Español

Explorar

Noticias de IA

30321 elementos — filtrados, clasificados y sin duplicados

Todos Models & Releases Research & Papers Funding & M&A Policy & Regulation Product Launches Industry Moves Developer Tooling Opinion & Editorial Security & Safety Other
arXiv cs.AI Research & Papers
Improved Guarantees for Heterogeneous Treatment-Effect Estimation via Matrix Completion
arXiv cs.AI Research & Papers
Self-Supervised Laplace Approximation for Bayesian Uncertainty Quantification
arXiv cs.AI Security & Safety
The Distillation Game: Adaptive Attacks & Efficient Defenses
arXiv cs.AI Research & Papers
MedMosaic: A Challenging Large Scale Benchmark of Diverse Medical Audio
arXiv cs.AI Research & Papers
When Models Learn to Ask Why: Adaptive Causal Reasoning for Trustworthy Medical Vision-La…
arXiv cs.AI Research & Papers
Entropy-KL Divergence-based Token Masking: A Novel Approach for Selective Fine-tuning of …
arXiv cs.AI Research & Papers
In-Context Reward Adaptation for Robust Preference Modeling
arXiv cs.AI Research & Papers
Reasoning about Reasoning: BAPO Bounds on Chain-of-Thought Token Complexity in LLMs
arXiv cs.AI Research & Papers
COMET: Concept Space Dissection of the Modality Gap in Audio-Text Multimodal Contrastive …
arXiv cs.AI Research & Papers
Architecture-Induced Recoverability Bias in Differentiable Symbolic Regression
arXiv cs.AI Research & Papers
Temporal Stability and Few-Shot Prompting in Math Task Assessment
arXiv cs.AI Research & Papers
Inferring Code Correctness from Specification
arXiv cs.AI Research & Papers
SERC: LDPC-Inspired Semantic Error Correction for Retrieval-Augmented Generation
arXiv cs.AI Research & Papers
Thoughts-as-Planning: Latent World Models for Chain-of-Thoughts Optimization via Reinforc…
arXiv cs.AI Research & Papers
Make LLM Learn to Synthesize from Streaming Experiences through Feedback
arXiv cs.AI Research & Papers
Honest Lying: Understanding Memory Confabulation in Reflexive Agents
arXiv cs.AI Research & Papers
Anchorless Diversification for Parallel LLM Ideation
arXiv cs.AI Research & Papers
Evolve as a Team: Collaborative Self-Evolution for LLM-based Multi-Agent Systems
arXiv cs.AI Research & Papers
Dissociative Identity: Language Model Agents Lack Grounding for Reputation Mechanisms
arXiv cs.AI Research & Papers
On Distributional Reinforcement Learning in Chaotic Dynamical Systems
arXiv cs.AI Research & Papers
Teaching Values to Machines: Simulating Human-Like Behavior in LLMs
arXiv cs.AI Research & Papers
KLAS: Using Similarity to Stitch Neural Networks for Improved Accuracy-Efficiency Tradeof…
arXiv cs.AI Research & Papers
No More K-means:Single-Stage Sparse Coding for Efficient Multi-Vector Retrieval
arXiv cs.AI Research & Papers
Inform, Coach, Relate, Listen: Auditing LLM Caregiving Support Roles
arXiv cs.AI Research & Papers
Wait! There's a Way Out: A Decision Mechanism for Forecasting Conversational Derailment
arXiv cs.AI Research & Papers
Relevance as a Vulnerability: How Web Retrieval Degrades Safety Alignment in LLM Agents
arXiv cs.AI Research & Papers
Rethinking FID Through the Geometry of the Reference Dataset
arXiv cs.AI Research & Papers
Beyond Normalization: Rethinking the Partition Function as a Difficulty Scheduler for RLVR
arXiv cs.AI Research & Papers
DialToM: A Theory of Mind Benchmark for Forecasting State-Driven Dialogue Trajectories
arXiv cs.AI Research & Papers
GPF-LiveNews: A Streaming Evaluation Protocol for Group-Conditioned Framing in Large Lang…