Rocket - Think it. Type it. Launch it.
Mini toolsPapers
Filter by company
-
OnlineHMR: Video-based Online World-Grounded Human Mesh Recovery
-
PACE-RAG: Patient-Aware Contextual and Evidence-based Policy RAG for Clinical Drug Recommendation
-
WebPII: Benchmarking Visual PII Detection for Computer-Use Agents
-
A 3D Reconstruction Benchmark for Asset Inspection
-
MCoT-MVS: Multi-level Vision Selection by Multi-modal Chain-of-Thought Reasoning for Composed Image Retrieval
-
Public Profile Matters: A Scalable Integrated Approach to Recommend Citations in the Wild
-
Continually self-improving AI
-
Lightweight Adaptation for LLM-based Technical Service Agent: Latent Logic Augmentation and Robust Noise Reduction
-
Variational Kernel Design for Internal Noise: Gaussian Chaos Noise, Representation Compatibility, and Reliable Deep Learning
-
Towards Safer Large Reasoning Models by Promoting Safety Decision-Making before Chain-of-Thought Generation
-
Material Magic Wand: Material-Aware Grouping of 3D Parts in Untextured Meshes
-
Interpretable Context Methodology: Folder Structure as Agentic Architecture
-
Speak, Segment, Track, Navigate: An Interactive System for Video-Guided Skull-Base Surgery
-
3D tomography of exchange phase in a Si/SiGe quantum dot device
-
Residual Stream Duality in Modern Transformer Architectures
-
Power Analysis for Prediction-Powered Inference
-
Shuffling the Stochastic Mirror Descent via Dual Lipschitz Continuity and Kernel Conditioning
-
Collaborative Temporal Feature Generation via Critic-Free Reinforcement Learning for Cross-User Sensor-Based Activity Recognition
-
Enhancing Linguistic Generalization of VLA: Fine-Tuning OpenVLA via Synthetic Instruction Augmentation
-
POaaS: Minimal-Edit Prompt Optimization as a Service to Lift Accuracy and Cut Hallucinations on On-Device sLLMs
-
The Era of End-to-End Autonomy: Transitioning from Rule-Based Driving to Large Driving Models
-
A Context Alignment Pre-processor for Enhancing the Coherence of Human-LLM Dialog
-
ARISE: Agent Reasoning with Intrinsic Skill Evolution in Hierarchical Reinforcement Learning
-
Safe Distributionally Robust Feature Selection under Covariate Shift
-
ViT-AdaLA: Adapting Vision Transformers with Linear Attention
-
Large Reward Models: Generalizable Online Robot Reward Generation with Vision-Language Models
-
Adaptive regularization parameter selection for high-dimensional inverse problems: A Bayesian approach with Tucker low-rank constraints
-
Attribution Upsampling should Redistribute, Not Interpolate
-
Resource Consumption Threats in Large Language Models
-
PhysQuantAgent: An Inference Pipeline of Mass Estimation for Vision-Language Models
-
SEAHateCheck: Functional Tests for Detecting Hate Speech in Low-Resource Languages of Southeast Asia
-
ClaimFlow: Tracing the Evolution of Scientific Claims in NLP
-
MDM-Prime-v2: Binary Encoding and Index Shuffling Enable Compute-optimal Scaling of Diffusion Language Models
-
Volumetrically Consistent Implicit Atlas Learning via Neural Diffeomorphic Flow for Placenta MRI
-
A Depth-Aware Comparative Study of Euclidean and Hyperbolic Graph Neural Networks on Bitcoin Transaction Systems
-
Structured prototype regularization for synthetic-to-real driving scene parsing
-
Prompt-tuning with Attribute Guidance for Low-resource Entity Matching
-
Interact3D: Compositional 3D Generation of Interactive Objects
-
Towards the Vision-Sound-Language-Action Paradigm: The HEAR Framework for Sound-Centric Manipulation
-
RecBundle: A Next-Generation Geometric Paradigm for Explainable Recommender Systems
-
CounterRefine: Answer-Conditioned Counterevidence Retrieval for Inference-Time Knowledge Repair in Factual Question Answering
-
Parallel In-context Learning for Large Vision Language Models
-
Diffusion Models for Joint Audio-Video Generation
-
LICA: Layered Image Composition Annotations for Graphic Design Research
-
OneWorld: Taming Scene Generation with 3D Unified Representation Autoencoder
-
Reevaluating the Intra-Modal Misalignment Hypothesis in CLIP
-
NanoGS: Training-Free Gaussian Splat Simplification
-
Efficient LLM Serving for Agentic Workflows: A Data Systems Perspective
-
Frequency Matters: Fast Model-Agnostic Data Curation for Pruning and Quantization
-
Machine intelligence supports the full chain of 2D dendrite synthesis
