AI.info
Latest Research — Page 107
Browse Latest Research on AI.info.
- Zero-Shot Novel Depth Synthesis Using 3D Foundation Models Scene Representations
- 3D-Consistent Multi-View Editing by Correspondence Guidance
- ReTerm: Recovery Training for Self-Improving Terminal Agents
- LSA: Localized Semantic Alignment for Enhancing Temporal Consistency in Traffic Video Generation
- Language Chain in Alignment: Cross-lingual Ranking Preference Optimization
- An RGB-D Image Dataset for Lychee Detection and Maturity Classification for Robotic Harvesting
- LABBench2: An Improved Benchmark for AI Systems Performing Biology Research
- Visual Implicit Geometry Transformer for Autonomous Driving
- Human-to-Robot Transfer via Bridging Representation and Action Space in VLAs
- Smooth trajectory generation and hybrid B-splines-Quaternions based tool path interpolation for a 3T1R parallel kinematic milling robot
- OBB-PBD: Extending Parallel Box Decoding to Oriented Bounding Boxes for Referring Expression Grounding in Aerial Imagery
- Hear, Localize, and Reason: Spatially Aware Scene Understanding for Audio-Visual LLMs
- UG-UMRE: Uncertainty-Guided Modality Augmentation and Distributional Calibration for Unified Multimodal Relation Extraction
- Surgical Repair of Collapsed Attention Heads in ALiBi Transformers
- Balanced conic rectified flow
- Enhancing Mathematical Problem Solving in LLMs through Execution-Driven Reasoning Augmentation
- OSWorld-MCP: Benchmarking MCP Tool Invocation In Computer-Use Agents
- Optimizing the Unknown: Black Box Bayesian Optimization with Energy-Based Model and Reinforcement Learning
- MCPAgentBench: A Real-world Task Benchmark for Evaluating LLM Agent MCP Tool Use
- Removing the NEEDLE in the Haystack: Backdoor Removal in LLMs via Weight Orthogonalisation
- Watermarking for Factuality: Guiding Vision-Language Models Toward Truth via Tri-layer Contrastive Decoding
- Scalable Single-Cell Gene Expression Generation with Latent Diffusion Models
- CausalTrace: A Neurosymbolic Causal Analysis Agent for Smart Manufacturing
- Empirical Likelihood-Based Fairness Auditing: Distribution-Free Certification and Flagging
- CDFlow: Building Invertible Layers with Circulant and Diagonal Matrices
- Explicit World Models for Reliable Human-Robot Collaboration
- Control-Data Flow Separation: Stable Prompt Optimization in Multi-Agent LLMs
- Metadata-Aware Multi-Prompt Reasoning for Zero-Shot Accident Understanding
- OmniSpectra: A Unified Foundation Model for Universal Spectra Representation Learning
- No Cache Left Idle: Accelerating diffusion model via Extreme-slimming Caching
- Assessing LLM Reasoning Steps via Principal Knowledge Grounding
- SALVE: Sparse Autoencoder-Latent Vector Editing for Mechanistic Control of Neural Networks
- End-to-end PDDL Planning with Hardcoded and Dynamic Agents
- ChartE$^{3}$: A Comprehensive Benchmark for End-to-End Chart Editing
- When Does Multi-Agent Collaboration Help? An Entropy Perspective
- From Pareto to Preference: Personalized Test-Time Scaling via Amortized Agentic Policy Discovery
- Inter-X++: A Comprehensive Benchmark for Multimodal Human-Human Interaction Analysis
- RepForcing: Representation-Space Initialization for Autoregressive Video Distillation
- Not All Needles Are Found: How Fact Distribution and Don't Make It Up Prompts Shape Retrieval, Reasoning, and Hallucination in Long-Context LLMs
- M$^{3}$T2IBench: A Large-Scale Multi-Category, Multi-Instance, Multi-Relation Text-to-Image Benchmark