AI.info
Latest Research — Page 19
Browse Latest Research on AI.info.
- SRS-Stories: Vocabulary-constrained multilingual story generation for language learning
- Drift-to-Action Controllers: Budgeted Interventions with Online Risk Certificates
- DreamRealm: Exploring and Materializing Hallucination Worlds for Trustworthy Vision-Language Models
- TRACER: A Multimodal Harness for Patient Care in Hospitals
- Which Layer Causes Distribution Deviation? Entropy-Guided Adaptive Pruning for Diffusion and Flow Models
- Laplace Approximation For Tensor Train Kernel Machines In System Identification
- SciPostLayoutTree: A Dataset for Structural Analysis of Scientific Posters
- Narrow Finetuning Leaves Clearly Readable Traces in Activation Differences
- Deeper with Riemannian Geometry: Overcoming Oversmoothing and Oversquashing for Graph Foundation Models
- CodeCompass: Navigating the Navigation Paradox in Agentic Code Intelligence
- GaussianRenderFormer: Transformer-based Rendering of 3D Gaussian Splats
- D-COT: Disciplined Chain-of-Thought Learning for Efficient Reasoning in Small Language Models
- Stratified Sparse Attention: Reducing the Sparse-to-Dense Gap at Extreme Sparsity
- DoSA: Dots Sparse Attention
- A Three-Layer Caching Architecture for Low-Latency LLM Web Search on Commodity CPU Hardware
- Tracing Mathematical Proficiency Through Problem-Solving Processes
- Benchmarking BERT-based Models for Sentence-level Topic Classification in Nepali Language
- The Beginning of ChatGPT Ads
- RepV: Safety-Separable Latent Spaces for Scalable Neurosymbolic Plan Verification
- SketchDirector: Complex Scene Sketching via Agentic Layout Reasoning and Detail Refinement
- H3DNAS: Hardware-Aware ONNX-Native 3D Point Cloud Model Compression
- Auxiliary Gene Learning: Spatial Gene Expression Estimation by Auxiliary Gene Selection
- CogniMap3D: Cognitive 3D Mapping and Rapid Retrieval
- Mitigating Intra- and Inter-modal Forgetting in Continual Learning of Unified Multimodal Models
- AIMO Interpretability Challenge
- WikiSkill: Compiling Agent Experience into Persistent Knowledge for Skill Evolution
- Innovative Design of Multi-functional Supernumerary Robotic Limbs with Ellipsoid Workspace Optimization
- QUAL: Quantile Alignment Improves Zero-Shot Time-Series Foundation Models
- DICE: Structured Reasoning in LLMs through SLM-Guided Chain-of-Thought Correction
- Judging in Latent Space: Efficient Generative Reward Modeling via Semantics-Preserving Compression
- WearableQA: A Benchmark for Health Reasoning over Real-World Wearable Data
- FENCE: A Financial and Multimodal Jailbreak Detection Dataset
- NeSyPr: Neurosymbolic Proceduralization For Efficient Embodied Reasoning
- T1: Terminal Agent Reinforcement Learning for Long-Horizon Tasks
- Selective Learning for Deep Time Series Forecasting
- TIDES: Implicit Time-Awareness in Selective State Space Models
- OmniCam: Omni-Camera Trajectory Generation via Geometry-Grounded Pose Token Learning
- Format Matters: The Robustness of Multimodal LLMs in Reviewing Evidence from Tables and Charts
- Free-Grained Hierarchical Visual Recognition
- Deep Academic Survey: Stateful Agentic Closed-Loop Paradigm for Academic Survey Automation