Trending Research
TxAgent: An AI Agent for Therapeutic Reasoning Across a Universe of Tools
It selects tools based on task objectives and executes structured function calls to solve therapeutic tasks that require clinical reasoning and cross-source validation.
TextGrad: Automatic "Differentiation" via Text
Without modifying the framework, TextGrad improves the zero-shot accuracy of GPT-4o in Google-Proof Question Answering from $51\%$ to $55\%$, yields $20\%$ relative performance gain in optimizing LeetCode-Hard coding problem solutions, improves prompts for reasoning, designs new druglike small molecules with desirable in silico binding, and designs radiation oncology treatment plans with high specificity.
Ranked #4 on
on GPQA
HealthGPT: A Medical Large Vision-Language Model for Unifying Comprehension and Generation via Heterogeneous Knowledge Adaptation
To effectively learn the HealthGPT, we devise a comprehensive medical domain-specific comprehension and generation dataset called VL-Health.
Docling Technical Report
DS4SD/docling
•
•
This technical report introduces Docling, an easy to use, self-contained, MIT-licensed open-source package for PDF document conversion.
Why Do Multi-Agent LLM Systems Fail?
In this paper, we present the first comprehensive study of MAS challenges.
DEIM: DETR with Improved Matching for Fast Convergence
We introduce DEIM, an innovative and efficient training framework designed to accelerate convergence in real-time object detection with Transformer-based architectures (DETR).
Ranked #1 on
Real-Time Object Detection
on MS COCO
(using extra training data)
Reinforcement Learning Outperforms Supervised Fine-Tuning: A Case Study on Audio Question Answering
Recently, reinforcement learning (RL) has been shown to greatly enhance the reasoning capabilities of large language models (LLMs), and RL-based approaches have been progressively applied to visual multimodal tasks.
Sample-Efficient Alignment for LLMs
sail-sg/oat
•
•
The results demonstrate that SEA achieves highly sample-efficient alignment with oracle's preferences, outperforming recent active exploration methods for LLMs.
XAttention: Block Sparse Attention with Antidiagonal Scoring
In this paper, we introduce XAttention, a plug-and-play framework that dramatically accelerates long-context inference in Transformers models using sparse attention.
Twin-Merging: Dynamic Integration of Modular Expertise in Model Merging
In view of this, we propose Twin-Merging, a method that encompasses two principal stages: (1) modularizing knowledge into shared and exclusive components, with compression to reduce redundancy and enhance efficiency; (2) dynamically merging shared and task-specific knowledge based on the input.
