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

Mar 6

Submitted by

Yiran0924

Babel: Open Multilingual Large Language Models Serving Over 90% of Global Speakers

·
11 authors

Submitted by

ttn0011

HoT: Highlighted Chain of Thought for Referencing Supporting Facts from Inputs

·
4 authors

5

Submitted by

lx865712528

Process-based Self-Rewarding Language Models

·
7 authors

3

Submitted by

zhangchenxu

KodCode: A Diverse, Challenging, and Verifiable Synthetic Dataset for Coding

·
5 authors

Submitted by

akhaliq

GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Control

·
10 authors

Submitted by

wenhu

ABC: Achieving Better Control of Multimodal Embeddings using VLMs

·
3 authors

Submitted by

shuaishuaicdp

CrowdSelect: Synthetic Instruction Data Selection with Multi-LLM Wisdom

·
7 authors

Submitted by

che111

Enhancing Abnormality Grounding for Vision Language Models with Knowledge Descriptions

·
6 authors

Submitted by

SyedAbdul

Fine-Tuning Small Language Models for Domain-Specific AI: An Edge AI Perspective

·
4 authors

3

Submitted by

GuanghanWang

Remasking Discrete Diffusion Models with Inference-Time Scaling

·
4 authors

Submitted by

Franck-Dernoncourt

Mixture of Structural-and-Textual Retrieval over Text-rich Graph Knowledge Bases

·
8 authors

Submitted by

gsarti

QE4PE: Word-level Quality Estimation for Human Post-Editing

·
6 authors

Submitted by

Franck-Dernoncourt

Exploring Rewriting Approaches for Different Conversational Tasks

·
12 authors

Submitted by

vansin

FLAME: A Federated Learning Benchmark for Robotic Manipulation

·
5 authors

Submitted by

vansin

Retrieval Models Aren't Tool-Savvy: Benchmarking Tool Retrieval for Large Language Models

·
7 authors

Submitted by

vansin

Benchmarking Large Language Models for Multi-Language Software Vulnerability Detection

·
11 authors

Submitted by

vansin

CognitiveDrone: A VLA Model and Evaluation Benchmark for Real-Time Cognitive Task Solving and Reasoning in UAVs

·
8 authors

Submitted by

yuemithucsd

Reliable and Efficient Multi-Agent Coordination via Graph Neural Network Variational Autoencoders

·
6 authors

2

Submitted by

yuemithucsd

Diverse Controllable Diffusion Policy with Signal Temporal Logic

·
2 authors

2

Submitted by

vansin

SwiLTra-Bench: The Swiss Legal Translation Benchmark

·
19 authors

Submitted by

FanGShiYuu

Interact, Instruct to Improve: A LLM-Driven Parallel Actor-Reasoner Framework for Enhancing Autonomous Vehicle Interactions

·
6 authors