AI.info
Latest Research — Page 43
Browse Latest Research on AI.info.
- Learning Molecular Chirality via Chiral Determinant Kernels
- VideoGen-Agent: Reinforcing Video Generation Agents
- Learning Sparse Decision Trees via Transformer Variational Auto-Encoders
- GMTRouter: Personalized LLM Router over Multi-turn User Interactions
- Evolving to Match Capabilities: Improving Harness Self-Evolution via Skill Adaptation
- H-DDCM: Hadamard Codebooks for Fast Generative Image and Video Compression
- Compact Example-Based Explanations for Language Models
- TabFM: A Zero-Shot Foundation Model for Tabular Data
- BlitzRank: Principled Zero-shot Ranking Agents with Tournament Graphs
- Sparse Methods for Vector Embeddings of TPC Data
- Capturing Head Avatar with Hand Contacts from a Monocular Video
- MALTopic: Multi-Agent LLM Topic Modeling Framework
- Neuro-Symbolic Geometric Abstraction (NeuSOGA): From Observations to Symbolic Mathematical Representations
- MolHop: Scaffold-Hopping Molecular Design with Agentic Reinforcement Learning
- What Does Privileged Information Add to On-Policy Self-Distillation?
- CUA-SWE: When Computer-Use Agents Meet Visual Software Engineering
- From Observations to Events: Event-Aware World Model for Reinforcement Learning
- AgentWorld: Benchmarking Long-Horizon Collaboration of Multi-agent LLMs
- SRAW-Attack: Space-Reweighted Adversarial Warping Attack for SAR Target Recognition
- Interpreting the Latent Structure of Operator Precedence in Language Models
- Easy-3Dfy: Object-Level Geometric Composition for Single-Image 3D Scene Construction
- Improving Day-Ahead Grid Carbon Intensity Forecasting by Joint Modeling of Local-Temporal and Cross-Variable Dependencies Across Different Frequencies
- Simulstream: Open-Source Toolkit for Evaluation and Demonstration of Streaming Speech-to-Text Translation Systems
- Ask a Strong LLM Judge when Your Reward Model is Uncertain
- NEMO: Execution-Aware Optimization Modeling via Autonomous Coding Agents
- Measuring What LLMs Think They Do: SHAP Faithfulness and Deployability on Financial Tabular Classification
- Contrast-X: A Multi-Modal Contrast Image Synthesis Benchmark and Universal Modality Flow Matching
- AdSpark: A Large-Scale Dataset and Benchmark for Product-Centric Advertisement Video Generation
- WDT-MD: Wavelet Diffusion Transformers for Microaneurysm Detection in Fundus Images
- BaseCal: Unsupervised Confidence Calibration via Base Model Signals
- EmbodiedSplat: Online Feed-Forward Semantic 3DGS for Open-Vocabulary 3D Scene Understanding
- The Information Geometry of Softmax: Probing and Steering
- Back to the Future: Rethinking EDA Infrastructure for Agentic Systems in Chip Design Verification
- Semantic Enrichment of CAD-Based Industrial Environments via Scene Graphs for Simulation and Reasoning
- CLIP4VI-ReID: Learning Modality-shared Representations via CLIP Semantic Bridge for Visible-Infrared Person Re-identification
- WOD-E2E: Waymo Open Dataset for End-to-End Driving in Challenging Long-tail Scenarios
- ViBED-Net: Video Based Engagement Detection Network Using Face-Aware and Scene-Aware Spatiotemporal Cues
- Compact Prompting in Instruction-tuned LLMs for Joint Argumentative Component Detection
- Pareto-Conditioned Diffusion Models for Offline Multi-Objective Optimization
- PrismaCoder: Pushing the Boundaries of Open Multimodal Code Intelligence through Decomposed Rubric Synthesis