Base44 Superagents-AI agent that does it all
Mini toolsPapers
Filter by company
-
Confucius Code Agent: Scalable Agent Scaffolding for Real-World Codebases
-
CXL-SpecKV: A Disaggregated FPGA Speculative KV-Cache for Datacenter LLM Serving
-
BabyVLM-V2: Toward Developmentally Grounded Pretraining and Benchmarking of Vision Foundation Models
-
Omni-Attribute: Open-vocabulary Attribute Encoder for Visual Concept Personalization
-
Glance: Accelerating Diffusion Models with 1 Sample
-
Sharp Monocular View Synthesis in Less Than a Second
-
On Learning-Curve Monotonicity for Maximum Likelihood Estimators
-
Matrix-game 2.0: An open-source real-time and streaming interactive world model
-
UniUGP: Unifying Understanding, Generation, and Planing For End-to-end Autonomous Driving
-
Efficiently Reconstructing Dynamic Scenes One D4RT at a Time
-
PAVAS: Physics-Aware Video-to-Audio Synthesis
-
Chain-of-Image Generation: Toward Monitorable and Controllable Image Generation
-
HybridToken-VLM: Hybrid Token Compression for Vision-Language Models
-
MM-CoT:A Benchmark for Probing Visual Chain-of-Thought Reasoning in Multimodal Models
-
Process Reward Models That Think
-
Distribution Matching Variational AutoEncoder
-
Skywork-R1V4: Toward Agentic Multimodal Intelligence through Interleaved Thinking with Images and DeepResearch
-
UnityVideo: Unified Multi-Modal Multi-Task Learning for Enhancing World-Aware Video Generation
-
Kimi-Dev: Agentless Training as Skill Prior for SWE-Agents
-
Unsupervised decoding of encoded reasoning using language model interpretability
-
EditThinker: Unlocking Iterative Reasoning for Any Image Editor
-
Entropy Ratio Clipping as a Soft Global Constraint for Stable Reinforcement Learning
-
EgoEdit: Dataset, Real-Time Streaming Model, and Benchmark for Egocentric Video Editing
-
Delving into Latent Spectral Biasing of Video VAEs for Superior Diffusability
-
Semantics Lead the Way: Harmonizing Semantic and Texture Modeling with Asynchronous Latent Diffusion
-
SIMA 2: A Generalist Embodied Agent for Virtual Worlds
-
SMP: Reusable Score-Matching Motion Priors for Physics-Based Character Control
-
Training LLMs for Honesty via Confessions
-
DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models
-
VIGS-SLAM: Visual Inertial Gaussian Splatting SLAM
-
The Art of Scaling Test-Time Compute for Large Language Models
-
TUNA: Taming Unified Visual Representations for Native Unified Multimodal Models
-
The Adoption and Usage of AI Agents: Early Evidence from Perplexity
-
ThetaEvolve: Test-time Learning on Open Problems
-
LatBot: Distilling Universal Latent Actions for Vision-Language-Action Models
-
Canvas-to-Image: Compositional Image Generation with Multimodal Controls
-
LayerComposer: Multi-Human Personalized Generation via Layered Canvas
-
The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexity
-
Early Science Acceleration Experiments with GPT-5
-
Anthropic Economic Index report: Uneven geographic and enterprise AI adoption
-
Weight-Sparse Transformers Have Interpretable Circuits
-
SageServe: Optimizing LLM Serving on Cloud Data Centers with Forecast Aware Auto-Scaling
-
Tiny Model, Big Logic: Diversity-Driven Optimization Elicits Large-Model Reasoning Ability in VibeThinker-1.5B
-
Steering Language Models with Weight ArithmeticUniversity of Copenhagen
-
Step-Audio-EditX Technical Report
-
s3: You Don't Need That Much Data to Train a Search Agent via RL
-
Kimi Linear: An Expressive, Efficient Attention Architecture
-
Charts Are Not Images: On the Challenges of Scientific Chart Editing
-
Signs of introspection in large language models
-
An efficient probabilistic hardware architecture for diffusion-like models
