AI.info
Latest Research — Page 93
Browse Latest Research on AI.info.
- CGBench: Benchmarking Language Model Scientific Reasoning for Clinical Genetics Research
- Approximate Domain Unlearning for Vision-Language Models
- ReCite: Agentic Reasoning for Faithful Citation
- Test-Time Adaptive Object Detection with Foundation Model
- From Benchmarks to Business Impact: Deploying IBM Generalist Agent in Enterprise Production
- Learning Adaptive Distribution Alignment with Neural Characteristic Function for Graph Domain Adaptation
- SIRF: A Spec-Internalized Risk Foundation Model for Industrial Content Risk Control
- Leveraging Human Reading Behavior for Keyphrase Extraction: A Webcam-based Eye-tracking Corpus
- Scalable, Explainable and Provably Robust Anomaly Detection with One-Step Flow Matching
- From Fair Representation to Just Recognition in Generative AI
- Language-Informed Flow Matching for Trend-Guided Structure-Based 3D Molecular Generation
- VIRO: Robust and Efficient Neuro-Symbolic Reasoning with Verification for Referring Expression Comprehension
- PROFASR-BENCH: A Benchmark for Context-Conditioned ASR in High-Stakes Professional Speech
- Residual Decoding: Mitigating Hallucinations in Large Vision-Language Models via History-Aware Residual Guidance
- Rethinking Garment Conditioning in Diffusion-based Virtual Try-On: Decouple, Don't Denoise
- Exploring the Interplay Between Voice, Personality, and Gender in Human-Agent Interactions
- CARDIUM: Congenital Anomaly Recognition with Diagnostic Images and Unified Medical records
- Map-Det3D: Metric Feed-Forward 3D Reconstruction Prior for Multi-view 3D Object Detection from Streaming Inputs
- UniRec-0.1B: Unified Text and Formula Recognition with 0.1B Parameters
- Stable On-Policy Distillation through Adaptive Target Reformulation
- Adapting Neural Audio Codecs to EEG
- CARDIAG: A Dense Segment Classification Benchmark of Deep Learning Architectures for Coronary Angiography
- Detecting Data Contamination from Reinforcement Learning Post-training for Large Language Models
- Counterfactual-based Agent Influence Ranker for Agentic AI Workflows
- EchoTrail-GUI: Building Actionable Memory for GUI Agents via Critic-Guided Self-Exploration
- SocioVerse2: A Longitudinal Dynamic Social Simulation Framework under a Human-AI Co-evolutionary Paradigm
- Look-Ahead Reasoning on Learning Platforms
- HypoEvolve: Genetic Algorithms Enable Multi-Agent LLMs to Discover Scientific Hypotheses
- O3N: Omnidirectional Open-Vocabulary Occupancy Prediction
- A superpersuasive autonomous policy debating system
- DuoMo: Dual Motion Diffusion for World-Space Human Reconstruction
- Causally-Grounded Dual-Path Attention Intervention for Object Hallucination Mitigation in LVLMs
- TPV: Parameter Perturbations Through the Lens of Test Prediction Variance
- SoFlow: Solution Flow Models for One-Step Generative Modeling
- Measuring Agents in Production
- Gimballed Rotor Mechanism for Omnidirectional Quadrotors
- Long-Tailed Recognition via Information-Preservable Two-Stage Learning
- SHAP Meets Tensor Networks: Provably Tractable Explanations with Parallelism
- HccePose(BF): Predicting Front & Back Surfaces to Construct Ultra-Dense 2D-3D Correspondences for Pose Estimation
- Chain-of-Goals Hierarchical Policy for Long-Horizon Offline Goal-Conditioned RL