AI.info
Latest Research — Page 105
Browse Latest Research on AI.info.
- What Does It Take to Build a Performant Selective Classifier?
- Thinking Ahead: Foresight Intelligence in MLLMs and World Model
- Learning Compact Latent Space for Representing Neural Signed Distance Functions with High-fidelity Geometry Details
- Style or Signature? Artist-Disjoint Evaluation of Style Classification in Frozen Vision Embeddings
- Partial Ring Scan: Revisiting Scan Order in Vision State Space Models
- FineVAU: A Novel Human-Aligned Benchmark for Fine-Grained Video Anomaly Understanding
- LLM Agents Implement an NLG System from Scratch: Building Interpretable Rule-Based RDF-to-Text Generators
- Beyond Scattered Acceptance: Fast and Coherent Inference for DLMs via Longest Stable Prefixes
- TSBOW -- Traffic Surveillance Benchmark for Occluded Vehicles Under Various Weather Conditions
- Jailbreak-Zero: A Path to Pareto Optimal Red Teaming for Large Language Models
- Stick to What You Know: A Study of Knowledge-Aligned Supervised Fine-Tuning
- InnoGym: Benchmarking the Innovation Potential of AI Agents
- $\mathcal{V}isi\mathcal{P}runer$: Decoding Discontinuous Cross-Modal Dynamics for Efficient Multimodal LLMs
- EAGLE: Episodic Appearance- and Geometry-aware Memory for Unified 2D-3D Visual Query Localization in Egocentric Vision
- SaFiRe: Saccade-Fixation Reiteration with Mamba for Referring Image Segmentation
- ToolLoop: Closed-Loop Tool-Use Data Synthesis via Decomposed Generation and Dynamic Self-Feedback
- Accelerating Storage-Based Training for Graph Neural Networks
- Retrieving Objects from 3D Scenes with Box-Guided Open-Vocabulary Instance Segmentation
- Leveraging Multispectral Sensors for Color Correction in Mobile Cameras
- Visually-Guided Policy Optimization for Multimodal Reasoning
- GimbalDiffusion: Gravity-Aware Camera Control for Video Generation
- Live or Lie: Action-Aware Capsule Multiple Instance Learning for Risk Assessment in Live Streaming Platforms
- Candidate Attended Dialogue State Tracking Using BERT
- ComponentBench: Diagnosing Component-Level Failures in Computer-Use Agents
- Dataset Distillation for Pre-Trained Self-Supervised Vision Models
- DynaAct: Large Language Model Reasoning with Dynamic Action Spaces
- Gaussian See, Gaussian Do: Semantic 3D Motion Transfer from Multiview Video
- From Passive Perception to Active Memory: A Weakly Supervised Image Manipulation Localization Framework Driven by Coarse-Grained Annotations
- Guide-Guard: Off-Target Predicting in CRISPR Applications
- PRESTO: Preimage-Informed Instruction Optimization for Prompting Black-Box LLMs
- MAS-Orchestra: Understanding and Improving Multi-Agent Reasoning Through Holistic Orchestration and Controlled Benchmarks
- Memora: A Harmonic Memory Representation Balancing Abstraction and Specificity
- Beyond the Individual: Virtualizing Multi-Disciplinary Reasoning for Clinical Intake via Collaborative Agents
- Speculative Coupled Decoding for Training-Free Lossless Acceleration of Autoregressive Visual Generation
- ClaimReceipt: Verifying Evidence Sufficiency and Coverage in Agent Evaluations
- Machine Learning Algorithms in Statistical Modelling Bridging Theory and Application
- Isaac Lab: A GPU-Accelerated Simulation Framework for Multi-Modal Robot Learning
- Balanced Anomaly-guided Ego-graph Diffusion Model for Inductive Graph Anomaly Detection
- MDReID: Modality-Decoupled Learning for Any-to-Any Multi-Modal Object Re-Identification
- AlignTree: Efficient Defense Against LLM Jailbreak Attacks