Smaller Models are Natural Explorers for Policy-Level Diversity in GRPO
Explorar
Noticias de IA
21757 elementos — filtrados, clasificados y sin duplicados
XLGoBench: Detecting cross-lingual skill gaps with algorithmic tasks
Beyond Agreement: Scoring Panel-Surfaced Biomedical Entity Candidates for Curator Triage
PatchWorld: Gradient-Free Optimization of Executable World Models
De-attribute to Forget for LLM Unlearning
Reading Between the Citations: A Typed Claim Network for Scientific Literature
AnchorSteer: Self-Discovered Concept Injection for Structure-Preserving Music Editing
Variational Adapter for Cross-modal Similarity Representation
Does Visual Information Play a Decisive Role in Vision-Language-Action Model Driving Beha…
On Revisiting Entropy for Identifying Mislabeled Images
SpecDB: LLM-Generated Customized Databases via Feature-Oriented Decomposition
From Evidence to Design: Developing an AI-Augmented UX Research Point of View for Digital…
Developing a UXR Point of View for Cognitive Accessibility in Mobile Learning with Genera…
D$^3$: Dynamic Directional Graph-Constrained Data Scheduling for LLM Training
Steering LLMs? Actually, Sparse Autoencoders can outperform simple baselines
Comparing LLM-Based Conversational and Graphical Interfaces for Industrial Decision Tasks…
EchoRL: Reinforcement Learning via Rollout Echoing
Beyond Classification: Dynamic Adapter Routing for Continual Multimodal Retrieval
ERGeoBench:A Comprehensive Benchmark for Embodied Reasoning and Geo-localization in Multi…
Personalized to Persuade: The Effects of Contextualization and Warmth on Trust and Relian…
DeMaVLA: A Vision-Language-Action Foundation Model for Generalizable Deformable Manipulat…
Chunking German Legal Code
PROWL: Prioritized Regret-Driven Optimization for World Model Learning
Much of Geospatial Web Search Is Beyond Traditional GIS
Spurious Correlation Learning in Preference Optimization: Mechanisms, Consequences, and M…
Autoregressive Visual Generation Needs a Prologue
Rays as Pixels: Learning A Joint Distribution of Videos and Camera Trajectories
Aligning Dense Retrievers with LLM Utility via Distillation
Targeted Speaker Poisoning Framework in Zero-Shot Text-to-Speech
Surprised by Attention: Predictable Query Dynamics for Time Series Anomaly Detection