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

Jun 16

Submitted by

itaynakash

Effective Red-Teaming of Policy-Adherent Agents

·
6 authors

Submitted by

bracio9623

Aligned Novel View Image and Geometry Synthesis via Cross-modal Attention Instillation

·
7 authors

Submitted by

s-sahoo

The Diffusion Duality

·
6 authors

Submitted by

Dongwei

Feedback Friction: LLMs Struggle to Fully Incorporate External Feedback

·
5 authors

Submitted by

russwang

ViCrit: A Verifiable Reinforcement Learning Proxy Task for Visual Perception in VLMs

·
13 authors

1

Submitted by

wchai

LiveCodeBench Pro: How Do Olympiad Medalists Judge LLMs in Competitive Programming?

·
19 authors

1

Submitted by

Ziruibest

SwS: Self-aware Weakness-driven Problem Synthesis in Reinforcement Learning for LLM Reasoning

·
8 authors

Submitted by

LiuXR

Beyond Homogeneous Attention: Memory-Efficient LLMs via Fourier-Approximated KV Cache

·
12 authors

1

Submitted by

thomasschmied

pLSTM: parallelizable Linear Source Transition Mark networks

·
5 authors

Submitted by

jinypark

DeepVideo-R1: Video Reinforcement Fine-Tuning via Difficulty-aware Regressive GRPO

·
4 authors

Submitted by

cyrilzakka

Med-PRM: Medical Reasoning Models with Stepwise, Guideline-verified Process Rewards

·
12 authors

Submitted by

kpzhang996

A High-Quality Dataset and Reliable Evaluation for Interleaved Image-Text Generation

·
11 authors

Submitted by

yxK

SkillBlender: Towards Versatile Humanoid Whole-Body Loco-Manipulation via Skill Blending

·
8 authors

1

Submitted by

paulcouairon

JAFAR: Jack up Any Feature at Any Resolution

·
6 authors

1

Submitted by

liranringel

Learning a Continue-Thinking Token for Enhanced Test-Time Scaling

·
3 authors

1

Submitted by

lxucs

Dense Retrievers Can Fail on Simple Queries: Revealing The Granularity Dilemma of Embeddings

·
6 authors

1

Submitted by

bobxwu

Detecting Harmful Memes with Decoupled Understanding and Guided CoT Reasoning

·
3 authors

1

Submitted by

dacharya-avey

Don't Pay Attention

·
2 authors

1

Submitted by

dawn0815

Mirage-1: Augmenting and Updating GUI Agent with Hierarchical Multimodal Skills

·
8 authors

Submitted by

marksibrahim

AbstentionBench: Reasoning LLMs Fail on Unanswerable Questions

·
4 authors

Submitted by

vicgalle

Configurable Preference Tuning with Rubric-Guided Synthetic Data

·
1 authors

1

Submitted by

cjeen

LoRA-Edit: Controllable First-Frame-Guided Video Editing via Mask-Aware LoRA Fine-Tuning

·
6 authors

Submitted by

gabeorlanski

Reward Models Enable Scalable Code Verification by Trading Accuracy for Throughput

·
4 authors

Submitted by

Splend1dchan

A Self-Refining Framework for Enhancing ASR Using TTS-Synthesized Data

·
8 authors

Submitted by

ananthu-aniraj

Inherently Faithful Attention Maps for Vision Transformers

·
4 authors

1

Submitted by

ZacLiu

Infinity Instruct: Scaling Instruction Selection and Synthesis to Enhance Language Models

·
8 authors

2

Submitted by

MingxuanXia

Prompt Candidates, then Distill: A Teacher-Student Framework for LLM-driven Data Annotation

·
7 authors

1