AI.info
Latest Research — Page 86
Browse Latest Research on AI.info.
- Dual Randomized Smoothing: Beyond Global Noise Variance
- NOVA: Next-step Open-Vocabulary Autoregression for 3D Multi-Object Tracking in Autonomous Driving
- DigiData: Training and Evaluating General-Purpose Mobile Control Agents
- PoKER: A Probability of Kill Estimation Rate Model for Air-to-Air Missiles Using Machine Learning on Stochastic Targets
- Understanding Counting Mechanisms in Large Language and Vision-Language Models
- Atlas: Orchestrating Heterogeneous Models and Tools for Multi-Domain Complex Reasoning
- Cost-Minimized Label-Flipping Poisoning Attack to LLM Alignment
- Root-Cause Attribution Is a Search Problem: Continual Search for Long-Horizon Agent Failures
- The devil is in the details: Enhancing Video Virtual Try-On via Keyframe-Driven Details Injection
- REFRAMED: Towards Realistic Audio Description Generation for Movies
- CoworkOS:Scaling Agent Coworkers for Real-world Automation
- Recovering Reliable Supervision via Critique-Guided On-Policy Distillation
- LORE: Jointly Learning the Intrinsic Dimensionality and Relative Similarity Structure From Ordinal Data
- Modeling Endogenous Logic: Causal Neuro-Symbolic Reasoning Model for Explainable Multi-Behavior Recommendation
- I Have a Stream: Making Self-Supervised Learning Work on Continuous Video
- Lesion-Aware Post-Training of Latent Diffusion Models for Synthesizing Diffusion MRI from CT Perfusion
- Conditional Clifford-Steerable CNNs for PDE Modeling
- SPA-Cache: Singular Proxies for Adaptive Caching in Diffusion Language Models
- Learn-to-Distance: Distance Learning for Detecting LLM-Generated Text
- Human-AI Collaboration Mechanism Study on AIGC Assisted Image Production for Special Coverage
- FlyPrompt: Brain-Inspired Random-Expanded Routing with Temporal-Ensemble Experts for General Continual Learning
- AdaReasoner: Dynamic Tool Orchestration for Iterative Visual Reasoning
- On-Policy or Off-Policy Learning? A Systematic Study of Distillation Dynamics
- Learning Sewing Patterns via Latent Flow Matching of Implicit Fields
- A Survey of Flow Matching in Reinforcement Learning
- DropKV: Decoupling Residual-Output Perturbation for Near-Optimal KV-Cache Eviction
- Beyond Benchmark Accuracy: A Diagnostic Test for LLM Chemical Prediction
- Exploring Conditions for Diffusion models in Robotic Control
- Let the Experts Speak: Improving Survival Prediction & Calibration via Mixture-of-Experts Heads
- DuFal: Dual-Frequency-Aware Learning for High-Fidelity Extremely Sparse-view CBCT Reconstruction
- Efficient Tool-Calling Multi-Expert NPC Agent for Commonsense Persona-Grounded Dialogue
- Towards Robust and Fair Next Visit Diagnosis Prediction under Noisy Clinical Notes with Large Language Models
- LEGO: A Lifting-Free Approach for Exocentric-to-Egocentric Video Generation
- A note on the area under the likelihood and the fake evidence for model selection
- TOMCAT: Test-time Comprehensive Knowledge Accumulation for Compositional Zero-Shot Learning
- Walk the Lines 2: Contour Tracking for Detailed Segmentation
- Tabular Foundation Models are Strong Graph Anomaly Detectors
- Beyond Unit-Circle Eigenvalues: Invariant Bases for Stable State Space Dynamics
- Changes in Real Time: Online Scene Change Detection with Multi-View Fusion
- Probing Scientific General Intelligence of LLMs with Scientist-Aligned Workflows