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

Jan 31

Submitted by

yueliu1999

GuardReasoner: Towards Reasoning-based LLM Safeguards

·
10 authors

3

Submitted by

akhaliq

Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs

·
14 authors

Submitted by

ArthurDouillard

Streaming DiLoCo with overlapping communication: Towards a Distributed Free Lunch

·
14 authors

Submitted by

akhaliq

Large Language Models Think Too Fast To Explore Effectively

·
3 authors

Submitted by

pablovalle

o3-mini vs DeepSeek-R1: Which One is Safer?

·
5 authors

3

Submitted by

lindsay-qu

MedXpertQA: Benchmarking Expert-Level Medical Reasoning and Understanding

·
9 authors

2

Submitted by

davanstrien

WILDCHAT-50M: A Deep Dive Into the Role of Synthetic Data in Post-Training

·
2 authors

Submitted by

WeiChow

PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding

·
6 authors

3

Submitted by

Yuyang-z

SANA 1.5: Efficient Scaling of Training-Time and Inference-Time Compute in Linear Diffusion Transformer

·
13 authors

Submitted by

oaishi

CowPilot: A Framework for Autonomous and Human-Agent Collaborative Web Navigation

·
7 authors