Mini toolsPapers
Filter by company
-
Fusian: Multi-LoRA Fusion for Fine-Grained Continuous MBTI Personality Control in Large Language Models
-
TrinityGuard: A Unified Framework for Safeguarding Multi-Agent Systems
-
SEA-Vision: A Multilingual Benchmark for Comprehensive Document and Scene Text Understanding in Southeast Asia
-
A Hybrid Modeling Framework for Crop Prediction Tasks via Dynamic Parameter Calibration and Multi-Task Learning
-
Local Urysohn Width: A Topological Complexity Measure for Classification
-
RESQ: A Unified Framework for REliability- and Security Enhancement of Quantized Deep Neural Networks
-
GDPO-SR: Group Direct Preference Optimization for One-Step Generative Image Super-Resolution
-
AnyCrowd: Instance-Isolated Identity-Pose Binding for Arbitrary Multi-Character Animation
-
Amplification Effects in Test-Time Reinforcement Learning: Safety and Reasoning Vulnerabilities
-
MA-VLCM: A Vision Language Critic Model for Value Estimation of Policies in Multi-Agent Team Settings
-
CLAG: Adaptive Memory Organization via Agent-Driven Clustering for Small Language Model Agents
-
Invisible failures in human-AI interactions
-
Physics-informed fine-tuning of foundation models for partial differential equations
-
Gym-V: A Unified Vision Environment System for Agentic Vision Research
-
Real-Time Human Frontal View Synthesis from a Single Image
-
Listening to the Echo: User-Reaction Aware Policy Optimization via Scalar-Verbal Hybrid Reinforcement Learning
-
MV2UV: Generating High-quality UV Texture Maps with Multiview Prompts
-
Deep Reinforcement Learning for Fano Hypersurfaces
-
Music Genre Classification: A Comparative Analysis of Classical Machine Learning and Deep Learning Approaches
-
Unlocking the Value of Text: Event-Driven Reasoning and Multi-Level Alignment for Time Series Forecasting
-
GLANCE: Gaze-Led Attention Network for Compressed Edge-inference
-
A Framework for Modeling Liquefaction-Induced Road Disruptions After Earthquakes: Implications for Emergency Response and Access in the Cascadia Region of North America
-
Evasive Intelligence: Lessons from Malware Analysis for Evaluating AI Agents
-
Evaluating Time Awareness and Cross-modal Active Perception of Large Models via 4D Escape Room Task
-
RoCo Challenge at AAAI 2026: Benchmarking Robotic Collaborative Manipulation for Assembly Towards Industrial Automation
-
Automated Counting of Stacked Objects in Industrial Inspection
-
Anchor then Polish for Low-light Enhancement
-
Agent Lifecycle Toolkit (ALTK): Reusable Middleware Components for Robust AI Agents
-
Seeing Beyond: Extrapolative Domain Adaptive Panoramic Segmentation
-
ViFeEdit: A Video-Free Tuner of Your Video Diffusion Transformer
-
TabKD: Tabular Knowledge Distillation through Interaction Diversity of Learned Feature Bins
-
Talk, Evaluate, Diagnose: User-aware Agent Evaluation with Automated Error Analysis
-
RSGen: Enhancing Layout-Driven Remote Sensing Image Generation with Diverse Edge Guidance
-
Agentic workflow enables the recovery of critical materials from complex feedstocks via selective precipitation
-
Grokking as a Variance-Limited Phase Transition: Spectral Gating and the Epsilon-Stability Threshold
-
Real-Time Oriented Object Detection Transformer in Remote Sensing Images
-
Understanding Reasoning in LLMs through Strategic Information Allocation under Uncertainty
-
Seeking SOTA: Time-Series Forecasting Must Adopt Taxonomy-Specific Evaluation to Dispel Illusory Gains
-
Federated Learning of Binary Neural Networks: Enabling Low-Cost Inference
-
Not All Invariants Are Equal: Curating Training Data to Accelerate Program Verification with SLMs
-
FreeTalk: Emotional Topology-Free 3D Talking Heads
-
ViX-Ray: A Vietnamese Chest X-Ray Dataset for Vision-Language Models
-
Beyond the Covariance Trap: Unlocking Generalization in Same-Subject Knowledge Editing for Large Language Models
-
SlovKE: A Large-Scale Dataset and LLM Evaluation for Slovak Keyphrase Extraction
-
Clinically Aware Synthetic Image Generation for Concept Coverage in Chest X-ray Models
-
Building Trust in PINNs: Error Estimation through Finite Difference Methods
-
Are Dilemmas and Conflicts in LLM Alignment Solvable? A View from Priority Graph
-
Vib2ECG: A Paired Chest-Lead SCG-ECG Dataset and Benchmark for ECG Reconstruction
-
DOT: Dynamic Knob Selection and Online Sampling for Automated Database Tuning
-
Bridging Local and Global Knowledge: Cascaded Mixture-of-Experts Learning for Near-Shortest Path Routing
