Portada · pág. 45

← primera página

GeoFitBench-LLM: A Benchmark for Assessing Large Language Models' Capabilities in Geospatial Data Requirements Elicitation for Geo-Analytic Tasks
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
Unsupervised Multimodal Reward Modeling
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
KITE: A Knowledge-Injected Temporal Encoder for Time-Series Event Forecasting
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
Trajectory Prediction for Autonomous Driving in Road Construction Zones Using Human-in-the-Loop Driving Data
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
Semantic Views: Certified Reuse of LLM Labels Across Semantic Queries
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
REDaCT: Collapse-Free Unlearning in Large Reasoning Models
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
Meta-Reflective Evolution Effectively Improves Production AI Systems
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
Efficient Audio-Visual Speech Enhancement via Reinforcement Learning-Based Neural Architecture Search
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
LeWAM: End-to-End World and Action Modeling with JEPAs
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
COFFEQA: Counterfactual-Guided Few-Shot Distillation for LLM Question Answering
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
When Generative Models Act as Simulators
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
Co-Modifying Application Code and Deployment Infrastructure: A Causal Study of AI Agent Pull Requests
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
Localized Generative Design of Ship Hulls with Diffusion Models and High-Fidelity Assessment
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
Surfing the Activation Wave: Analyzing the Information and Geometry of LLM Hidden States for Speculative Decoding
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
JoyInside-VLM-Agent: Product-Conditioned Multimodal Policy Learning for Embodied Agents
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
MotionCoach: Constructing Multimodal Guidance for Video Professional Motion Editing
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
The Evidence Anchoring Boundary: Where Visual Interventions Matter and When They Help in Multimodal LLMs
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
What Should SFT Learn? Conditional Information Gain for Generalizable Post-Training
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
Generalized Proximal Policy Optimization: Unifying LLM RL Algorithms from the Perspective of Divergence
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
Don't Guess, Just Ask: Evaluating Interactive Requirement Clarification for Repository-Level Software Development
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
GeoGR: Spatial-Semantic Token Compression and Group Routing for Efficient 3D VLMs
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
CoBe: A Benchmark For Conversational Counterfactual Text Editing
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
Evolving Creatives with Clicks: CTR-Driven Advertising image Editing via Attribute Disentanglement and Preference Alignment
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
Continually Post-training Small Models via Synthetic Self-distillation
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
Does Learning Recurrent Networks Matter in Partially Observable RL?
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
Beyond Actions: Learning Future Operation Targets for Vision-Language-Action Models
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
ReSFlow: Rectifying Categorical Flows on Statistical Manifolds for One-Step Generation
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
How Reliable are AMR Parser Outputs? Uncertainty Estimation for AMR Parsing
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
Tabular Foundation Models Are Effectively Shallow
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
Agent4Spec: An LLM-based Agentic System to Optimize API Specifications through Automated Validation and Market Analysis
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
PRIME: Pre-Retrieval Index Modeling Enhancement for Structured Document Retrieval-Real
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
Agreement Without Alignment: Label-Free Rubric Clarification Increases LLM-Judge Consensus but Not Agreement with Humans
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
AgentSWE: Can Coding Agents Build the Agent You Actually Want?
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
ProgramGym: Scaling Training Environments for Long-Horizon Program Reproduction Agents
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
In-Context Learning for System Identification: Probabilistic Formulation, Long-Sequence Handling, and Benchmark Validation
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
CNN-Transformer with Sigmoid Label for High-Resolution Sub-Degree DOA Estimation
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
Collective Autonomous Vehicle Routing Needs Social Awareness for Coexistence with Human Drivers
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
When MLLMs miss what humans read: diagnosing and learning to read squint text
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
Beyond Temporal Proximity: Explanatory World Models for Credit Assignment in Reinforcement Learning
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
RESCUE: Is This Alarm Worth Acting On? Counterfactual Evaluation of VLA Runtime Monitors
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
Defence against the dark arts of distillation: Unsupervised discovery of subliminal learning
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
AudioTETRIS: Token Elimination via Transitional Importance Signals for Efficient Audio LLMs
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
SWE-DeceptionBench: Benchmarking Deceptive Behaviors of LLMs Across the Software Development Lifecycle
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
Model-agnostic Knowledge Augmented Machine Learning for Weakly Annotated Bioimaging Data
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
SelectArena: A Modern Benchmark for Feature Selection on Real-world Tabular Data
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
Pretraining and Test-Time Training Budgets Matter for ARC: A Controlled Study of VARC and TRM
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
Inject a Turn, Not a Token: Learning Where to Redirect LLM Reasoning for Self-Correction
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
Not All Dimensions Are Equal: Outlier-Aware Attention Linearization with Grouped Quadratic Kernels
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
Variance-Reduced Policy Gradient is Nearly Minimax-Optimal
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
Calibration in One Go: Jointly Learning Accurate and Calibrated Neural Networks
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle