AI.info
Latest Research — Page 84
Browse Latest Research on AI.info.
- Generator-based Graph Generation via Heat Diffusion
- Towards Scalable Pre-training of Visual Tokenizers for Generation
- DiCaP: Distribution-Calibrated Pseudo-labeling for Semi-Supervised Multi-Label Learning
- RADAR: Accelerate Large Language Model Inference With RL-Based Dynamic Draft Trees
- Building and Evaluating Fixed-Voice Thai TTS from Synthetic Speech
- Counterfactual Explainable AI (XAI) Method for Deep Learning-Based Multivariate Time Series Classification
- TurboBoA: Faster and Exact Attention-aware Quantization without Backpropagation
- Look Before You Leap: Thermodynamic Arbitration of Parametric and Non-Parametric Knowledge in LLM Agents via Self-Regulating Memory Architectures
- A Decade in a Day: Synthesizing Agent-Native Interfaces from Human-Oriented Software Evolution
- Sliding-window beats linear attention
- Flexible Intensities Matter: A Comprehensive Re-evaluation of Hawkes Processes and Neural Temporal Point Processes
- RxnBench: A Multimodal Benchmark for Evaluating Large Language Models on Chemical Reaction Understanding from Scientific Literature
- Ctrl&Shift: High-Quality Geometry-Aware Object Manipulation in Visual Generation
- LuMon: A Comprehensive Benchmark and Development Suite with Novel Datasets for Lunar Monocular Depth Estimation
- CaRGo-T: Causal Reasoning Graph-of-Thought improves Multimodal Humor Comprehension
- NOWJ @BioCreative IX ToxHabits: An Ensemble Deep Learning Approach for Detecting Substance Use and Contextual Information in Clinical Texts
- Salt++: Context-Aligned Post-Training for Few-Step Streaming Multimodal Generation
- SiameseNorm: Breaking the Barrier to Reconciling Pre/Post-Norm
- M3-AD: Reflection-aware Multi-modal, Multi-category, and Multi-dimensional Benchmark and Framework for Industrial Anomaly Detection
- Who May Release an Agent's Promise? Standing over Commitments in Multi-Party Chat
- Improving Language Identification for Code-Switched Utterances with Integer Linear Programming
- Can Reasoning Path still be Effective as Input? Bridging Post-Reasoning to Chain-of-Thought Compression
- LiteGE: Lightweight Geodesic Embedding for Efficient Geodesics Computation and Non-Isometric Shape Correspondence
- Addressing Overthinking in Large Vision-Language Models via Gated Perception-Reasoning Optimization
- Physics-Informed Neural Koopman Machine for Interpretable Longitudinal Personalized Alzheimer's Disease Forecasting
- Instruction Tuning of Large Language Models for Tabular Data Generation-in One Day
- VC4VG: Optimizing Video Captions for Text-to-Video Generation
- AlphaOPT: Formulating Optimization Programs with Self-Improving LLM Experience Library
- TrajDiff: End-to-end Autonomous Driving without Perception Annotation
- Constructive Distortion: Improving MLLMs with Attention-Guided Image Warping
- UniComp: A Unified Evaluation of Large Language Model Compression via Pruning, Quantization, and Distillation
- Learning Physics-Grounded 4D Dynamics with Neural Gaussian Force Fields
- Organ-Aware Attention Improves CT Triage and Classification
- Angular Gradient Sign Method: Uncovering Vulnerabilities in Hyperbolic Networks
- Rare Event Early Detection: A Dataset of Sepsis Onset for Critically Ill Trauma Patients
- From Attribution to Action: Jointly ALIGNing Predictions and Explanations
- ZeroS: Zero-Sum Linear Attention for Efficient Transformers
- Attention Retention for Continual Learning with Vision Transformers
- SurvHTE-Bench: A Benchmark for Heterogeneous Treatment Effect Estimation in Survival Analysis
- Sources of Truth: A Multi-Platform, Multilingual Audit of Citations in AI Mental Health Information Queries