Discover the Best AI Resources
Curated essentials, no noise — just what matters
Transforms scientific code repositories into executable, agent-learnable environments that support task generation, execution, and scientific verification. Agent-guided repository transformation produces verified interaction trajectories used to train the PhAI-IDE model family. Intended for research on agent learning, scientific-code repair, and training RL/SFT models.
Extracts replayable behaviors from working web apps and converts them into verifiable, reference-guided software-engineering tasks to evaluate and diagnose coding agents; includes an automated pipeline that scales to thousands of tasks.
Analyzes a failure mode in PPO critics called “Value Flattening” and proposes SP³O (Sparse PPO), which supervises a small set of well-separated states per response to mitigate flattened value estimates and improve policy learning for LLM alignment and reasoning tasks.
Enables specifying exact 24-bit hex colors for object-level image generation and editing via a unified prompt interface, using a Paint-500K dataset and timestep-gated pure-color anchors to improve color fidelity.
Describes DeepSeek-V4.1-Flash, a 552B-parameter multimodal Mixture-of-Experts LLM that supports up to 1M-token contexts and reduces KV cache footprint using Compressed Sparse Attention 2, FP4 KV caching, and SWA Bounded Replay to lower HBM/SSD and prefill costs.
Generates complete UI, poster and infographic layouts from text prompts, rendering legible in-image text and producing native RGBA output with transparent backgrounds. Suited for text-rich visual design workflows and pairs with a companion model that decomposes designs into editable layers.
Analyzes why on-policy distillation can produce excessively long student rollouts by identifying termination-token mismatch between students and teachers, and proposes aggregating functionally equivalent EOS tokens as a shared semantic stopping action to mitigate length inflation.
Finds token- and API-cost-saving harness mechanisms for long-horizon coding agents using automated recursive self-improvement; packages four surviving mechanisms (action fusion, context compaction, observation archiving, delegated reading) to cut recorded token traffic ~44.7–49.0% and API cost by about one third while preserving most capability.
Measures how individual harness components—planning, action space, and context management—affect coding agents' success, cost, and behavior. Uses a modular harness across 176 matched settings on SWE-Bench Verified and Terminal-Bench 2.1 to isolate component effects and surface model- and budget-dependent trade-offs.
Provides a domain-agnostic world-modeling framework that factorizes latent targets into orthogonal predictive components, with dedicated prediction branches and synthesis for multi-domain forecasting and intervention. Demonstrates improved dynamics and long-horizon rollouts across seven domains and includes experimental biological validation.
Provides reproducible, multi‑platform environments and execution‑grounded verification for hybrid computer‑use agents that interleave GUI exploration and code/CLI. Key features: a five‑platform harness, RecreationBench (250 tasks), reference‑grounded programmatic and visual assertions for automatic scoring.
Provides a complete benchmark and training release for native audio‑visual dialogue: 2,800 synthesized audio‑visual dialogues, tiered rubrics, scoring code, ~28GB of 1080p media, and an RL reward recipe to evaluate and train omni models that take video+audio and return text.