AI.info

Latest Research — Page 79

Browse Latest Research on AI.info.

• AutoBrep: Autoregressive B-Rep Generation with Unified Topology and Geometry
• Accelerating Accurate Assignment Authoring Using Solution-Generated Autograders
• AutoOpt: A Dataset and a Unified Framework for Automating Optimization Problem Solving
• Enough is as good as a feast: A Comprehensive Analysis of How Reinforcement Learning Mitigates Task Conflicts in LLMs
• The Structure of Quantization Damage in LLMs: Why the Next Bit Should Be Spent Globally
• Arguments that Alter Minds: LLM Rationales Sway Human (and LLM) Notions of Plausibility
• TopoAlign: A Framework for Aligning Code to Math via Topological Decomposition
• Satellite Trajectory Optimization via Proximal Policy Optimization for Space Debris Avoidance
• LazyHMC: Hamiltonian Monte Carlo Simulation for Lazy, Infinite Dimensional Probabilistic Programs
• Select-Then-Decompose: From Empirical Analysis to Adaptive Selection Strategy for Task Decomposition in Large Language Models
• HandMvNet: Real-Time 3D Hand Pose Estimation Using Multi-View Cross-Attention Fusion
• Multimodal Datasets with Controllable Mutual Information
• Lookahead Sample Reward Guidance for Test-Time Scaling of Diffusion Models
• Iteratively Refined Early Interaction Alignment for Subgraph Matching based Graph Retrieval
• Divide-and-Conquer Decoupled Network for Cross-Domain Few-Shot Segmentation
• WeaveTime: Stream from Earlier Frames into Emergent Memory in VideoLLMs
• Tactile Data Recording System for Clothing with Motion-Controlled Robotic Sliding
• General Quantification of Covariate and Concept Shifts
• Seeing Justice Clearly: Handwritten Legal Document Translation with OCR and Vision-Language Models
• Localized Adaptation Reveals Distinct Learning Signatures in Transformers
• LaoBench: A Large-Scale Multidimensional Lao Benchmark for Large Language Models
• Hidden Errors in Big Data: The Case of Property Records
• InfinityStar: Unified Spacetime AutoRegressive Modeling for Visual Generation
• TokenSeek: Memory Efficient Fine Tuning via Instance-Aware Token Ditching
• Dynamic SpectraFormer for Ultra-High-Definition Underwater Image Enhancement
• CompAgent: An Agentic Framework for Visual Compliance Verification
• Online Generic Event Boundary Detection
• Can Vision-Language Models Assess Proxemic Risk from Egocentric Robot Images?
• Fixed Budget is No Harder Than Fixed Confidence in Best-Arm Identification up to Logarithmic Factors
• Group-Aware Reinforcement Learning for Output Diversity in Large Language Models
• PaperGym: Rubric-Centered Evolution for Research-Plan Generation
• PRiSM: Benchmarking Phone Realization in Speech Models
• TimePerceiver: An Encoder-Decoder Framework for Generalized Time-Series Forecasting
• C-NAV: Towards Self-Evolving Continual Object Navigation in Open World
• HiF-VLA: Hindsight, Insight and Foresight through Motion Representation for Vision-Language-Action Models
• Dynamic Retriever for In-Context Knowledge Editing via Policy Optimization
• Intuitive Programming, Adaptive Task Planning, and Dynamic Role Allocation in Human-Robot Collaboration
• Adapting MLLMs for Nuanced Video Retrieval
• CoCo-IR: Contextual Composed Image Retrieval
• LangHOPS: Language Grounded Hierarchical Open-Vocabulary Part Segmentation