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 6

Submitted by

fsteinbauer

Grokking in the Wild: Data Augmentation for Real-World Multi-Hop Reasoning with Transformers

·
3 authors

3

Submitted by

zhitinghu

Voila: Voice-Language Foundation Models for Real-Time Autonomous Interaction and Voice Role-Play

·
7 authors

4

Submitted by

gaotang

RM-R1: Reward Modeling as Reasoning

·
12 authors

1

Submitted by

akhaliq

Practical Efficiency of Muon for Pretraining

·
24 authors

Submitted by

akshaynambi

Agentic Reasoning and Tool Integration for LLMs via Reinforcement Learning

·
4 authors

2

Submitted by

leejaymin

A Survey on Inference Engines for Large Language Models: Perspectives on Optimization and Efficiency

·
6 authors

2

Submitted by

zhouliang

FormalMATH: Benchmarking Formal Mathematical Reasoning of Large Language Models

·
13 authors

1

Submitted by

idsedykh

ReplaceMe: Network Simplification via Layer Pruning and Linear Transformations

·
7 authors

4

Submitted by

yifanzhang114

R1-Reward: Training Multimodal Reward Model Through Stable Reinforcement Learning

·
16 authors

1

Submitted by

Ray2333

Optimizing Chain-of-Thought Reasoners via Gradient Variance Minimization in Rejection Sampling and RL

·
7 authors

Submitted by

poeroz

LLaMA-Omni2: LLM-based Real-time Spoken Chatbot with Autoregressive Streaming Speech Synthesis

·
5 authors

2

Submitted by

iiiiwis

Think on your Feet: Adaptive Thinking via Reinforcement Learning for Social Agents

·
9 authors

1

Submitted by

IngridYU

SkillMimic-V2: Learning Robust and Generalizable Interaction Skills from Sparse and Noisy Demonstrations

·
7 authors

1

Submitted by

limingcv

SuperEdit: Rectifying and Facilitating Supervision for Instruction-Based Image Editing

·
7 authors

1

Submitted by

BiaoGong

Ming-Lite-Uni: Advancements in Unified Architecture for Natural Multimodal Interaction

·
16 authors

1

Submitted by

wchai

TEMPURA: Temporal Event Masked Prediction and Understanding for Reasoning in Action

·
14 authors

1

Submitted by

Zhiwei840

Low-Precision Training of Large Language Models: Methods, Challenges, and Opportunities

·
9 authors

1

Submitted by

yanze

MUSAR: Exploring Multi-Subject Customization from Single-Subject Dataset via Attention Routing

·
6 authors

1

Submitted by

guanzhong2

Attention Mechanisms Perspective: Exploring LLM Processing of Graph-Structured Data

·
5 authors

1

Submitted by

Mifucius

Learning Heterogeneous Mixture of Scene Experts for Large-scale Neural Radiance Fields

·
4 authors

1

Submitted by

vaidehi99

Unlearning Sensitive Information in Multimodal LLMs: Benchmark and Attack-Defense Evaluation

·
6 authors

1

Submitted by

Chrisathy

Rethinking RGB-Event Semantic Segmentation with a Novel Bidirectional Motion-enhanced Event Representation

·
3 authors

1