AI.info

Latest Research — Page 14

Browse Latest Research on AI.info.

• Controllable LLM Reasoning via Sparse Autoencoder-Based Steering
• Flow Equivariant World Models: Memory for Partially Observed Dynamic Environments
• Can We Predict Before Executing Machine Learning Agents?
• One Inverse Step is a Convex Program: Bayes-Limit Calibration of Diffusion Inversion
• WebATLAS: An LLM Agent with Experience-Driven Memory and Action Simulation
• BanglaSentNet: An Explainable Hybrid Deep Learning Framework for Multi-Aspect Sentiment Analysis with Cross-Domain Transfer Learning
• MeViS: A Multi-Modal Dataset for Referring Motion Expression Video Segmentation
• Rethinking Multimodal Few-Shot 3D Point Cloud Segmentation: From Fused Refinement to Decoupled Arbitration
• TEXTRIX: Latent Attribute Grid for Native Texture Generation and Beyond
• Hierarchical Prompt Learning for Image- and Text-Based Person Re-Identification
• Constrained Particle Seeking: Solving Diffusion Inverse Problems with Just Forward Passes
• A Contextual Analysis of Driver-Facing and Dual-View Video Inputs for Distraction Detection in Naturalistic Driving Environments
• Conditional Diffusion Model for Multi-Agent Dynamic Task Decomposition
• When Numbers Speak: Aligning Textual Numerals and Visual Instances in Text-to-Video Diffusion Models
• Flow Matching Neural Processes
• TANDEM: Temporal-Aware Neural Detection for Multimodal Hate Speech
• Which Metrics Save the Most Human Annotation? Prediction-Powered Evaluation and Meta-Evaluation
• Self-Training with Dynamic Weighting for Robust Gradual Domain Adaptation
• GAUGE: A Measurement-Grounded Benchmark for Physical Fidelity in Simulation Engines and Video World Models
• DISPO: Enhancing Training Efficiency and Stability in Reinforcement Learning for Large Language Model Mathematical Reasoning
• GDKVM: Echocardiography Video Segmentation via Spatiotemporal Key-Value Memory with Gated Delta Rule
• Scaling Internal-State Policy-Gradient Methods for POMDPs
• POWSM: A Phonetic Open Whisper-Style Speech Foundation Model
• TC-LoRA: Temporally Modulated Conditional LoRA for Adaptive Diffusion Control
• Scaling Web Agent Training through Automatic Data Generation and Fine-grained Evaluation
• Flexing in 73 Languages: A Single Small Model for Multilingual Inflection
• LigBench: A Unified and Human-Aligned Benchmark for LLM-based Research Idea Generation
• In Quest of an Extensible Multi-Level Harm Taxonomy for Adversarial AI: Heart of Security, Ethical Risk Scoring and Resilience Analytics
• DCER: Dual-Stage Compression and Energy-Based Reconstruction
• Auditing Exposure to Harmful Content on TikTok using Multimodal Language Models: A Cross-National, Age-Stratified Study
• Superposition Without Interference? Towards Isolated Interventions via Almost Orthogonal Features in Language Models
• Once Upon an Input: Reasoning via Per-Instance Program Synthesis
• From Static Structures to Ensembles: Studying and Harnessing Protein Structure Tokenization
• Tasks over Application Manuals: Revealing Gaps in Long-Horizon Procedural Reasoning for Language Models
• Co-EPG: A Framework for Co-Evolution of Planning and Grounding in Autonomous GUI Agents
• Robotic Fabric Alignment System for Sewing Using Global Local Weighted ICP
• SM4RT: Learning Structured Motion Geometry for 4D Reconstruction
• Information-Theoretic Discrete Diffusion
• Retrofitting Existing 3D Objects with Surface-Conforming Capacitive Sensing
• Semantically Labelled Automata for Multi-Task Reinforcement Learning with LTL Instructions