AI.info
Latest Research — Page 103
Browse Latest Research on AI.info.
- Task-Aware LLM Routing with Multi-Level Task-Profile-Guided Data Synthesis for Cold-Start Scenarios
- POSESTITCH-SLT: Linguistically Inspired Pose-Stitching for End-to-End Sign Language Translation
- Characterizing and Optimizing the Spatial Kernel of Multi Resolution Hash Encodings
- Skeletons Matter: Dynamic Data Augmentation for Text-to-Query
- MentisOculi: Revealing the Limits of Reasoning with Mental Imagery
- SCOPE: Saliency-Coverage Oriented Token Pruning for Efficient Multimodel LLMs
- AgentRouter: Heterogeneous Model Routing for Cost-Optimal Multi-Step Agentic Workflows
- Attention-Informed Surrogates for Navigating Power-Performance Trade-offs in HPC
- OneDayAgent: Towards a Long-Horizon Harness for Autonomous Agents
- Self-Rewarding PPO: Aligning Large Language Models with Demonstrations Only
- Analyzing Shapley Additive Explanations to Understand Anomaly Detection Algorithm Behaviors and Their Complementarity
- HoneyBee: Data Recipes for Vision-Language Reasoners
- SAHOO: Safeguarded Alignment for High-Order Optimization Objectives in Recursive Self-Improvement
- Pixel Seal: Adversarial-only training for invisible image and video watermarking
- Understanding Multi-View Transformers
- Sketch-to-Layout: Sketch-Guided Multimodal Layout Generation
- GeoWorld: Geometric World Models
- Context Tokens are Anchors: Understanding the Repetition Curse in dMLLMs from an Information Flow Perspective
- XModBench: Benchmarking Cross-Modal Capabilities and Consistency in Omni-Language Models
- Track, Inpaint, Resplat: Subject-driven 3D and 4D Generation with Progressive Texture Infilling
- Learning Intractable Multimodal Policies with Reparameterization and Diversity Regularization
- LiveStar: Live Streaming Assistant for Real-World Online Video Understanding
- From Abstract to Contextual: What LLMs Still Cannot Do in Mathematics
- HGAdapter: Hypergraph-based Adapters in Language Models for Code Summarization and Clone Detection
- Scal3R: Learning Efficient Multi-Relative Pose Query for Scalable Online 3D Reconstruction
- Towards Universal Computational Aberration Correction in Photographic Cameras: A Comprehensive Benchmark Analysis
- Foundation Inference Models for Ordinary Differential Equations
- When Derived Measurements Mislead: Quantifying and Mitigating LLM Over-Trust with Privileged-Modality Reliability Evidence
- Galaw at Gunita: Extended Reality Murals for Experiencing Filipino Art
- Semantic Glitch: Agency and Artistry in an Autonomous Pixel Cloud
- TIC-VLA: A Think-in-Control Vision-Language-Action Model for Robot Navigation in Dynamic Environments
- Multilingual Agent-Based World Modeling for Social Science
- Binary Quadratic Quantization: Beyond First-Order Quantization for Real-Valued Matrix Compression
- Neuron-Level Analysis of Cultural Understanding in Large Language Models
- LLaVA-FA: Learning Fourier Approximation for Compressing Large Multimodal Models
- Curing Miracle Steps in LLM Mathematical Reasoning with Rubric Rewards
- S$^2$Drug: Bridging Protein Sequence and 3D Structure in Contrastive Representation Learning for Virtual Screening
- EviGen: Predictive Evidence Scaffolding for Verifiable Clinical Rationale Generation
- Learning to Tessellate: Point Cloud Generation via Recursive Spectral Partitioning
- SEMPO: Lightweight Foundation Models for Time Series Forecasting