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

May 27

Submitted by

Hennara

Mutarjim: Advancing Bidirectional Arabic-English Translation with a Small Language Model

·
6 authors

5

Submitted by

zichenwen

Shifting AI Efficiency From Model-Centric to Data-Centric Compression

·
16 authors

2

Submitted by

sharfikeg

Alchemist: Turning Public Text-to-Image Data into Generative Gold

·
5 authors

1

Submitted by

Tinker250

BizFinBench: A Business-Driven Real-World Financial Benchmark for Evaluating LLMs

·
5 authors

2

Submitted by

Yi53

PATS: Process-Level Adaptive Thinking Mode Switching

·
5 authors

1

Submitted by

Connoriginal

Embodied Agents Meet Personalization: Exploring Memory Utilization for Personalized Assistance

·
8 authors

1

Submitted by

hsaest

ARM: Adaptive Reasoning Model

·
7 authors

3

Submitted by

siyuyuan

Enigmata: Scaling Logical Reasoning in Large Language Models with Synthetic Verifiable Puzzles

·
12 authors

1

Submitted by

zsytony

Deciphering Trajectory-Aided LLM Reasoning: An Optimization Perspective

·
8 authors

2

Submitted by

taesiri

B-score: Detecting biases in large language models using response history

·
4 authors

1

Submitted by

P2333

Lifelong Safety Alignment for Language Models

·
7 authors

1

Submitted by

ZonglinY

MOOSE-Chem2: Exploring LLM Limits in Fine-Grained Scientific Hypothesis Discovery via Hierarchical Search

·
10 authors

1

Submitted by

FSCCS

Can MLLMs Guide Me Home? A Benchmark Study on Fine-Grained Visual Reasoning from Transit Maps

·
8 authors

2

Submitted by

zstanjj

Surrogate Signals from Format and Length: Reinforcement Learning for Solving Mathematical Problems without Ground Truth Answers

·
7 authors

Submitted by

sungnyun

Flex-Judge: Think Once, Judge Anywhere

·
4 authors

1

Submitted by

Xuandong

Learning to Reason without External Rewards

·
5 authors

1

Submitted by

xiaonengmiao

Reinforcement Fine-Tuning Powers Reasoning Capability of Multimodal Large Language Models

·
10 authors

2

Submitted by

DongfuJiang

StructEval: Benchmarking LLMs' Capabilities to Generate Structural Outputs

·
20 authors

1

Submitted by

henry12348

Discrete Markov Bridge

·
5 authors

1

Submitted by

karrykkk

Which Data Attributes Stimulate Math and Code Reasoning? An Investigation via Influence Functions

·
5 authors

1

Submitted by

Z-MU-Z

Omni-R1: Reinforcement Learning for Omnimodal Reasoning via Two-System Collaboration

·
9 authors

Submitted by

JanPf

ModernGBERT: German-only 1B Encoder Model Trained from Scratch

·
5 authors

1

Submitted by

ElysiaTrue

Done Is Better than Perfect: Unlocking Efficient Reasoning by Structured Multi-Turn Decomposition

·
5 authors

1

Submitted by

JoeYing

AdaCtrl: Towards Adaptive and Controllable Reasoning via Difficulty-Aware Budgeting

·
7 authors

1

Submitted by

wjldw

The Quest for Efficient Reasoning: A Data-Centric Benchmark to CoT Distillation

·
6 authors

2

Submitted by

NeoZ123

Hard Negative Contrastive Learning for Fine-Grained Geometric Understanding in Large Multimodal Models

·
7 authors

1

Submitted by

le723z

REARANK: Reasoning Re-ranking Agent via Reinforcement Learning

·
5 authors

2

Submitted by

RRoy233

Interleaved Reasoning for Large Language Models via Reinforcement Learning

·
8 authors

2

Submitted by

Zigeng

Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression

·
4 authors

1

Submitted by

leonardPKU

G1: Bootstrapping Perception and Reasoning Abilities of Vision-Language Model via Reinforcement Learning

·
8 authors

1

Submitted by

nate-gillman

Force Prompting: Video Generation Models Can Learn and Generalize Physics-based Control Signals

·
7 authors

Submitted by

Tianduo

From Tens of Hours to Tens of Thousands: Scaling Back-Translation for Speech Recognition

·
4 authors

Submitted by

chchenhui

MLR-Bench: Evaluating AI Agents on Open-Ended Machine Learning Research

·
10 authors

1

Submitted by

RanjanSapkota

Vibe Coding vs. Agentic Coding: Fundamentals and Practical Implications of Agentic AI

·
3 authors

1

Submitted by

tianyic

WINA: Weight Informed Neuron Activation for Accelerating Large Language Model Inference

·
7 authors

1

Submitted by

gallilmaimon

WHISTRESS: Enriching Transcriptions with Sentence Stress Detection

·
3 authors

Submitted by

Hoyeon

The Coverage Principle: A Framework for Understanding Compositional Generalization

·
10 authors

1

Submitted by

AdinaY

LLaDA 1.5: Variance-Reduced Preference Optimization for Large Language Diffusion Models

·
11 authors

Submitted by

Bin12345

InfantAgent-Next: A Multimodal Generalist Agent for Automated Computer Interaction

·
11 authors

1

Submitted by

dtiapkin

Accelerating Nash Learning from Human Feedback via Mirror Prox

·
8 authors

1

Submitted by

iliashum

Strong Membership Inference Attacks on Massive Datasets and (Moderately) Large Language Models

·
16 authors

1

Submitted by

boyiwei

Dynamic Risk Assessments for Offensive Cybersecurity Agents

·
6 authors

1

Submitted by

DeyangKong

Rethinking the Sampling Criteria in Reinforcement Learning for LLM Reasoning: A Competence-Difficulty Alignment Perspective

·
8 authors

1

Submitted by

aashiqmuhamed

Position: Mechanistic Interpretability Should Prioritize Feature Consistency in SAEs

·
8 authors

1

Submitted by

Haoxiang-Wang

Bridging Supervised Learning and Reinforcement Learning in Math Reasoning

·
10 authors

Submitted by

zyma

STAR-R1: Spatial TrAnsformation Reasoning by Reinforcing Multimodal LLMs

·
9 authors

1

Submitted by

Xiao-HF

GLEAM: Learning Generalizable Exploration Policy for Active Mapping in Complex 3D Indoor Scenes

·
6 authors

1

Submitted by

Jarvis1111

DoctorAgent-RL: A Multi-Agent Collaborative Reinforcement Learning System for Multi-Turn Clinical Dialogue

·
4 authors

1

Submitted by

xyfJASON

Jodi: Unification of Visual Generation and Understanding via Joint Modeling

·
5 authors

1

Submitted by

hammh0a

An Embarrassingly Simple Defense Against LLM Abliteration Attacks

·
4 authors

1

Submitted by

wuyangchen

Hybrid Neural-MPM for Interactive Fluid Simulations in Real-Time

·
6 authors

Submitted by

iliashum

Architectural Backdoors for Within-Batch Data Stealing and Model Inference Manipulation

·
4 authors

1

Submitted by

liumy2010

UFT: Unifying Supervised and Reinforcement Fine-Tuning

·
3 authors

2

Submitted by

njedidi

Don't "Overthink" Passage Reranking: Is Reasoning Truly Necessary?

·
4 authors

Submitted by

Jiawei1222

EquivPruner: Boosting Efficiency and Quality in LLM-Based Search via Action Pruning

·
5 authors

2

Submitted by

soujanyaporia

Error Typing for Smarter Rewards: Improving Process Reward Models with Error-Aware Hierarchical Supervision

·
5 authors

1

Submitted by

yuezrhb

Hybrid Latent Reasoning via Reinforcement Learning

·
9 authors

Submitted by

JianghaoWu

TAGS: A Test-Time Generalist-Specialist Framework with Retrieval-Augmented Reasoning and Verification

·
8 authors

1

Submitted by

zenyn

Towards Holistic Evaluation of Large Audio-Language Models: A Comprehensive Survey

·
3 authors

1

Submitted by

akhaliq

DiSA: Diffusion Step Annealing in Autoregressive Image Generation

·
6 authors

Submitted by

vincentjliu

EgoZero: Robot Learning from Smart Glasses

·
6 authors

1

Submitted by

qcz

Seeing is Believing, but How Much? A Comprehensive Analysis of Verbalized Calibration in Vision-Language Models

·
5 authors

Submitted by

yuzc19

FLAME-MoE: A Transparent End-to-End Research Platform for Mixture-of-Experts Language Models

·
3 authors

Submitted by

Zaid

MOLE: Metadata Extraction and Validation in Scientific Papers Using LLMs

·
3 authors

1

Submitted by

shayekh

The Birth of Knowledge: Emergent Features across Time, Space, and Scale in Large Language Models

·
3 authors

Submitted by

hhua2

MMIG-Bench: Towards Comprehensive and Explainable Evaluation of Multi-Modal Image Generation Models

·
8 authors

Submitted by

qcz

The Pragmatic Mind of Machines: Tracing the Emergence of Pragmatic Competence in Large Language Models

·
6 authors

Submitted by

zifuwan

InstructPart: Task-Oriented Part Segmentation with Instruction Reasoning

·
8 authors

Submitted by

deqing

Textual Steering Vectors Can Improve Visual Understanding in Multimodal Large Language Models

·
8 authors

Submitted by

JisuHann

Option-aware Temporally Abstracted Value for Offline Goal-Conditioned Reinforcement Learning

·
4 authors

1

Submitted by

ahmedheakl

CASS: Nvidia to AMD Transpilation with Data, Models, and Benchmark

·
6 authors