AI.info

Latest Research — Page 77

Browse Latest Research on AI.info.

• Mitigating Reward Hacking in RLHF via Bayesian Non-negative Reward Modeling
• Efficient Low Rank Attention for Long-Context Inference in Large Language Models
• SimRPD: Optimizing Recruitment Proactive Dialogue Agents through Simulator-Based Data Evaluation and Selection
• $D^2Prune$: Sparsifying Large Language Models via Dual Taylor Expansion and Attention Distribution Awareness
• BackDFL: A Unified Benchmark For Backdoor Attacks and Defenses In Decentralized Federated Learning
• Benchmark Datasets for Lead-Lag Forecasting on Social Platforms
• Equivariance by Contrast: Identifiable Equivariant Embeddings from Unlabeled Finite Group Actions
• Rethinking Long-tailed Dataset Distillation: A Uni-Level Framework with Unbiased Recovery and Relabeling
• Benchmarking Probabilistic Time Series Forecasting Models on Neural Activity
• HexMIL: Hierarchical Attention MIL for Ante-Hoc Explainable Detection of AI-Manipulated CT Volumes
• PatientHub: A Unified Framework for Patient Simulation
• Breaking the Modality Barrier: Generative Modeling for Accurate Molecule Retrieval from Mass Spectra
• D-CoDe: Scaling Image-Pretrained VLMs to Video via Dynamic Compression and Question Decomposition
• AnchorDS: Anchoring Dynamic Sources for Semantically Consistent Text-to-3D Generation
• WIND: Weather Inverse Diffusion for Zero-Shot Atmospheric Modeling
• ESCORT: Efficient Stein-variational and Sliced Consistency-Optimized Temporal Belief Representation for POMDPs
• OccuFly: A 3D Vision Benchmark for Semantic Scene Completion from the Aerial Perspective
• Incentivizing Agentic Reasoning in LLM Judges via Tool-Integrated Reinforcement Learning
• AgencyBench: Benchmarking the Frontiers of Autonomous Agents in 1M-Token Real-World Contexts
• Uni-DAD: Unified Distillation and Adaptation of Diffusion Models for Few-step Few-shot Image Generation
• Point-SRA: Self-Representation Alignment for 3D Representation Learning
• Evolve to Inspire: Novelty Search for Diverse Image Generation
• PlayWorld: Benchmarking World Models with Agent Players over Long-Horizon Objectives
• Towards Scalable Meta-Learning of near-optimal Interpretable Models via Synthetic Model Generations
• RL-VLA$^3$: A Flexible and Asynchronous Reinforcement Learning Framework for VLA Training
• MIND: Multi-rationale INtegrated Discriminative Reasoning Framework for Multi-modal Large Models
• Decoupling Planning and Control for Instructable Agents
• Learning Vision-Driven Reactive Soccer Skills for Humanoid Robots
• Your VAR Model is Secretly an Efficient and Explainable Generative Classifier
• SpecGuard: Spectral Projection-based Advanced Invisible Watermarking
• NurseLLM: The First Specialized Language Model for Nursing
• Low-Back Pain Physical Rehabilitation by Movement Analysis in Clinical Trial
• An Evolutionary Algorithm Assisted by an Ensemble of Pareto-Optimal Surrogate Models
• Periodic Skill Discovery
• Per-Axis Weight Deltas for Frequent Model Updates
• Real Garment Benchmark (RGBench): A Comprehensive Benchmark for Robotic Garment Manipulation featuring a High-Fidelity Scalable Simulator
• Emergent Coordinated Behaviors in Networked LLM Agents: Modeling the Strategic Dynamics of Information Operations
• Multi-Objective Reinforcement Learning with Max-Min Criterion: A Game-Theoretic Approach
• Multimodal Negative Learning
• RAIGen: Rare Attribute Identification in Text-to-Image Generative Models