Research Papers
Kimi Launches Agent Swarm: Self-Organizing AI Teams of Up to 100 Agents
Kimi introduces Agent Swarm, a system that autonomously creates and manages up to 100 sub-agents to tackle complex tasks in parall...
Kimi Unveils PerceptionBench: A New Benchmark for Multimodal Perception
Kimi (Moonshot) introduces PerceptionBench, a benchmark designed to evaluate multimodal perception capabilities of AI models.
TableVerse: 100K Real-World Tabletop Scenes for Generalizable Robot Manipulation
Hugging Face researchers introduce TableVerse, an automated Real2Sim pipeline that reconstructs high-fidelity, physically plausibl...
Recurrent Sinusoidal INRs Boost Fidelity with Fewer Parameters
A new study from Hugging Face shows that recurrent sinusoidal activations in implicit neural representations (INRs) enrich spectra...
Predictive Divergence Masks: A New Direction for LLM Reinforcement Learning
Researchers propose predictive divergence masks to replace the ratio-based direction criterion in PPO-style RL for LLMs, improving...
ReOPD: Off-Environment On-Policy Distillation for Multi-Turn LLM Agents
Hugging Face researchers propose ReOPD, a method that reuses pre-collected teacher trajectories as replayed prefixes to achieve on...
Hugging Face Unveils Robostral Navigate: An 8B VLM for Scalable Robot Navigation Using Only a Single RGB Camera
Robostral Navigate is an 8B vision-language model that consumes only monocular RGB images to predict waypoints, achieving state-of...
Hugging Face Researchers Introduce Experience Distillation: Retaining 64.8% of In-Context Learning Gains Without Context
A new method called Experience Distillation allows agents to internalize interaction histories into model weights without addition...
Meta AI Launches Muse Spark: A Multimodal Reasoning Model Toward Personal Superintelligence
Meta AI introduces Muse Spark, the first model from Meta Superintelligence Labs, featuring native multimodal reasoning, tool use,...
Kimi Releases PerceptionBench: A New Benchmark for Atomic Visual Perception in Multimodal AI
Kimi (Moonshot) unveils PerceptionBench, a benchmark designed to isolate and evaluate atomic visual perception capabilities in mul...
Meta's Brain2Qwerty v2 Decodes Brain Signals into Text Without Surgery, Achieving 61% Word Accuracy
Meta AI announces Brain2Qwerty v2, a non-invasive AI system that decodes brain activity into text in real time, achieving 61% word...
Meta's SAM 3 and DINOv3 Power Real-Time Scientific Imaging at DOE Labs
Meta's open-source AI models, Segment Anything Model 3 (SAM 3) and DINOv3, are being used by the SYNAPS-I project at Lawrence Berk...