Ежедневные Исследовательские Статьи по ИИ

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

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

Process-based Self-Rewarding Language Models

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

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

ABC: Achieving Better Control of Multimodal Embeddings using VLMs

Enhancing Abnormality Grounding for Vision Language Models with Knowledge Descriptions

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

CrowdSelect: Synthetic Instruction Data Selection with Multi-LLM Wisdom

Remasking Discrete Diffusion Models with Inference-Time Scaling

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

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

Exploring Rewriting Approaches for Different Conversational Tasks

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

FLAME: A Federated Learning Benchmark for Robotic Manipulation

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

Benchmarking Large Language Models for Multi-Language Software Vulnerability Detection

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

Diverse Controllable Diffusion Policy with Signal Temporal Logic

SwiLTra-Bench: The Swiss Legal Translation Benchmark

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