state-of-the-art results
State-of-the-art results define the highest performance level achieved in a specific task or benchmark within the AI community. This serves as a measure of success and a goal for ongoing research efforts.
- A Multimodal BiMamba Network with Test-Time Adaptation for Emotion Recognition Based on Physiological Signals
- A TRIANGLE Enables Multimodal Alignment Beyond Cosine Similarity
- A Unified Solution to Video Fusion: From Multi-Frame Learning to Benchmarking
- ADG: Ambient Diffusion-Guided Dataset Recovery for Corruption-Robust Offline Reinforcement Learning
- AI Research Agents for Machine Learning: Search, Exploration, and Generalization in MLE-bench
- Accurate and Efficient Low-Rank Model Merging in Core Space
- Asymmetric Dual Self-Distillation for 3D Self-Supervised Representation Learning
- Compress & Cache: Vision token compression for efficient generation and retrieval
- Confusion-Driven Self-Supervised Progressively Weighted Ensemble Learning for Non-Exemplar Class Incremental Learning
- Disentanglement Beyond Static vs. Dynamic: A Benchmark and Evaluation Framework for Multi-Factor Sequential Representations
- Domain-RAG: Retrieval-Guided Compositional Image Generation for Cross-Domain Few-Shot Object Detection
- DynamicRAG: Leveraging Outputs of Large Language Model as Feedback for Dynamic Reranking in Retrieval-Augmented Generation
- Execution Guided Line-by-Line Code Generation
- Fast and Fluent Diffusion Language Models via Convolutional Decoding and Rejective Fine-tuning
- Fixed-Point RNNs: Interpolating from Diagonal to Dense
- GUIDED: Granular Understanding via Identification, Detection, and Discrimination for Fine-Grained Open-Vocabulary Object Detection
- GraphKeeper: Graph Domain-Incremental Learning via Knowledge Disentanglement and Preservation
- HopaDIFF: Holistic-Partial Aware Fourier Conditioned Diffusion for Referring Human Action Segmentation in Multi-Person Scenarios
- KLASS: KL-Guided Fast Inference in Masked Diffusion Models
- Knowledge Graph Enhanced Generative Multi-modal Models for Class-Incremental Learning
- Learning Neural Exposure Fields for View Synthesis
- Logic.py: Bridging the Gap between LLMs and Constraint Solvers
- Omnipresent Yet Overlooked: Heat Kernels in Combinatorial Bayesian Optimization
- PLEIADES: Building Temporal Kernels with Orthogonal Polynomials
- RL Tango: Reinforcing Generator and Verifier Together for Language Reasoning
- SE-GUI: Enhancing Visual Grounding for GUI Agents via Self-Evolutionary Reinforcement Learning
- Temporal Chain of Thought: Long-Video Understanding by Thinking in Frames
- TopER: Topological Embeddings in Graph Representation Learning
- UniCTokens: Boosting Personalized Understanding and Generation via Unified Concept Tokens