Español

Explorar

Noticias de IA

27413 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
The Information Geometry of Softmax: Probing and Steering
arXiv cs.AI Research & Papers
SCOPE: Selective Conformal Optimized Pairwise LLM Judging
arXiv cs.AI Research & Papers
HERMES: Towards Efficient and Verifiable Mathematical Reasoning in LLMs
arXiv cs.AI Research & Papers
Post-Training LLMs as Better Decision-Making Agents: A Regret-Minimization Approach
arXiv cs.AI Research & Papers
OLG++: A Semantic Extension of Obligation Logic Graph
arXiv cs.AI Research & Papers
ProofWala: A Framework for Multilingual Proof Data Synthesis and Theorem-Proving
arXiv cs.AI Research & Papers
PAC-Bayesian Reinforcement Learning Trains Generalizable Policies
arXiv cs.AI Research & Papers
Unifying and Optimizing Data Values for Selection via Sequential Decision-Making
arXiv cs.AI Research & Papers
TunerDiT: Training-free Progressive Steering of Diffusion Transformer for Multi-Event Vid…
arXiv cs.AI Research & Papers
Vision-Language Models Suppress Female Representations Under Ambiguous Input
arXiv cs.AI Research & Papers
DynaTree: Dynamic Agentic Retrieval Tree for Time-Sensitive News Retrieval
arXiv cs.AI Research & Papers
Positional versus Symbolic Attention Heads: Learning Dynamics, RoPE Geometry, and Length …
arXiv cs.AI Research & Papers
Plain Transformers are Surprisingly Powerful Link Predictors
arXiv cs.AI Research & Papers
SVL: Goal-Conditioned Reinforcement Learning as Survival Learning
arXiv cs.AI Research & Papers
FBHM: Functional Benchmarking and Steering of VLMs for Hateful Meme Detection
arXiv cs.AI Research & Papers
Pull Requests as a Training Signal for Repo-Level Code Editing
arXiv cs.AI Research & Papers
FreeTimeGS++: Secrets of Dynamic Gaussian Splatting and Their Principles
arXiv cs.AI Research & Papers
Circuit-Inspired High-Order Neural Networks with Unified Neural Dynamics Modeling for PDE…
arXiv cs.AI Research & Papers
RayDer: Scalable Self-Supervised Novel View Synthesis from Real-World Video
arXiv cs.AI Research & Papers
Social welfare optimisation under institutional reward and punishment
arXiv cs.AI Research & Papers
Latent Space Disentanglement via Activation Steering for Interpretable Attribute Control …
arXiv cs.AI Research & Papers
Compile to Compress: Boosting Formal Theorem Provers by Compiler Outputs
arXiv cs.AI Research & Papers
World Action Verifier: Self-Improving World Models via Forward-Inverse Asymmetry
arXiv cs.AI Research & Papers
On Efficient Scaling of GNNs via IO-Aware Layers Implementations
arXiv cs.AI Research & Papers
Simulation of collision avoidance behavior in crowd movement by data-driven approach
arXiv cs.AI Research & Papers
Shared Doubt: Zero-shot Cross-Lingual Confidence Estimation for Language Models
arXiv cs.AI Research & Papers
Unraveling LoRA Interference: Orthogonal Subspaces for Robust Model Merging
arXiv cs.AI Research & Papers
AutoSci: A Memory-Centric Agentic System for the Full Scientific Research Lifecycle
arXiv cs.AI Research & Papers
Functorial Neural Architectures from Higher Inductive Types
arXiv cs.AI Research & Papers
Fine-grained Verification via Diagnostic Reasoning Supervision for Aspect Sentiment Tripl…