News
AI, cybersecurity, machine learning, scraping & programming news.
Learning Meta-Skills for Agent Harness Design in Test-Time AI4AI
Agent performance depends on both reasoning ability and the environment in which it acts. Most research focuses on improving the model itself, but this paper from Apodex and the University of Illinois Urbana-Champaign takes a diff...
Breaking the Uniformity Trap: Scaling Video Diffusion Model via SplitMoE
Video diffusion models have achieved remarkable fidelity in text-to-video synthesis, yet scaling these models to capture complex spatiotemporal dynamics remains computationally expensive. Diffusion Transformers (DiTs) have become...
Multi-Agent Flow Matching with Decoupled Generative Guidance
Generative modeling has become a cornerstone for producing diverse objects from complex, multimodal distributions. Diffusion models and flow matching frameworks have demonstrated remarkable success across domains ranging from lang...
Show HN: Worlds, local replicas of Stripe and Zendesk for testing AI agents
AI agent testing has entered a new phase where every action can be traced, replayed, and verified against a known state. Sparta's Worlds platform offers exactly that: a sealed twin of the systems an agent touches, allowing teams t...
PDMD: Projected Distribution Matching Distillation for Video Diffusion Models
Modern video diffusion models require many denoising evaluations over long spatiotemporal token sequences, making inference computationally expensive. Distribution Matching Distillation (DMD) was introduced to reduce the number of...
Unifying Distributional Training for One-Step Visual Generation
One-step visual generation requires efficient supervision that can shape a generator in a single forward pass. Prior distributional training methods match real and generated features in frozen representation spaces, but lack a uni...
TokenCast: Forecasting Token Consumption During LLM Agent Execution
When a large language model (LLM) agent executes the same task, token consumption can vary by over an order of magnitude across runs. The agent chooses its next steps based on tool feedback and intermediate results, while the grow...
Improving Test-Time Scaling with Adaptive Looped Transformers
Looped transformers have emerged as a parameter-efficient architecture by reusing a shared stack of layers across multiple input positions during a single forward pass. This reuse treats computation as a dynamic process that can b...
Copy the Same, Distill the Difference: Initializing Linear Vision Transformers
Linear Vision Transformers (ViTs) aim to replace the softmax attention mechanism with a linear-complexity alternative, enabling more efficient token routing at scale. However, a persistent obstacle is that linear ViTs typically re...
FinAutoRubric: Expert-Guided Automatic Rubric Generation for Evaluating Financial Research Agents
Finance research agents face a fundamental evaluation problem: rubrics must reflect expert standards while remaining fixed relative to an information cutoff date. Traditional benchmarks rely on hand-crafted, per-item rubrics that...