new

Get trending papers in your email inbox once a day!

Get trending papers in your email inbox!

Daily Papers

by AK and the research community

Feb 28

Submitted by

weqweasdas

Self-rewarding correction for mathematical reasoning

·
6 authors

Submitted by

che111

MedVLM-R1: Incentivizing Medical Reasoning Capability of Vision-Language Models (VLMs) via Reinforcement Learning

·
9 authors

Submitted by

zhoutianyi

R2-T2: Re-Routing in Test-Time for Multimodal Mixture-of-Experts

·
3 authors

Submitted by

tomaarsen

NeoBERT: A Next-Generation BERT

·
4 authors

Submitted by

lynazhang

LongRoPE2: Near-Lossless LLM Context Window Scaling

·
8 authors

Submitted by

JiangYi

UniTok: A Unified Tokenizer for Visual Generation and Understanding

·
8 authors

Submitted by

BestWishYsh

Multimodal Representation Alignment for Image Generation: Text-Image Interleaved Control Is Easier Than You Think

·
8 authors

Submitted by

Guizhen

FINEREASON: Evaluating and Improving LLMs' Deliberate Reasoning through Reflective Puzzle Solving

·
9 authors

Submitted by

akhaliq

FlexiDiT: Your Diffusion Transformer Can Easily Generate High-Quality Samples with Less Compute

·
10 authors

Submitted by

shuaishuaicdp

CODESYNC: Synchronizing Large Language Models with Dynamic Code Evolution at Scale

·
9 authors

Submitted by

akhaliq

Mobius: Text to Seamless Looping Video Generation via Latent Shift

·
7 authors

Submitted by

OliverRen

Beyond Next-Token: Next-X Prediction for Autoregressive Visual Generation

·
6 authors

Submitted by

AlignAI

Guardians of the Agentic System: Preventing Many Shots Jailbreak with Agentic System

·
6 authors

Submitted by

keanudicap

Lean and Mean: Decoupled Value Policy Optimization with Global Value Guidance

·
9 authors

Submitted by

mizersy

SoRFT: Issue Resolving with Subtask-oriented Reinforced Fine-Tuning

·
6 authors

Submitted by

thuhsy

Building Interactable Replicas of Complex Articulated Objects via Gaussian Splatting

·
6 authors

Submitted by

Mihir3009

PlanGEN: A Multi-Agent Framework for Generating Planning and Reasoning Trajectories for Complex Problem Solving

·
14 authors

Submitted by

akhaliq

R1-T1: Fully Incentivizing Translation Capability in LLMs via Reasoning Learning

·
13 authors

Submitted by

kargaranamir

On Relation-Specific Neurons in Large Language Models

·
9 authors

Submitted by

gisilvs

Training Consistency Models with Variational Noise Coupling

·
5 authors

Submitted by

imsuperkong

Efficient Gaussian Splatting for Monocular Dynamic Scene Rendering via Sparse Time-Variant Attribute Modeling

·
3 authors