upsample What Matters: Region-Adaptive Latent Sampling for Accelerated Diffusion Transformers

·
4 authors

Submitted by

vanilla1116

Semi-off-Policy Reinforcement Learning for Vision-Language Slow-thinking Reasoning

·
10 authors

1

Submitted by

deqing

Zebra-CoT: A Dataset for Interleaved Vision Language Reasoning

·
14 authors

Submitted by

jasper0314-huang

ThinkAct: Vision-Language-Action Reasoning via Reinforced Visual Latent Planning

·
5 authors

1

Submitted by

hba123

Experience is the Best Teacher: Grounding VLMs for Robotics through Self-Generated Memory

·
7 authors

2

Submitted by

LeoLau

HOComp: Interaction-Aware Human-Object Composition

·
4 authors

3

Submitted by

xiangh

RefCritic: Training Long Chain-of-Thought Critic Models with Refinement Feedback

·
9 authors

Submitted by

lichangh20

Task-Specific Zero-shot Quantization-Aware Training for Object Detection

·
5 authors

Submitted by

MonteXiaofeng

SPAR: Scholar Paper Retrieval with LLM-based Agents for Enhanced Academic Search

·
6 authors

Submitted by

tongwu2020

Does More Inference-Time Compute Really Help Robustness?

·
7 authors

1

Submitted by

kh4dien

Steering Out-of-Distribution Generalization with Concept Ablation Fine-Tuning

·
6 authors

1

Submitted by

RuijieZhu

ObjectGS: Object-aware Scene Reconstruction and Scene Understanding via Gaussian Splatting

·
8 authors

1