AI.info
Latest Research — Page 53
Browse Latest Research on AI.info.
- Why Is Video Still So Expensive? A Survey of Inference-Efficiency Mechanisms in Video and Audiovisual LLMs
- Decision-Focused Learning in MDPs: An Occupancy Measure Approach
- Insight Miner: A Time Series Analysis Dataset for Cross-Domain Alignment with Natural Language
- Affordance-Guided Coarse-to-Fine Exploration for Base Placement in Open-Vocabulary Mobile Manipulation
- QuEPT: Quantized Elastic Precision Transformers with One-Shot Calibration for Multi-Bit Switching
- IB-GAN: Disentangled Representation Learning with Information Bottleneck Generative Adversarial Networks
- EDiS: Edge Disjoint Subgraph Sparsification Framework for Graph Neural Networks
- Don't Look Back in Anger: MAGIC Net for Streaming Continual Learning with Temporal Dependence
- How to Marginalize in Causal Structure Learning?
- VCode: a Multimodal Coding Benchmark with SVG as Symbolic Visual Representation
- Context-Nav: Context-Driven Exploration and Viewpoint-Aware 3D Spatial Reasoning for Instance Navigation
- Dual-objective Language Models: Training Efficiency Without Overfitting
- MixFlow Training: Alleviating Exposure Bias with Slowed Interpolation Mixture
- Markovian Scale Prediction: A New Era of Visual Autoregressive Generation
- Staged Continual Adaptation of Multimodal Foundation Models for Japanese Financial Documents
- Mitigating Structural Overfitting: A Distribution-Aware Rectification Framework for Missing Feature Imputation
- Learning with less: label-efficient land cover classification at very high spatial resolution using self-supervised deep learning
- Continual Adaptation for Pacific Indigenous Speech Recognition
- Dexbotic: Open-Source Vision-Language-Action Toolbox
- Unified Spherical Frontend: Learning Rotation-Equivariant Representations of Spherical Images from Any Camera
- UltraShape 1.0: High-Fidelity 3D Shape Generation via Scalable Geometric Refinement
- CCQ: A Multi-State Child Care Quality Dataset to Support AI for Children's Health Research
- SLICEChat: Progressive In-Encoder Token Pruning for Whole-Slide Pathology Language Models
- CultureConverse: A Multilingual Multi-turn Simulation Harness for Culturally Grounded Assistance in East and Southeast Asia
- PyroAdapt: Adapting Wildfire Prediction under Spatial Heterogeneity and Temporal Shift
- NutriOrion: A Hierarchical Multi-Agent Framework for Personalized Nutrition Intervention Grounded in Clinical Guidelines
- What LLM Trading Agents Actually Do in Production: A Six-Month, Population-Scale Record from Two Fleets
- Thinking Longer, Not Always Smarter: Evaluating LLM Capabilities in Hierarchical Legal Reasoning
- BiKC+: Bimanual Hierarchical Imitation with Keypose-Conditioned Coordination-Aware Consistency Policies
- ControlScope: Workflow Revision and Reliability in LLM Agents
- HSPR: Recovering Software-Agent Benchmark Scores via Hierarchical Posterior Inference
- FlashVID: Efficient Video Large Language Models via Training-free Tree-based Spatiotemporal Token Merging
- WinARDet: Compressed Window Auto-Regression for Long-Horizon Vision-Language Grounding
- When Does Predictor-Based RL Align with Human Perception? A Study of Subjective Rewards in Codec-Based Speech Language Models
- Fast Converging 3D Gaussian Splatting for 1-Minute Reconstruction
- Cornserve: A Distributed Serving System for Any-to-Any Multimodal Models
- BanglaRhet: Benchmarking Classical and Transformer Models for Rhetorical and Persuasion Detection in Bangla Political Speech
- Active Slice Discovery in Large Language Models
- Robust Detection of Directional Adversarial Attacks in Deep Neural Networks for Radiological Imaging
- A Scaled-Up Empirical Study of Syntactic Language Models