arXiv
When Good Verifiers Go Bad: Self-Improving VLMs Can Regress on New Tasks
Verifier-driven self-DPO is a common recipe for self-improving production visual-language models. In this setup, a fr...
🤖 AI 前沿资讯
每天自动聚合 AI 领域最新动态
arXiv
From Self-Supervised Speech Models to Mixture-of-Experts for Robust Anti-Spoofing
Recent advances in speech generation have significantly improved the naturalness of synthetic speech, making spoofing...
arXiv
Listening with Attention: Entropy-Guided Explainability for Transformer-Based Audio Models
Transformer-based automatic speech recognition (ASR) models such as Whisper are highly accurate, but their prediction...
arXiv
Abstracting Cross-Domain Action Sequences into Interpretable Workflows
Sequential or time-stamped interaction logs provide objective records of digital application usage, yet their granula...
arXiv
Giving AI a Headache: Acoustic Adversarial Attacks to Computer Vision Applications
Artificial Intelligence (AI) is increasingly used to automate a variety of real-world computer vision (CV) applicatio...
arXiv
Towards Direct Latent-Space Synthesis for Parallel Branches in LLM-Agent Workflows
Large language models increasingly serve as execution engines for agentic systems, yet they still consume context thr...
arXiv
CottonLeafVision: An Explainable and Robust Deep Learning Framework for Cotton Leaf Disease Classification
Globally, cotton is a highly economically beneficial crop, as the textile industry heavily depends on it. So, the pre...
arXiv
Flood and Harvest: The Provable Necessity of Trivia for Generating Valuable Mathematics via the Lens of Language Generation in the Limit
AI systems coupled to proof assistants now generate formal mathematics at scale, and the gap between what a checker c...
arXiv
Learning Coordinated Preference for Multi-Objective Multi-Agent Reinforcement Learning
Cooperative multi-objective multi-agent reinforcement learning (MOMARL) models team decision making under multiple, p...
arXiv
ClinHallu: A Benchmark for Diagnosing Stage-Wise Hallucinations in Medical MLLM Reasoning
Building trustworthy medical multimodal large language models (MLLMs) is critical for reliable clinical decision supp...
HuggingFace
μ_0: A Scalable 3D Interaction-Trace World Model
World models that capture how actions induce physical change enable scalable robot learning without reliance on embod...
HuggingFace
HarnessX: A Composable, Adaptive, and Evolvable Agent Harness Foundry
AI agent performance depends critically on the runtime harness, comprising the prompts, tools, memory, and control fl...