SOTAVerified

Position

Papers

Showing 51100 of 3684 papers

TitleStatusHype
How do Large Language Models Learn In-Context? Query and Key Matrices of In-Context Heads are Two Towers for Metric LearningCode2
Position: What Can Large Language Models Tell Us about Time Series AnalysisCode2
Robot Trajectron: Trajectory Prediction-based Shared Control for Robot ManipulationCode2
Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space ModelCode2
Extending LLMs' Context Window with 100 SamplesCode2
Never Lost in the Middle: Mastering Long-Context Question Answering with Position-Agnostic Decompositional TrainingCode2
Fast Chain-of-Thought: A Glance of Future from Parallel Decoding Leads to Answers FasterCode2
Position Interpolation Improves ALiBi ExtrapolationCode2
ProbTS: Benchmarking Point and Distributional Forecasting across Diverse Prediction HorizonsCode2
PoSE: Efficient Context Window Extension of LLMs via Positional Skip-wise TrainingCode2
Lost in the Middle: How Language Models Use Long ContextsCode2
Think Twice before Driving: Towards Scalable Decoders for End-to-End Autonomous DrivingCode2
Detection Transformer with Stable MatchingCode2
LayoutDM: Discrete Diffusion Model for Controllable Layout GenerationCode2
A Length-Extrapolatable TransformerCode2
CroCo v2: Improved Cross-view Completion Pre-training for Stereo Matching and Optical FlowCode2
Point Transformer V2: Grouped Vector Attention and Partition-based PoolingCode2
Mega: Moving Average Equipped Gated AttentionCode2
DeepInteraction: 3D Object Detection via Modality InteractionCode2
Stratified Transformer for 3D Point Cloud SegmentationCode2
ParC-Net: Position Aware Circular Convolution with Merits from ConvNets and TransformerCode2
Train Short, Test Long: Attention with Linear Biases Enables Input Length ExtrapolationCode2
FLAT: Chinese NER Using Flat-Lattice TransformerCode2
MPNet: Masked and Permuted Pre-training for Language UnderstandingCode2
Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic SegmentationCode2
Machine Learning in Asset Management—Part 1: Portfolio Construction—Trading StrategiesCode2
R-FCN-3000 at 30fps: Decoupling Detection and ClassificationCode2
SeqPE: Transformer with Sequential Position EncodingCode1
POSS: Position Specialist Generates Better Draft for Speculative DecodingCode1
ComRoPE: Scalable and Robust Rotary Position Embedding Parameterized by Trainable Commuting Angle MatricesCode1
LLM as Effective Streaming Processor: Bridging Streaming-Batch Mismatches with Group Position EncodingCode1
A Skull-Adaptive Framework for AI-Based 3D Transcranial Focused Ultrasound SimulationCode1
PoseBench3D: A Cross-Dataset Analysis Framework for 3D Human Pose EstimationCode1
RGB-Event Fusion with Self-Attention for Collision PredictionCode1
TC-GS: Tri-plane based compression for 3D Gaussian SplattingCode1
LookAhead Tuning: Safer Language Models via Partial Answer PreviewsCode1
Visual Position Prompt for MLLM based Visual GroundingCode1
GNNs as Predictors of Agentic Workflow PerformancesCode1
VRoPE: Rotary Position Embedding for Video Large Language ModelsCode1
A Contextual-Aware Position Encoding for Sequential RecommendationCode1
WyckoffDiff -- A Generative Diffusion Model for Crystal SymmetryCode1
Position-aware Automatic Circuit DiscoveryCode1
ADIFF: Explaining audio difference using natural languageCode1
Learning Efficient Positional Encodings with Graph Neural NetworksCode1
AlphaPre: Amplitude-Phase Disentanglement Model for Precipitation NowcastingCode1
Rethinking Addressing in Language Models via Contexualized Equivariant Positional EncodingCode1
DriveEditor: A Unified 3D Information-Guided Framework for Controllable Object Editing in Driving ScenesCode1
Cross-View Geo-Localization with Street-View and VHR Satellite Imagery in Decentrality SettingsCode1
Wonderful Matrices: Combining for a More Efficient and Effective Foundation Model ArchitectureCode1
Cross-Attention Head Position Patterns Can Align with Human Visual Concepts in Text-to-Image Generative ModelsCode1
Show:102550
← PrevPage 2 of 74Next →

No leaderboard results yet.