Maps a state and question to typed probabilistic decisions (choice distributions, yes/no probabilities, or scored/ordinal outputs) across controlled synthetic tasks. Offers multiple frozen configs with train/calibration/validation/test/OOD splits, Parquet + raw JSONL exports, and reproducible manifests and provenance.
Converts multimodal inputs (text, image, audio, video) plus a question and options into calibrated probability distributions over choices. Built on Gemma 4 12B with a 30,000-question fine-tune, optimized for per-question decision classification and low-latency inference (Apache-2.0).
Converts natural-language SVG instructions into instance-aware six-item rubrics and uses a vision–language judge to score rendered SVGs item-by-item as dense RL rewards. Produces stronger human alignment and lifts benchmark rubric scores substantially on MMSVG datasets.
Scores candidate actions against a textual state using contrastive state/action embeddings for very fast zero-shot ranking and typed decision-making. Built as two small projection heads on frozen Qwen3-8B; fine-tunable as a verifier for agentic benchmarks.
Provides a unified data and evaluation suite for measuring gameplay capabilities across short, medium, and long temporal horizons. Includes an automated annotator, a 5,000-hour AAA gameplay dataset with temporally aligned frames, actions and multi-horizon instructions, and a reproducible offline + stepwise online benchmark.
Evaluates whether generative world models maintain consistent, controllable, and physically plausible simulated environments under exploration, interaction, and intervention. Introduces a six-level W1–W6 capability taxonomy across three tracks (video, spatial, embodied) with human A/B Arena and automated metrics to measure behavioral correctness.
Uses diffusion-model forking moments as a proxy for perceptual distance to automatically generate pointwise reference-grounded labels, enabling annotation-free training of reference-based image quality assessment metrics.
Provides WROP: a 1.5M-sample synthetic video corpus and a 300-question exam for training and evaluating object permanence and solidity in video world models. Includes 150 Blender task generators, a human Elo benchmark across 14 models, and a fine-tuned 16B continuation model (PWM-WROP).
Edits an LLM agent's internal task state and action continuations to remove unsupported assumptions and noisy plans, improving downstream decisions instead of reconstructing high-entropy tool outputs. Combines Action Judge, State Revision, and EditAct and shows consistent gains across benchmarks and agent backbones.
Provides 2,000 synthetic multiple-choice items designed for continuation log-likelihood scoring to evaluate small language models' Theory of Mind (social-cognitive) abilities; 40 constructs, balanced answer positions, and easy/medium difficulty.
Surveys memory mechanisms for autoregressive video generation, framing memory as persistent historical information that influences future generation. Organizes work by Forms, Functions, Operations, Learning, and Evaluation, and synthesizes challenges for long-horizon consistency and memory-aware learning.
Transforms user prompts into shot-level cinematic directions for text-to-video generation, using a 397B prompt-enhancer trained on 1.05M videos and SC-GRPO to preserve semantic consistency across shots; evaluated on WanPEval (5–30s) with large human-preference gains.