AI.info
Latest Research — Page 42
Browse Latest Research on AI.info.
- How Identity and Opinion Shape Political Sycophancy in LLMs
- Reason Through the Latent! Making Latent Visual Reasoning Necessary
- Rosetta at AlexandriaX-2026: LoRA-Adapted NileChat for Context-Aware Dialectal Arabic Dialogue Translation
- Multilingual Medical Reasoning for Question Answering with Large Language Models
- Knowledge Pull Requests for Continual Document Authoring
- Hy-Nomas: Towards Free-form Interactive World Generation
- Multimodal Disease Progression Modeling via Spatiotemporal Disentanglement and Multiscale Alignment
- Ovis-Embedding: Pushing the Frontiers of Universal Omni-Modal Embeddings
- Beyond Technological Solutionism: Rethinking XR in Healthcare
- Can LLM Annotators Match Human Consistency? Benchmarking Human Agreement and Optimizing Multi-Agent with Contrastive Knowledge
- VC-Attention: Value Smoothing and Softmax Casting for Low-bit Attention
- wa-hls4ml: A Benchmark and Surrogate Models for hls4ml Resource and Latency Estimation
- StaR-KVQA: Structured Reasoning Traces for Implicit-Knowledge Visual Question Answering
- Calibrating WEAT Against Anisotropy: ZCA Whitening as a Geometric Pre-Processing Step for Embedding Association Tests
- AI-Driven Early Warning Systems for Student Success: Discovering Static Feature Dominance in Temporal Prediction Models
- MOLE: Detecting Insider Threats in AI Agents
- A Benchmark Dataset for Spatially Aligned Road Damage Assessment in Small Uncrewed Aerial Systems Disaster Imagery
- When AI Agents Collude Online: Financial Fraud Risks by Collaborative LLM Agents on Social Platforms
- ExecCritic: Learn to Test, Test to Improve for Coding Agents
- Perturb Your Data: Paraphrase-Guided Training Data Watermarking
- Labels have Human Values: Value Calibration of Subjective Tasks
- DocReward: A Document Reward Model for Structuring and Stylizing
- SwarmEvolve: Latent Agent Swarms for Evolutionary Discovery and Optimization
- Reasoning Core: A Scalable Procedural Data Generation Suite for Symbolic Pre-training and Post-Training
- FastVMT: Eliminating Redundancy in Video Motion Transfer
- MBD-ML: Many-body dispersion from machine learning for molecules and materials
- VEHME: A Vision-Language Model For Evaluating Handwritten Mathematics Expressions
- FronTalk: Benchmarking Front-End Development as Conversational Code Generation with Multi-Modal Feedback
- CrossSWE: Benchmarking Cross-Repository Joint Development for Coding Agents
- Geometry of Reason: Spectral Signatures of Valid Mathematical Reasoning
- From Observations to States: Latent Time Series Forecasting
- Token Sparse Attention: Efficient Long-Context Inference with Interleaved Token Selection
- UFVideo: Towards Unified Fine-Grained Video Cooperative Understanding with Large Language Models
- A Robust Classification Method using Hybrid Word Embedding for Early Diagnosis of Alzheimer's Disease
- Designer-RSI: Evolving Procedural Memory from User Traffic for Agentic Graphic Design
- A comprehensive and trustworthy benchmark of AI methods for change detection in Earth observation
- Interpreting and Controlling Model Behavior via Constitutions for Atomic Concept Edits
- Toward Part-Aware Choral Transcription with singing voice assignment
- Comparing the Performance of LLMs in RAG-based Question-Answering: A Case Study in Computer Science Literature
- ICA: Information-Aware Credit Assignment for Visually Grounded Long-Horizon Information-Seeking Agents