AI.info
Latest Research — Page 34
Browse Latest Research on AI.info.
- SpecPilot: Autonomous Algorithm Discovery and Systems Optimization for Speculative Decoding
- Learning Structure-Semantic Evolution Trajectories for Graph Domain Adaptation
- CD-DPE: Dual-Prompt Expert Network Based on Convolutional Dictionary Feature Decoupling for Multi-Contrast MRI Super-Resolution
- Cook and Clean Together: Teaching Embodied Agents for Parallel Task Execution
- Judged Useless, Queried Anyway: Tool-Using Agents Rarely Turn Their Own Evidence Judgments into Stopping Decisions
- Decoupled Predictive Decision Making: A Shared Conditional Predictor for Agents
- Provable FDR Control for Deep Feature Selection: Deep MLPs and Beyond
- Predicting Unseen Scientific Interactions: Conditional Flow Models Hallucinate Non-Additive Effects
- CARDEA: Auditable Reasoning Grounded in Spatial Evidence for End-to-End Coronary Angiography Interpretation
- RPC-Bench: A Fine-grained Benchmark for Research Paper Comprehension
- A Unified Shape-Aware Foundation Model for Time Series Classification
- Online Dense Reinforcement Learning with Planning-Grounding Agent for UI Navigation on Live IOS Apps
- The Illusion of Generalization in Tabular Language Models
- ABot-N0: Technical Report on the VLA Foundation Model for Versatile Embodied Navigation
- Text-Assisted Event Stream Visual Place Recognition via Multi-Scale Spatiotemporal Optimal Transport
- VideoARM: Agentic Reasoning over Hierarchical Memory for Long-Form Video Understanding
- AutoSAGE: Input-Aware CUDA Scheduling for Sparse GNN Aggregation (SpMM/SDDMM) and CSR Attention
- LoRA-DA: Data-Aware Initialization for Low-Rank Adaptation via Asymptotic Analysis
- TowerVision: Understanding and Improving Multilinguality in Vision-Language Models
- Towards Long-window Anchoring in Vision-Language Model Distillation
- ML-EcoLyzer: Quantifying the Environmental Cost of Machine Learning Inference Across Frameworks and Hardware
- GRACE: A Unified 2D Multi-Robot Path Planning Simulator & Benchmark for Grid, Roadmap, And Continuous Environments
- Thompson Sampling via Fine-Tuning of LLMs
- ChronusOmni: Improving Time Awareness of Omni Large Language Models
- Kierston & KierstonBench: Simulation of Allentown, PA and Evaluation of Language Models in Crime Investigation and Surveillance Tasks
- R2M-Bench: Evaluating Revisit Memory via Relative Consistency in Interactive Video World Models
- HumanCrafter: Synergizing Generalizable Human Reconstruction and Semantic 3D Segmentation
- Token Taxes: mitigating AGI's economic risks
- SSTODE: Ocean-Atmosphere Physics-Informed Neural ODEs for Sea Surface Temperature Prediction
- HGMEM: Hypergraph-based Working Memory to Improve Multi-step RAG for Long-Context Complex Relational Modeling
- Self-Evolving Agent Harness
- ConceptScope: Characterizing Dataset Bias via Disentangled Visual Concepts
- Routing Should Pay for Itself: Sparse Supervision for Economical LLM Routing
- Cross-Centaur: Modeling Individual Decision-Making Across Psychological Tasks with Language Models
- World Action Models are Zero-shot Policies
- QuantCode Model: Specializing Language Models for Executable Algorithmic Trading Code
- Semi-Supervised High Dynamic Range Image Reconstructing via Bi-Level Uncertain Area Masking
- CoVeR: Coverage-Based Token Pruning for Multi-View 3D Reasoning in VLMs
- Stroke3D: Lifting 2D strokes into rigged 3D model via latent diffusion models
- Learning Where Outcomes Change:Credit-Addressable Reasoning for Multimodal Geometry