AI.info
Latest Research — Page 131
Browse Latest Research on AI.info.
- I-RAVEN-X: Benchmarking Generalization and Robustness of Analogical and Mathematical Reasoning in Large Language and Reasoning Models
- SKEL-CF: Coarse-to-Fine Biomechanical Skeleton and Surface Mesh Recovery
- Research Design Tracking and Assessment for the Social Sciences
- RF-DETR: Neural Architecture Search for Real-Time Detection Transformers
- Rethinking Progression of Memory State in Robotic Manipulation: An Object-Centric Perspective
- BRIC: Bridging Kinematic Plans and Physical Control at Test Time
- OpenVTON-Bench: A Large-Scale High-Resolution Benchmark for Controllable Virtual Try-On Evaluation
- Action Without Interaction: Probing the Physical Foundations of Video LMMs via Contact-Release Detection
- ModHiFi: Identifying High Fidelity predictive components for Model Modification
- Towards Multiscale Graph-based Protein Learning with Geometric Secondary Structural Motifs
- Formalizing Style in Personal Narratives
- Bridging Online and Offline Handwriting via Differentiable Physical Rendering
- MapRoute++: Surrogate-Guided Semantic Routing for Visual Concept Unlearning
- Social Story Frames: Contextual Reasoning about Narrative Intent and Reception
- The Paradox of Robustness: Decoupling Rule-Based Logic from Affective Noise in High-Stakes Decision-Making
- Augmented Radiance Field: A General Framework for Enhanced Gaussian Splatting
- StreamReady: Learning What to Answer and When in Long Streaming Videos
- ActiveGrasp: Information-Guided Active Grasping with Calibrated Energy-based Model
- EduClaw-Bench: A Long-Horizon Benchmark for Pedagogical LLM Agents with Simulated Learners
- FlexLoRA: Entropy-Guided Flexible Low-Rank Adaptation
- One Token Embedding Is Enough to Deadlock Your Large Reasoning Model
- SparseCoop: Cooperative Perception with Kinematic-Grounded Queries
- Generative Semantic Scene Completion
- Learning Task-Agnostic Representations through Multi-Teacher Distillation
- Toward Human Rights Benchmarking for LLMs: A Pilot Methodology
- MIP Candy: A Modular PyTorch Framework for Medical Image Processing
- Provably Explaining Neural Additive Models
- A Multimodal Dataset of Student Oral Presentations with Sensors and Evaluation Data
- TRACE: Spatiotemporal Contact Memory Graph Network Simulator for Granular Dynamics
- Tensor-DTI: Enhancing Biomolecular Interaction Prediction with Contrastive Embedding Learning
- PILOT-Bench: A Benchmark for Legal Reasoning in the Patent Domain with IRAC-Aligned Classification Tasks
- Language Model Representations for Efficient Few-Shot Tabular Classification
- Gated KalmaNet: A Fading Memory Layer Through Test-Time Ridge Regression
- Fidelity Is Not Enough: Dispatch-Level Instrumentation for Agentic Datasheet Extraction
- Lloyd's $K$-Means Clustering Algorithm Is Frank-Wolfe in Disguise
- scPilot: Large Language Model Reasoning Toward Automated Single-Cell Analysis and Discovery
- Revisiting Logit Distributions for Reliable Out-of-Distribution Detection
- Video Reasoning without Training
- Health-ORSC-Bench: A Benchmark for Measuring Over-Refusal and Safety Completion in Health Context
- Whatever Remains Must Be True: Filtering Drives Reasoning in LLMs, Shaping Diversity