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 8

Submitted by

ssl-asuka

Entropy-Adaptive Fine-Tuning: Resolving Confident Conflicts to Mitigate Forgetting

Submitted by

Bang-UdeM-Mila

Evolving Programmatic Skill Networks

Université de Montréal

Submitted by

Jinyang23

Atlas: Orchestrating Heterogeneous Models and Tools for Multi-Domain Complex Reasoning

·
8 authors

2

Submitted by

ChengsongHuang

Benchmark^2: Systematic Evaluation of LLM Benchmarks

·
16 authors

3

Submitted by

leolhb

ROI-Reasoning: Rational Optimization for Inference via Pre-Computation Meta-Cognition

RUC

Renmin University of China

4

Submitted by

taesiri

Klear: Unified Multi-Task Audio-Video Joint Generation

KlingTeam

Submitted by

taesiri

Choreographing a World of Dynamic Objects

·
7 authors

Submitted by

taesiri

Agentic Rubrics as Contextual Verifiers for SWE Agents

ScaleAI

Submitted by

FredericFan

MDAgent2: Large Language Model for Code Generation and Knowledge Q&A in Molecular Dynamics

PekingUniversity

Peking University

2

Submitted by

zhangsj0722

E-GRPO: High Entropy Steps Drive Effective Reinforcement Learning for Flow Models

Tsinghua University

Submitted by

ZhishanQ

EpiQAL: Benchmarking Large Language Models in Epidemiological Question Answering for Enhanced Alignment and Reasoning

·
10 authors

Submitted by

quyanh

RedBench: A Universal Dataset for Comprehensive Red Teaming of Large Language Models

knoveleng

Knovel Engineering

Submitted by

paraslossfunk

Why LLMs Aren't Scientists Yet: Lessons from Four Autonomous Research Attempts

Lossfunk

Submitted by

taesiri

ThinkRL-Edit: Thinking in Reinforcement Learning for Reasoning-Centric Image Editing

ByteDance

Submitted by

atsuki-yamaguchi

Enhancing Linguistic Competence of Language Models through Pre-training with Language Learning Tasks

l2t-project

Language Learning Tasks (L2T) Project

Submitted by

zouharvi

Pearmut: Human Evaluation of Translation Made Trivial

·
2 authors

Submitted by

akhaliq

ResTok: Learning Hierarchical Residuals in 1D Visual Tokenizers for Autoregressive Image Generation

·
6 authors

Submitted by

udayallu

MAGMA: A Multi-Graph based Agentic Memory Architecture for AI Agents

·
4 authors

Submitted by

JaceyH919

Gen3R: 3D Scene Generation Meets Feed-Forward Reconstruction

·
6 authors

Submitted by

Breeze1124

RGS-SLAM: Robust Gaussian Splatting SLAM with One-Shot Dense Initialization

NYCU

National Yang Ming Chiao Tung University

2