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 27

Submitted by

nastasia-y

GHOST 2.0: generative high-fidelity one shot transfer of heads

·
5 authors

Submitted by

bzantium

Kanana: Compute-efficient Bilingual Language Models

·
29 authors

Submitted by

akhaliq

TheoremExplainAgent: Towards Multimodal Explanations for LLM Theorem Understanding

·
6 authors

Submitted by

jiminHuang

Plutus: Benchmarking Large Language Models in Low-Resource Greek Finance

·
10 authors

Submitted by

AggarwalTushar

Language Models' Factuality Depends on the Language of Inquiry

·
6 authors

Submitted by

akhaliq

Towards an AI co-scientist

·
34 authors

Submitted by

CheeryLJH

Can Large Language Models Detect Errors in Long Chain-of-Thought Reasoning?

·
10 authors

Submitted by

Wesleythu

Agentic Reward Modeling: Integrating Human Preferences with Verifiable Correctness Signals for Reliable Reward Systems

·
7 authors

Submitted by

shash42

Can Language Models Falsify? Evaluating Algorithmic Reasoning with Counterexample Creation

·
6 authors

Submitted by

orionweller

Rank1: Test-Time Compute for Reranking in Information Retrieval

·
6 authors

Submitted by

AmeyaPrabhu

Project Alexandria: Towards Freeing Scientific Knowledge from Copyright Burdens via LLMs

·
12 authors

Submitted by

vyokky

VEM: Environment-Free Exploration for Training GUI Agent with Value Environment Model

·
10 authors

Submitted by

DrChiZhang

Distill Any Depth: Distillation Creates a Stronger Monocular Depth Estimator

·
6 authors

Submitted by

nielsr

BIG-Bench Extra Hard

·
20 authors

Submitted by

KYLN24

CritiQ: Mining Data Quality Criteria from Human Preferences

·
11 authors

Submitted by

nonstopfor

AISafetyLab: A Comprehensive Framework for AI Safety Evaluation and Improvement

·
16 authors

Submitted by

Asap7772

FSPO: Few-Shot Preference Optimization of Synthetic Preference Data in LLMs Elicits Effective Personalization to Real Users

·
8 authors

Submitted by

Taishi-N324

Drop-Upcycling: Training Sparse Mixture of Experts with Partial Re-initialization

·
6 authors

Submitted by

ThePyProgrammer

Adapting Automatic Speech Recognition for Accented Air Traffic Control Communications

·
9 authors

Submitted by

kailinjiang

MMKE-Bench: A Multimodal Editing Benchmark for Diverse Visual Knowledge

·
7 authors

Submitted by

TongZheng1999

Towards Optimal Multi-draft Speculative Decoding

·
8 authors

Submitted by

AzureLeon1

MolSpectra: Pre-training 3D Molecular Representation with Multi-modal Energy Spectra

·
7 authors

Submitted by

rohitsaxena

PosterSum: A Multimodal Benchmark for Scientific Poster Summarization

·
3 authors

Submitted by

SteveZeyuZhang

DOEI: Dual Optimization of Embedding Information for Attention-Enhanced Class Activation Maps

·
9 authors