Base44 Superagents-AI agent that does it all
Mini toolsPapers
Filter by company
-
Gemini Robotics 1.5: Pushing the Frontier of Generalist Robots with Advanced Embodied Reasoning, Thinking, and Motion Transfer
-
Shielded Diffusion: Generating Novel and Diverse Images using Sparse Repellency
-
Generating Creative Chess Puzzles
-
Artificial Hivemind: The Open-Ended Homogeneity of Language Models (and Beyond)Lila Sciences / Allen Institute for Artificial Intelligence, Carnegie Mellon University, Stanford University, University of Washington
-
A Comprehensive Survey on Reinforcement Learning-based Agentic Search: Foundations, Roles, Optimizations, Evaluations, and Applications
-
VEHME: A Vision-Language Model For Evaluating Handwritten Mathematics ExpressionsPohang University of Science and Technology, Ulsan National Institute of Science and Technology
-
Step2Motion: Locomotion Reconstruction from Pressure Sensing InsolesMax Planck Institute for Informatics, Universitat Politècnica de Catalunya
-
HunyuanVideo 1.5 Technical Report
-
Enabling Differentially Private Federated Learning for Speech Recognition: Benchmarks, Adaptive Optimizers and Gradient Clipping
-
Evaluating honesty and lie detection techniques on a diverse suite of dishonest models
-
ControlThinker: Unveiling Latent Semantics for Controllable Image Generation through Visual Reasoning
-
ATLAS: Practical Scaling Laws for Multilingual Models
-
Neural Texture Splatting: Expressive 3D Gaussian Splatting for View Synthesis, Geometry, and Dynamic Reconstruction
-
AlphaFlow: Understanding and Improving MeanFlow Models
-
Seer: Online Context Learning for Fast Synchronous LLM Reinforcement Learning
-
Pico-Banana-400K: A Large-Scale Dataset for Text-Guided Image Editing
-
Rope to Nope and Back Again: A New Hybrid Attention Strategy
-
MEF: A Systematic Evaluation Framework for Text-to-Image Models
-
Seed3D 1.0: From Images to High-Fidelity Simulation-Ready 3D Assets
-
Kaleido: Open-Sourced Multi-Subject Reference Video Generation Model
-
Glyph: Scaling Context Windows via Visual-Text Compression
-
Arctic-Extract Technical Report
-
Cortex AISQL: A Production SQL Engine for Unstructured Data
-
When Intelligence Fails: An Empirical Study on Why LLMs Struggle with Password CrackingFuture Data Minds Research Lab
-
Chronos-2: From Univariate to Universal Forecasting
-
Agentic Misalignment: How LLMs Could Be Insider ThreatsUniversity College London
-
Cortex: Workflow-Aware Resource Pooling and Scheduling for Agentic Servin
-
Shifting Work Patterns with Generative AI
-
SparK: Query-Aware Unstructured Sparsity with Recoverable KV Cache Channel Pruning
-
BenchPress: Rapid Benchmark Curation
-
LLM-based Relevance Assessment for Web-Scale Search Evaluation at Pinterest
-
Training-Free Group Relative Policy Optimization
-
LUT-LLM: Efficient Large Language Model Inference with Memory-based Computations on FPGAs
-
Efficient and Adaptable Overlapping for Computation and Communication via Signaling and Reordering
-
Training-Free Group Relative Policy Optimization
-
What Is Your Agent's GPA? A Framework for Evaluating Agent Goal-Plan-Action Alignment
-
Seeing, Listening, Remembering, and Reasoning: A Multimodal Agent with Long-Term Memory
-
Poisoning Attacks on LLMs Require a Near-constant Number of Poison SamplesAnthropic / Alan Turing Institute, Oxford Applied and Theoretical Machine Learning, Swiss Federal Institute of Technology in Zurich, UK AI Security Institute, University of Oxford
-
WebAgent-R1: Training Web Agents via End-to-End Multi-Turn Reinforcement Learning
-
Moloch's Bargain: Emergent Misalignment When LLMs Compete for AudiencesStanford University
-
SuffixDecoding: Extreme Speculative Decoding for Emerging AI Applications
-
Mind Your Tone: Investigating How Prompt Politeness Affects LLM Accuracy (short paper)The Pennsylvania State University
-
Less is More: Recursive Reasoning with Tiny Networks
-
Tongyi DeepResearch Technical Report
-
TabArena: A Living Benchmark for Machine Learning on Tabular Data
-
IBM Granite 4.0: hyper-efficient, high performance hybrid models for enterprise
-
Diffusion Adversarial Post-Training for One-Step Video Generatio
-
Pretraining Large Language Models with NVFP4
-
Training Agents Inside of Scalable World Models
-
APRIL: Active Partial Rollouts in Reinforcement Learning to Tame Long-tail Generation
