arXiv
Adaptive Critical Token-Aware Retrieval for Repository-Level Code Generation
The repository-level code generation task requires synthesizing code that satisfies task requirements while remaining...
🤖 AI 前沿资讯
每天自动聚合 AI 领域最新动态
arXiv
Efficient SWE Agent Benchmarking via Trajectory-Aware Evaluation
Evaluating software engineering agents on realistic benchmarks is costly, since each task may require multi-step code...
HuggingFace
The Mechanics of Democratic Dominance: A System Dynamics Paradigm for Dynamic Consent Engineering
Traditional frameworks of political communication operate under linear, event-driven assumptions that treat voter per...
HuggingFace
InternReviewer & InternAdvocate: Objective Reward and Evaluation for Agentic Reinforcement Learning in Peer Review and Rebuttal
Generating professional scholarly content, such as peer reviews and rebuttals, requires an intricate synergy between ...
HuggingFace
ReFlowSET: Representation-Aligned Latent Flow Matching for SAR-to-EO Image Translation
SAR-to-EO image translation aims to generate electro-optical (EO) imagery from synthetic aperture radar (SAR) observa...
HuggingFace
EM^2Mem: Event-Centric Multimodal Memory for Large Language Models
Multimodal memory offers a scalable interface for long-video question answering, but existing methods often retrieve ...
HuggingFace
Hi-Q: Hierarchical Evidence-guided Query Refinement for Multi-Hop Question Answering
A central bottleneck in multi-hop Question Answering (QA) is that the granularity at which a question is expressed of...
HuggingFace
Uncovering Understanding-Generation Synergy in Native Unified Multimodal Models: From Representation, Task to System
While unified multimodal models (UMMs) jointly perform visual understanding and generation within a single model, fun...
HuggingFace
Control-Data Flow Separation: Stable Prompt Optimization in Multi-Agent LLMs
Prompt optimization can improve multi-agent LLM systems, but the prompts being optimized often serve two entangled ro...
HuggingFace
Evaluating Multimodal LLMs as Generalist Vision-Language-Action Agents for Drone Control: Commanding, Approaching, Tracking and Searching
Multimodal Large Language Models (MLLMs) are strong perceivers of images and video. We ask how far that reach extends...
HuggingFace
StudentSim: Training LLM-based Student Simulators
AI tutors are most useful when they adapt to each student's strengths, weaknesses, and preferred guidance, but eviden...
HuggingFace
H3-World: Turning Language Understanding into World Control
We present H3-World, an efficient framework that turns the 33B MiniMax-H3 video generator into an interactive world m...