AI.info
Latest Research — Page 66
Browse Latest Research on AI.info.
- DuGI-MAE: Improving Infrared Mask Autoencoders via Dual-Domain Guidance
- Typhoon-S: Minimal Open Post-Training for Sovereign Large Language Models
- ReaSon: Reinforced Causal Search with Information Bottleneck for Video Understanding
- Qwen3-ASR Technical Report
- DCcluster-Opt: Benchmarking Dynamic Multi-Objective Optimization for Geo-Distributed Data Center Workloads
- Hierarchical Deep Research with Local-Web RAG: Toward Automated System-Level Materials Discovery
- Exploropleth: exploratory analysis of data binning methods in choropleth maps
- Reconstruction-Anchored Diffusion Model for Text-to-Motion Generation
- SMART: Scalable Mesh-free Aerodynamic Simulations from Raw Geometries using a Transformer-based Surrogate Model
- MechDetect: Detecting Data-Dependent Errors
- JustDepth: Real-Time Radar-Camera Depth Estimation with Single-Scan LiDAR Supervision
- Odin: Oriented Dual-module Integration for Text-rich Network Representation Learning
- Latent Chain-of-Thought World Modeling for End-to-End Driving
- AMemGym: Interactive Memory Benchmarking for Assistants in Long-Horizon Conversations
- Hamilton-Jacobi Reachability for Hybrid Systems: Unified Goal-Driven Control with Safety Guarantees
- Taming the Real-world Complexities in CPT E/M Coding with Large Language Models
- FlatLand: Personalized Graph Federated Learning via Tailored Lorentz Space
- On the Identifiability of Tensor Ranks via Prior Predictive Matching
- Order from Chaos: Physical World Understanding from Glitchy Gameplay Videos
- Learning Time in Static Classifiers
- ProBench: Benchmarking GUI Agents with Accurate Process Information
- Kinematic Kitbashing
- Continual Action Quality Assessment via Adaptive Manifold-Aligned Graph Regularization
- Rethinking Camera Choice: An Empirical Study on Fisheye Camera Properties in Robotic Manipulation
- EU-Agent-Bench: Measuring Illegal Behavior of LLM Agents Under EU Law
- Teacher Demonstrations in a BabyLM's Zone of Proximal Development for Contingent Multi-Turn Interaction
- OBCache: Optimal Brain KV Cache Pruning for Efficient Long-Context LLM Inference
- Guaranteed Optimal Compositional Explanations for Neurons
- WHOLE: World-Grounded Hand-Object Lifted from Egocentric Videos
- High-Order Markov Blanket Discovery via a k-Order Relaxation of the Faithfulness Assumption
- Flux4D: Flow-based Unsupervised 4D Reconstruction
- H-SPLID: HSIC-based Saliency Preserving Latent Information Decomposition
- Benchmarking is Broken -- Don't Let AI be its Own Judge
- Spatial Preference Rewarding for MLLMs Spatial Understanding
- Tighter CMI-Based Generalization Bounds via Stochastic Projection and Quantization
- GeoGen: A Two-stage Coarse-to-Fine Framework for Fine-grained Synthetic Location-based Social Network Trajectory Generation
- OpenVE-3M: A Large-Scale High-Quality Dataset for Instruction-Guided Video Editing
- One Diffusion Model, Two Roles: Guided Trajectory Planning and Safety-Critical Scenario Generation in Closed-Loop Simulation
- Recurrent Attention-based Token Selection for Efficient Streaming Video-LLMs
- Evaluating the Ability of Explanations to Disambiguate Models in a Rashomon Set