Stores speaker-labeled verbatim messages alongside derived person- and group-level states to improve attribution and long-term memory in multi-party dialogues. Proposes a dual-track memory and a speaker-conditioned Writer trained with SpeakerLevenshtein and GRPO; yields consistent gains on multiple dialogue memory benchmarks.
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).
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.
Turns a context, a question, and 2–20 candidate answers into a single chosen option for classification, routing, ordered scores, and Boolean decisions. Built on mmBERT-small with a 144.3M-parameter decision head, runs on CPU with up to 8,192 combined tokens; FP32 weights occupy 550.5 MiB and are Apache‑2.0 licensed.
Performs schema-driven, low-latency classification and structured decision-making over English text. Supports multi-head scoring, constrained joint decoding with confidence/feasibility metadata, span extraction, and local CPU/GPU deployment via the gliner2 runtime.
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.
Evaluates multimodal memory in large audio language models by testing four acoustic evidence types and four memory operations across multi-session spoken histories, stratified across 8K–64K token context budgets.
Provides 130,000 typed RAG claim-verification decisions that pair source-derived reference labels with jev-1.13.0 model predictions. Includes sentence/span grounding, hallucination-type presence, whole-response grounding and response-quality decisions with retained provenance. Suited for grounding error analysis, prototype evidence-checkers and confidence-threshold studies; license: other.
Provides 7,366 recorded agent trajectories from H Company’s Holo4 benchmark runs, with step-level reasoning, actions, tool results, token usage and screenshots for replay and analysis. Bundled as JSON and image files for per-trajectory inspection and automated replay; released under Apache 2.0.
Uses 360° panoramic observations to improve vision-and-language navigation by predicting longer action sequences, confidence-guided execution, and combined semantic–geometric panorama features; yields large SR gains on R2R-CE and RxR-CE Val-Unseen.
Co-evolves candidate solutions and web-search queries to help LLM-driven evolutionary discovery, using a retrieval gate plus bilevel inner/outer loops that refine queries, rank documents by predicted solution value, and generate evaluated candidates.
Predicts compact 'prospective tokens' that summarize upcoming information needs and uses them to select a small set of past frames for conditioning long-horizon video generation, improving long-range consistency, visual quality, and action alignment while remaining plug-and-play across diverse generators.