Scaling Vision-Language Models Is Not Enough to Mitigate Bias
Explorar
Noticias de IA
21863 elementos — filtrados, clasificados y sin duplicados
Fidelity Is Not Safety: Gently-Compressed LLMs Pass Every Data-Free Quality Guard Yet Inv…
Persistent Gaussian Perturbations Prevent Oversmoothing in Recurrent Graph Neural Networks
Multi-channel Uplift Policy Learning
Rethinking LLM-Judged Helpfulness as a Pedagogy Signal: A Pre-Registered Audit Across Tut…
ConMem: Contribution-Aware Memory for Long-Horizon Manufacturing Inspection Logs
Towards Practical Algorithm Selection for Unsupervised Domain Adaptation in Medical Imagi…
Distilling Answer Set Programming Theories from Large Language Models
LEEPS: Latent-Guided Explore-Exploit Prompt Sampling for Efficient RLVR in Large Language…
Echoverse: Deep, Evolving Environments for Training Computer-Use Agents at Scale
A Query-Efficient Stochastic Volume Rendering Framework for Time-Varying Implicit Neural …
Contrastive Reinforced Policy Optimization via Privileged Self-Distillation
Flux-OPD: On-Policy Distillation with Evolving Contexts
Share the Judge, Learn the Deferral: Where Specialization Helps LLM Evaluation
ViP-Rig: Visual-Prompted Controllable Rigging
Generalization Bounds on Optimal Control for Transformer Training and Wasserstein Distrib…
A fundamental flaw leaves LLMs strikingly vulnerable to attack
MARS-RA: Rank Aggregation for Credit Assignment via Multimodal Comparisons in Embodied Mu…
What Makes Graph Unified? Principles and Generative Sliding-Window Transformer for Graph …
FiRE: Enhancing MLLMs with Fine-Grained Context Learning for Complex Image Retrieval
LAST: The Last Query Token Guides Visual Token Pruning for Edge-Cloud Collaborative MLLM …
The Geometric Nature and a Free Proxy for Flow-Matching Uncertainty
ODEWorld: A Continuous Predictive Architecture via Physical-Time Flow
Memory Decoder at Scale: A Pretrained, Parametric Long-Term Memory
S-CEReBrO: Breaking the Memory Barrier in Continuous EEG Monitoring
IFHierBench: Hierarchical Instruction Following for Large Language Models
Integrating Contextual Embeddings into Evaluation of Expressive MIDI Piano Performances
Class-Aware Reinforcement Learning for Counterfactual Explanation Generation
One Patch Is Enough: Reinforcement-Optimized Visual Token Grounding for MLLM-Based Scene …
CoRE-UIR: Prior-guided common and residual experts for efficient all-in-one remote sensin…