Rocket - Think it. Type it. Launch it.
Mini toolsPapers
Filter by company
-
Slim attention: cut your context memory in half without loss – K-cache is all you need for MHA
-
Fundamental Limits of Neural Network Sparsification: Evidence from Catastrophic Interpretability Collapse
-
Adaptive Anchor Policies for Efficient 4D Gaussian Streaming
-
From Drop-off to Recovery: A Mechanistic Analysis of Segmentation in MLLMs
-
Visual SLAM with DEM Anchoring for Lunar Surface Navigation
-
KANtize: Exploring Low-bit Quantization of Kolmogorov-Arnold Networks for Efficient Inference
-
Neuron-Level Emotion Control in Speech-Generative Large Audio-Language Models
-
Draft-and-Prune: Improving the Reliability of Auto-formalization for Logical Reasoning
-
Deployment and Evaluation of an EHR-integrated, Large Language Model-Powered Tool to Triage Surgical Patients
-
Neural Radiance Maps for Extraterrestrial Navigation and Path Planning
-
GigaWorld-Policy: An Efficient Action-Centered World--Action Model
-
Graph-Native Cognitive Memory for AI Agents: Formal Belief Revision Semantics for Versioned Memory Architectures
-
On the Cone Effect and Modality Gap in Medical Vision-Language Embeddings
-
Binary Latent Protein Fitness Landscapes for Quantum Annealing Optimization
-
Pathology-Aware Multi-View Contrastive Learning for Patient-Independent ECG Reconstruction
-
Variational Rectification Inference for Learning with Noisy Labels
-
LED: A Benchmark for Evaluating Layout Error Detection in Document Analysis
-
ConfusionBench: An Expert-Validated Benchmark for Confusion Recognition and Localization in Educational Videos
-
Wasserstein-type Gaussian Process Regressions for Input Measurement Uncertainty
-
DANCE: Dynamic 3D CNN Pruning: Joint Frame, Channel, and Feature Adaptation for Energy Efficiency on the Edge
-
Mathematical Modeling of Cancer-Bacterial Therapy: Analysis and Numerical Simulation via Physics-Informed Neural Networks
-
S3T-Former: A Purely Spike-Driven State-Space Topology Transformer for Skeleton Action Recognition
-
Classifier Pooling for Modern Ordinal Classification
-
MCP-38: A Comprehensive Threat Taxonomy for Model Context Protocol Systems (v1.0)
-
Directing the Narrative: A Finetuning Method for Controlling Coherence and Style in Story Generation
-
GUIDE: GenAI Units In Digital Design Education
-
WINFlowNets: Warm-up Integrated Networks Training of Generative Flow Networks for Robotics and Machine Fault Adaptation
-
From Words to Worlds: Benchmarking Cross-Cultural Cultural Understanding in Machine Translation
-
3D MRI-Based Alzheimer's Disease Classification Using Multi-Modal 3D CNN with Leakage-Aware Subject-Level Evaluation
-
Contrastive Reasoning Alignment: Reinforcement Learning from Hidden Representations
-
Beyond bouba/kiki: Multidimensional semantic signals are deeply woven into the fabric of natural language
-
Symphony: A Cognitively-Inspired Multi-Agent System for Long-Video Understanding
-
A Synthesizable RTL Implementation of Predictive Coding Networks
-
ReLMXEL: Adaptive RL-Based Memory Controller with Explainable Energy and Latency Optimization
-
InfoDensity: Rewarding Information-Dense Traces for Efficient Reasoning
-
Ruyi2.5 Technical Report
-
Recurrent Reasoning with Vision-Language Models for Estimating Long-Horizon Embodied Task Progress
-
A Proposal-Free Query-Guided Network for Grounded Multimodal Named Entity Recognition
-
Physics-informed offline reinforcement learning eliminates catastrophic fuel waste in maritime routing
-
DarkDriving: A Real-World Day and Night Aligned Dataset for Autonomous Driving in the Dark Environment
-
ShuttleEnv: An Interactive Data-Driven RL Environment for Badminton Strategy Modeling
-
MedSAD-CLIP: Supervised CLIP with Token-Patch Cross-Attention for Medical Anomaly Detection and Segmentation
-
FineViT: Progressively Unlocking Fine-Grained Perception with Dense Recaptions
-
A Progressive Visual-Logic-Aligned Framework for Ride-Hailing Adjudication
-
Grid Spatial Understanding: A Dataset for Textual Spatial Reasoning over Grids, Embodied Settings, and Coordinate Structures
-
EvoGuard: An Extensible Agentic RL-based Framework for Practical and Evolving AI-Generated Image Detection
-
Learning Permutation Distributions via Reflected Diffusion on Ranks
-
Beyond Outliers: A Data-Free Layer-wise Mixed-Precision Quantization Approach Driven by Numerical and Structural Dual-Sensitivity
-
OnlineHMR: Video-based Online World-Grounded Human Mesh Recovery
-
PACE-RAG: Patient-Aware Contextual and Evidence-based Policy RAG for Clinical Drug Recommendation
