AI.info
Latest Research — Page 61
Browse Latest Research on AI.info.
- Provably Learning Attention with Queries
- CompoSET: A Controlled Single-Edit Benchmark for Vision-Language Compositionality
- MARC: Memory-Augmented RL Token Compression for Efficient Video Understanding
- Dating the Model: Hidden Dates in System Prompts Affect LLM Evaluation
- BEVDilation: LiDAR-Centric Multi-Modal Fusion for 3D Object Detection
- ASCIIBench: Evaluating Language-Model-Based Understanding of Visually-Oriented Text
- Capable yet Parsimonious: Extracting and Characterizing Hidden Chain-of-Thought in Frontier Models
- ObjEmbed: Towards Universal Multimodal Object Embeddings
- Reasoning With a Star: A Heliophysics Dataset and Benchmark for Agentic Scientific Reasoning
- COMBOOD: A Semiparametric Approach for Detecting Out-of-distribution Data for Image Classification
- Evaluating Inquiry Learning in LLM-Based Agents: Hypothesizing, Reasoning, and Exploration
- Single-step Diffusion-based Video Coding with Semantic-Temporal Guidance
- OpenSec: Measuring Incident Response Agent Calibration Under Adversarial Evidence
- Distill3R: A Pipeline for Democratizing 3D Foundation Models on Commodity Hardware
- Benchmark Success, Clinical Failure: When Reinforcement Learning Optimizes for Benchmarks, Not Patients
- VL-DocIR: A Benchmark for Vision-Based Long Document Information Retrieval
- T2SMark: Balancing Robustness and Diversity in Noise-as-Watermark for Diffusion Models
- Nemotron-Labs-Diffusion-Uni: Elastic Self-Refining Unified Diffusion LLM with Cross-Paradigm On-Policy Distillation
- Inference-Time Diversity in RL-Trained Lean Theorem Provers: A Diagnostic Study
- Kandinsky 5.0: A Family of Foundation Models for Image and Video Generation
- QuranicMMLU: A Cognitively-Aware Benchmark for Evaluating Generative AI Solutions on Quranic Linguistic Knowledge
- Causal Interpretation of Neural Network Computations with Contribution Decomposition
- Audio-Visual Camera Pose Estimation with Passive Scene Sounds and In-the-Wild Video
- DramaChain Bench: An End-to-End Benchmark for Short-Drama Generation
- Timepoint-Specific Benchmarking of Deep Learning Models for Glioblastoma Follow-Up MRI
- Quantigence: A Multi-Agent Framework for Post-Quantum Security Analysis on Commodity Hardware
- Digital Medicines Information at National Scale: Search Behaviour and System Performance of MediVerify Across 1.5 Million Queries
- TAPVid-360: Tracking Any Point in 360 from Narrow Field of View Video
- CulturalRiddles: A Multicultural Benchmark of Riddles
- U-Cast: A Surprisingly Simple and Efficient Frontier Probabilistic AI Weather Forecaster
- Specificity-aware reinforcement learning for fine-grained open-world classification
- Dual-Stream Spectral Decoupling Distillation for Remote Sensing Object Detection
- FlexRouter: Learning Complementary Model Sets for Flexible LLM Routing
- Increasing LLM Coding Capabilities through Diverse Synthetic Coding Tasks
- SparseWorld: A Flexible, Adaptive, and Efficient 4D Occupancy World Model Powered by Sparse and Dynamic Queries
- Monitor Accuracy Isn't the Answer: A Decision-Value Framework for Evaluating AI Agent Restart Monitors
- On the Optimality of Kinship Naming: an Information-theoretic Approach
- A Benchmark for Spatially Grounded Gesture Generation
- Beyond Cosine Similarity: Magnitude-Aware CLIP for No-Reference Image Quality Assessment
- Factorized Gradients for Scalable Highly-expressive Parametric Diffeomorphisms