experimental results
The outcomes obtained from controlled tests or studies, aimed at validating hypotheses or assessing the effectiveness of models and algorithms.
- 3D Gaussian Splatting based Scene-independent Relocalization with Unidirectional and Bidirectional Feature Fusion
- A Dynamic Learning Strategy for Dempster-Shafer Theory with Applications in Classification and Enhancement
- A Frustratingly Simple Yet Highly Effective Attack Baseline: Over 90% Success Rate Against the Strong Black-box Models of GPT-4.5/4o/o1
- Accelerated Distance-adaptive Methods for Hölder Smooth and Convex Optimization
- Adaptive Re-calibration Learning for Balanced Multimodal Intention Recognition
- AdvEDM: Fine-grained Adversarial Attack against VLM-based Embodied Agents
- AliO: Output Alignment Matters in Long-Term Time Series Forecasting
- Bag of Tricks for Inference-time Computation of LLM Reasoning
- COLA: Towards Efficient Multi-Objective Reinforcement Learning with Conflict Objective Regularization in Latent Space
- Can LLMs Outshine Conventional Recommenders? A Comparative Evaluation
- Combinatorial Ski Rental Problem: Robust and Learning-Augmented Algorithms
- DON’T NEED RETRAINING: A Mixture of DETR and Vision Foundation Models for Cross-Domain Few-Shot Object Detection
- Data-Free Model Extraction for Black-box Recommender Systems via Graph Convolutions
- DeblurDiff: Real-Word Image Deblurring with Generative Diffusion Models
- Diff-ICMH: Harmonizing Machine and Human Vision in Image Compression with Generative Prior
- Discovering Symbolic Partial Differential Equation by Abductive Learning
- Dual Prototype-Enhanced Contrastive Framework for Class-Imbalanced Graph Domain Adaptation
- Dynamic Semantic-Aware Correlation Modeling for UAV Tracking
- EAP-GP: Mitigating Saturation Effect in Gradient-based Automated Circuit Identification
- Enhancing the Maximum Effective Window for Long-Term Time Series Forecasting
- ErrorTrace: A Black-Box Traceability Mechanism Based on Model Family Error Space
- Evolutionary Multi-View Classification via Eliminating Individual Fitness Bias
- Explainable Reinforcement Learning from Human Feedback to Improve Alignment
- ImageSentinel: Protecting Visual Datasets from Unauthorized Retrieval-Augmented Image Generation
- Inference-Time Personalized Alignment with a Few User Preference Queries
- Investigating and Mitigating Catastrophic Forgetting in Medical Knowledge Injection through Internal Knowledge Augmentation Learning
- Learning to Rank for In-Context Example Retrieval
- Learning-Augmented Streaming Algorithms for Correlation Clustering
- Let's Revise Step-by-Step: A Unified Local Search Framework for Code Generation with LLMs
- Leveraging Conditional Dependence for Efficient World Model Denoising
- LoRO: Real-Time on-Device Secure Inference for LLMs via TEE-Based Low Rank Obfuscation
- Local-Global Associative Frames for Symmetry-Preserving Crystal Structure Modeling
- Logical Expressiveness of Graph Neural Networks with Hierarchical Node Individualization
- MLE-STAR: Machine Learning Engineering Agent via Search and Targeted Refinement
- MTL-KD: Multi-Task Learning Via Knowledge Distillation for Generalizable Neural Vehicle Routing Solver
- Mol-LLaMA: Towards General Understanding of Molecules in Large Molecular Language Model
- On the SAC-BL Algorithm for Anomaly Detection
- Open CaptchaWorld: A Comprehensive Web-based Platform for Testing and Benchmarking Multimodal LLM Agents
- Orientation Matters: Making 3D Generative Models Orientation-Aligned
- PRESTO: Preimage-Informed Instruction Optimization for Prompting Black-Box LLMs
- Poison as Cure: Visual Noise for Mitigating Object Hallucinations in LVMs
- R-KV: Redundancy-aware KV Cache Compression for Reasoning Models
- RF-Agent: Automated Reward Function Design via Language Agent Tree Search
- RealMath: A Continuous Benchmark for Evaluating Language Models on Research-Level Mathematics
- Reasoning Gym: Reasoning Environments for Reinforcement Learning with Verifiable Rewards
- Reasoning is Periodicity? Improving Large Language Models Through Effective Periodicity Modeling
- Rethinking Neural Combinatorial Optimization for Vehicle Routing Problems with Different Constraint Tightness Degrees
- Robust Hallucination Detection in LLMs via Adaptive Token Selection
- Robust Minimax Boosting with Performance Guarantees
- Robust and Scalable Autonomous Reinforcement Learning in Irreversible Environments
- Safe RLHF-V: Safe Reinforcement Learning from Multi-modal Human Feedback
- Scale-invariant attention
- Sign-In to the Lottery: Reparameterizing Sparse Training
- Skrull: Towards Efficient Long Context Fine-tuning through Dynamic Data Scheduling
- SpEx: A Spectral Approach to Explainable Clustering
- Sparse Autoencoders Learn Monosemantic Features in Vision-Language Models
- Split conformal classification with unsupervised calibration
- SymMaP: Improving Computational Efficiency in Linear Solvers through Symbolic Preconditioning
- Think Only When You Need with Large Hybrid-Reasoning Models
- Thoughts Are All Over the Place: On the Underthinking of Long Reasoning Models
- Torch-Uncertainty: Deep Learning Uncertainty Quantification
- Towards Generalizable 3D Human Pose Estimation via Ensembles on Flat Loss Landscapes
- Towards Generalizable Detector for Generated Image
- TranSUN: A Preemptive Paradigm to Eradicate Retransformation Bias Intrinsically from Regression Models in Recommender Systems
- UniCTokens: Boosting Personalized Understanding and Generation via Unified Concept Tokens
- Vad-R1: Towards Video Anomaly Reasoning via Perception-to-Cognition Chain-of-Thought