AI.info

Latest Research — Page 91

Browse Latest Research on AI.info.

• Improving the Straight-Through Estimator with Zeroth-Order Information
• CovMatch: Cross-Covariance Guided Multimodal Dataset Distillation with Trainable Text Encoder
• Evaluating Long-Horizon Memory for Multi-Party Collaborative Dialogues
• Beyond Patches: Global-aware Autoregressive Model for Multimodal Few-Shot Font Generation
• Towards Efficient Simultaneous Inverse Text Normalization with Pretrained Text-to-Text Language Model and Read-Tag-Write Policy
• Enhancing Meme Emotion Understanding with Multi-Level Modality Enhancement and Dual-Stage Modal Fusion
• Permission Manifests for Web Agents
• About Time: Model-free Reinforcement Learning with Timed Reward Machines
• Towards Test-time Efficient Visual Place Recognition via Asymmetric Query Processing
• Inferring Causal Graph Temporal Logic Formulas to Expedite Reinforcement Learning in Temporally Extended Tasks
• When Can You Prune Your Network? A Study of Intermediate Neurons in Multilingual Speech Parsing
• SpecMRL: Redesign Matryoshka Representation Learning within Parametric Spectrum
• Implicit Bias of Per-sample Adam on Separable Data: Departure from the Full-batch Regime
• LUCA: A Synthetic World for Experimental Reasoning
• Learning Agile Quadrotor Flight in the Real World
• Spiking Heterogeneous Graph Attention Networks
• Stronger Normalization-Free Transformers
• Task Aware Modulation Using Representation Learning for Upsaling of Terrestrial Carbon Fluxes
• Calibration-Free Early Stopping for Chain-of-Thought Reasoning via E-processes
• WarpRec: Unifying Academic Rigor and Industrial Scale for Responsible, Reproducible, and Efficient Recommendation
• Visual Categorization Across Minds and Models: Cognitive Analysis of Human Labeling and Neuro-Symbolic Integration
• Securing Dual-Use Pathogen Data of Concern
• FASA: Frequency-aware Sparse Attention
• On-Policy Distillation Teaches New Skills but Not New Knowledge
• ELBench: A Multi-Dimensional Benchmark for Education-Facing Large Language Models
• CORE: Improving Compositional Reasoning in MLLM Embedding via Reranker Distillation
• DEFT: Disentanglement-Enhanced Fine-Tuning for EEG Foundation Models
• MedGemma vs GPT-4: Open-Source and Proprietary Zero-shot Medical Disease Classification from Images
• A Linguistics-Aware LLM Watermarking via Syntactic Predictability
• RL-AWB: Deep Reinforcement Learning for Auto White Balance Correction in Low-Light Night-time Scenes
• RADRON: Cooperative Localization of Ionizing Radiation Sources by MAVs with Compton Cameras
• EMGauss: Continuous Slice-to-3D Reconstruction via Dynamic Gaussian Modeling in Volume Electron Microscopy
• AfriStereo: A Culturally Grounded Dataset for Evaluating Stereotypical Bias in Large Language Models
• Can Image-To-Video Models Simulate Pedestrian Dynamics?
• Revisiting Replanning from Scratch: Real-Time Incremental Planning with Fast Almost-Surely Asymptotically Optimal Planners
• MoE-SpAc: Efficient MoE Inference Based on Speculative Activation Utility in Heterogeneous Edge Scenarios
• MetaphorStar: Image Metaphor Understanding and Reasoning with End-to-End Visual Reinforcement Learning
• Open-o3-Video-v2: Seek, Ground, and Reason with Verifiable Spatio-Temporal Evidence
• Automatic Paper Reviewing with Heterogeneous Graph Reasoning over LLM-Simulated Reviewer-Author Debates
• A Tool Bottleneck Framework for Clinically-Informed and Interpretable Medical Image Understanding