AI.info

Latest Research — Page 62

Browse Latest Research on AI.info.

• Skill-Pro: Learning Reusable Skills from Experience via Non-Parametric PPO for LLM Agents
• Can LLMs Tell Stories Out of Order? A Corpus and Benchmark for Nonlinear Narrative Generation
• CordisBench: Can Language Models Reason About Component Lifecycles in Dynamic Agent Harnesses?
• Efficient Adversarial Attacks on High-dimensional Offline Bandits
• Synthetic Series-Symbol Data Generation for Time Series Foundation Models
• IE-SRGS: An Internal-External Knowledge Fusion Framework for High-Fidelity 3D Gaussian Splatting Super-Resolution
• Yes FLoReNce, I Will Do Better Next Time! Agentic Feedback Reasoning for Humorous Meme Detection
• Case-Grounded Evidence Verification: A Framework for Constructing Evidence-Sensitive Supervision
• Spatial Memory Intelligence: Endowing World Models with Understanding-Driven Long-Term Memory
• Delving into Cascaded Instability: A Lipschitz Continuity View on Image Restoration and Object Detection Synergy
• When Depth Lies: Benchmarking Vision-Language Models on Mirror-Induced RGB-D Ambiguity
• $\rm{A}^{\rm{SAR}}$: $\varepsilon$-Optimal Graph Search for Minimum Expected-Detection-Time Paths with Path Budget Constraints for Search and Rescue (SAR)
• Rethinking Verification in Agent Harnesses
• Editing Images into Reusable Layers via Compositional Edit-Prior Distillation
• RadJEPA: Radiology Encoder for Chest X-Rays via Joint Embedding Predictive Architecture
• EpicWorldModel: Exploration-driven Planning with Latent World Models
• Identifiable Equivariant Networks are Layerwise Equivariant
• JockeyBench: Evaluating LLM Agents on Horse-Racing Decision-Making
• EmoRES-TTS: Residual-Enhanced Vector Steering for Emotional Speech Generation
• A Fast Heuristic Search Approach for Energy-Optimal Profile Routing for Electric Vehicles
• What Makes Low-Bit Quantization-Aware Training Work for Reasoning LLMs? A Systematic Study
• CRISP: Contact-Guided Real2Sim from Monocular Video with Planar Scene Primitives
• PIANO: Physics-informed Dual Neural Operator for Precipitation Nowcasting
• TowerMind: A Tower Defence Game Learning Environment and Benchmark for LLM as Agents
• Multiscale Policy Optimization for Long-Horizon LLM Agents
• Accelerating PDE Surrogates via RL-Guided Mesh Optimization
• SimULi: Real-Time LiDAR and Camera Simulation with Unscented Transforms
• Towards Reliable Retrieval in RAG Systems for Large Legal Datasets
• ProgRouter: Online Progress-Guided Orchestration for Multi-Agent LLM Workflows under Quality-Cost Tradeoffs
• 4Director: Controlling Video World Models with Rigid 3D Geometry
• Leveraging LLMs for Semi-Automatic Corpus Filtration in Systematic Literature Reviews
• Fine-Tuned LLMs Know They Don't Know: A Parameter-Efficient Approach to Recovering Honesty
• The MICCAI Federated Tumor Segmentation (FeTS) Challenge 2024: Efficient and Robust Aggregation Methods for Federated Learning
• Distribution Matching for Graph Quantification Under Structural Covariate Shift
• T2AV-Compass: Towards Unified Evaluation for Text-to-Audio-Video Generation
• From Evidence-Based Medicine to Knowledge Graph: Retrieval-Augmented Generation for Sports Rehabilitation and a Domain Benchmark
• AlayaVista: Streaming World Modeling from Panoramic States to Perspective Video
• CorpusQA: A 10 Million Token Benchmark for Corpus-Level Analysis and Reasoning
• SpatialOPSD: Self-Distilling Spatial Intelligence from Verified Coding Agent Traces
• MPD-SGR: Robust Spiking Neural Networks with Membrane Potential Distribution-Driven Surrogate Gradient Regularization