AI.info
Latest Research — Page 68
Browse Latest Research on AI.info.
- Causal Bayesian Optimization: Foundations, Methods, and Applications
- Probabilistic Hash Embeddings for Online Learning of Categorical Features
- Menta: A Small Language Model for On-Device Mental Health Prediction
- ScaleDiff: Higher-Resolution Image Synthesis via Efficient and Model-Agnostic Diffusion
- REALM: A Real-to-Sim Validated Benchmark for Generalization in Robotic Manipulation
- Rectifying Shortcut Behaviors in Preference-based Reward Learning
- When Guardrails Look Effective: Construct Validity Failures in LLM Agent Commerce Evaluation
- A Stratified Multi-Rater Evaluation of LLM-Based Virtual Standardized Patients with a Deployed Data-Generation Platform
- Benchmarking Scientific Understanding and Reasoning for Video Generation using VideoScience-Bench
- User-Centric Object Navigation: A Benchmark with Integrated User Habits for Personalized Embodied Object Search
- Lower Complexity Bounds for Nonconvex-Strongly-Convex Bilevel Optimization with First-Order Oracles
- Entropic Confinement and Mode Connectivity in Overparameterized Neural Networks
- A Systematic Study of In-the-Wild Model Merging for Large Language Models
- AICD Bench: A Challenging Benchmark for AI-Generated Code Detection
- The Confidence Trap: Gender Bias and Predictive Certainty in LLMs
- VLSplat: Vision-Language Guided Object-Centric 3D Gaussian Splatting via Scene Graph
- How Many Experts Are Enough? Towards Optimal Semantic Specialization for Mixture-of-Experts
- Multi-Scale Protein Structure Modelling with Geometric Graph U-Nets
- A Mean-Field Framework for Inference-Time Distributional Control of Diffusion Models
- PAND: Prompt-Aware Neighborhood Distillation for Lightweight Fine-Grained Visual Classification
- Importance-Aware Data Selection for Efficient LLM Instruction Tuning
- ReFlowSET: Representation-Aligned Latent Flow Matching for SAR-to-EO Image Translation
- Diverse Preference Learning for Capabilities and Alignment
- Cite or Decline: A Strict Course-Grounded Chatbot for STEM Lecture Videos
- MEC$^3$O: Multi-Expert Consensus for Code Time Complexity Prediction
- Continuous SUN (Stable, Unique, and Novel) Metric for Generative Modeling of Inorganic Crystals
- StreamingVLM: Real-Time Understanding for Infinite Video Streams
- Feature-aware Modulation for Learning from Temporal Tabular Data
- Quality Diversity for Reliable Data Driven Time-Use Optimization
- Quant VideoGen: Auto-Regressive Long Video Generation via 2-Bit KV-Cache Quantization
- Diagnosing the Reference Gap: What Visual Scaffolds Can and Cannot Fix in Multimodal Reasoning
- CFM: Language-aligned Concept Foundation Model for Vision
- Aggregating Diverse Cue Experts for AI-Generated Image Detection
- Agent World Model: Infinity Synthetic Environments for Agentic Reinforcement Learning
- When More Metadata Misleads: Probing Field-Level Grounding in LLM-Generated Museum Descriptions
- FoundationalASSIST: An Educational Dataset for Foundational Knowledge Tracing and Pedagogical Grounding of LLMs
- Principle-Evolvable Scientific Discovery via Uncertainty Minimization
- ReplicatorBench: Benchmarking LLM Agents for Replicability in Social and Behavioral Sciences
- Uncertain Knowledge Graph Completion via Semi-Supervised Confidence Distribution Learning
- Toward More Reliable Artificial Intelligence: Reducing Hallucinations in Vision-Language Models