arXiv
Trade-offs in Medical LLM Adaptation: An Empirical Study in French QA
The development of large language models (LLMs) has led to an increased focus on their adaptation to specialized doma...
🤖 AI 前沿资讯
每天自动聚合 AI 领域最新动态
arXiv
NeSyCat Torch: A Differentiable Tensor Implementation of Categorical Semantics for Neurosymbolic Learning
Neurosymbolic semantics is fragmented: classical, fuzzy, probabilistic and neural systems each define truth by their ...
arXiv
Correct Yourself, Keep My Trust: How Self-Correction and Social Connection Shape Credibility in Social Chatbots
When social chatbots make mistakes, and they do, how they recover determines whether users trust them again. Social c...
arXiv
Explaining Attention with Program Synthesis
A longstanding goal of research on interpretable deep learning is to replace opaque neural computations with human-me...
arXiv
Data Intelligence Agents: Interpreting, Modeling, and Querying Enterprise Data via Autonomous Coding Agents
Production data integration is bottlenecked by repeated, lossy handoffs between data owners, engineers, and analysts ...
arXiv
Reference-Driven Multi-Speaker Audio Scene Generation from In-the-Wild Priors
Existing multi-speaker dialogue systems bind speakers to utterances through structured supervision: per-turn tags, mu...
arXiv
Rethinking Reward Supervision: Rubric-Conditioned Self-Distillation
Post-training of reasoning language models is commonly driven by supervised distillation and reinforcement learning w...
arXiv
UBP2: Uncertainty-Balanced Preference Planning for Efficient Preference-based Reinforcement Learning
Preference-based RL provides an approach to learning reward models from pairwise comparisons of behaviors, bypassing ...
HuggingFace
Verified Detection and Prevention of Concurrency Anomalies in Multi-Agent Large Language Model Systems
Multi-agent LLM systems share state through memory stores, vector indices, and tool registries. We model such sharing...
HuggingFace
Self-Evolving Visual Questioner
Vision-language models (VLMs) are typically trained as passive answerers, while their ability to actively ask diverse...
HuggingFace
Beyond Scalar Distances: Semantic Attribute Gradients from Frozen MLLMs for Visual Embeddings
Vision encoders for retrieval are typically trained with class-label supervision: each training pair reduces to a sca...
HuggingFace
Speaking the Language of Science: Toward a General-Purpose Generative Foundation Model for the Natural Sciences
In this report, we present LOGOS (Language Of Generative Objects in Science), a scientific generative language model ...