Rocket - Think it. Type it. Launch it.
Mini toolsPapers
Filter by company
-
Prompt Compression with Context-Aware Sentence Encoding for Fast and Improved LLM Inference
-
Alignment faking in large language models
-
How Often are Fingerprints Repeated in the Population? Expanding on Evidence from AI With the Birthday ParadoxUniversity of Pennsylvania Department of Criminology and Statistics, University of Pennsylvania School of Engineering and Applied Sciences
-
DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding
-
VDB-GPDF: Online Gaussian Process Distance Field with VDB Structure
-
pfl-research: simulation framework for accelerating research in Private Federated Learning
-
Frontier AI systems have surpassed the self-replicating red lineFudan University
-
InstantRestore: Single-Step Personalized Face Restoration with Shared-Image Attention
-
Best-of-N Jailbreaking
-
Creating realistic 3D shapes using generative AIMassachusetts Institute of Technology
-
Commit0: Library Generation from Scratch
-
ARTIST: Improving the Generation of Text-rich Images with Disentangled Diffusion Models and Large Language Models
-
Controlling Language and Diffusion Models by Transporting Activations
-
The Rise and Potential of Large Language Model Based Agents: A SurveyMIT
-
Evaluating Cultural and Social Awareness of LLM Web Agents
-
SF-V: Single Forward Video Generation Model
-
The Llama 3 Herd of Model
-
Improving Pinterest Search Relevance Using Large Language Models
-
NVLM: Open Frontier-Class Multimodal LLMs
-
HyQE: Ranking Contexts with Hypothetical Query Embeddings
-
RedPajama: an Open Dataset for Training Large Language Models
-
Understanding Chain-of-Thought in LLMs through Information Theory
-
Survival of the Safest: Towards Secure Prompt Optimization through Interleaved Multi-Objective Evolution
-
Nemotron-4-340B-Instruct
-
Pixtral 12B
-
Data-Driven Discovery of Conservation Laws from Trajectories via Neural Deflation
-
Chronos: Learning the Language of Time Series
-
Qwen2-VL: Enhancing Vision-Language Model’s Perception of the World at Any Resolution
-
Duo-LLM: A Framework for Studying Adaptive Computation in Large Language Models
-
HM3: Heterogeneous Multi-Class Model Merging
-
arsier: Recipes for Training and Evaluating Large Video Description Models
-
OpenVLA: An Open-Source Vision-Language-Action Model
-
ViewCrafter: Taming Video Diffusion Models for High-fidelity Novel View Synthesis
-
Learning-based Multi-View Stereo: A Survey
-
Arctic-TILT. Business Document Understanding at Sub-Billion Scale
-
General-Purpose User Modeling with Behavioral Logs
-
LazyLLM: Dynamic Token Pruning for Efficient Long Context LLM Inference
-
Qwen2-Audio Technical Report
-
Qwen2 Technical Report
-
Sycophancy to Subterfuge: Investigating Reward-Tampering in Large Language Models
-
Harvesting Efficient On-Demand Order Pooling from Skilled Couriers: Enhancing Graph Representation Learning for Refining Real-time Many-to-One Assignments
-
Claude 3.5 Sonnet Model Card Addendum
-
Abliteration
-
Multi-Agent Software Development through Cross-Team Collaboration
-
Efficient Large Language Model Inference with Limited Memory
-
AgentBoard: An Evaluation Platform for LLM-Based Autonomous Agents
-
Creative Text-to-Audio Generation via Synthesizer Programming
-
Retrieval Augmented Generation for Domain-specific Question Answering
-
Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnet
-
Multimodal Chain-of-Thought Reasoning in Language Models
