Tag

OmniEcho: Audio-Visual Spatial Understanding for Omni-Modal Embodied Agents

Provides a unified benchmark and a spatially aware omni-modal model for spatial audio-visual reasoning in embodied agents — OmniEchoBench (197 scenes, 2,972 QA pairs; 900 FOA-based navigation tasks) plus OmniEcho, which adds an FOA spatial encoder to a pretrained semantic audio pathway to enable spatial QA and sound-guided navigation.

Qwen-Image-2.1 Text Encoder (Heretic) — GGUF

GGUF-format, quantized (Q4_K_M) and refusal-ablated (Heretic) text encoder build for Qwen-Image-2.1, supplied with a separate f16 vision mmproj so the full multimodal pipeline runs on llama.cpp/ComfyUI (Mac/non-CUDA friendly); multiple formats and quantizations included.

RULER: Instance-aware Rubric Rewards for SVG Generation

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.

MiMo-V2.6-Flash-RL

A sparse-MoE multimodal LLM fine-tuned with large-scale mixed reinforcement learning, supporting text/image/video/audio and a 1M-token context window; designed for long-horizon agentic tasks, coding and visual reasoning with groupwise grading and on-policy distillation.

LensVLM-9B

Scans long documents rendered as compressed page-images, locates relevant pages, and selectively expands only those pages to full text for question answering; built on Qwen3.5-9B, supports 5x/10x/15x compression and is released under Apple’s research-only model license.

MiMo-V2.6-Pro-RL

Open-weights multimodal LLM checkpoint designed for 1M-token long-context agent runs that combines large-scale on-policy RL with groupwise grading for iterative self-improvement. Key traits: sparse MoE backbone (≈1.02T total / 42B active), text-only output with image/video/audio inputs, MIT-licensed weights on HuggingFace—suited for long-horizon agents and research at significant infra cost.

GameHorizon Suite: Multi-Horizon Data and Evaluation in Gameplay

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.

HappyWorld-Bench

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.

MiMo-V2.6-Distill-Qwen-9B

A 9B agentic multimodal SFT checkpoint distilled from Qwen3.5-9B for coding, general agent tasks, visual coding and cybersecurity. Provided by Xiaomi MiMo as a research seed (77.4B-token SFT mix) to bootstrap agentic RL and tool-use experiments.

Honey-Data-V2

A multimodal supervised fine‑tuning corpus for training MLLMs: 44.3M samples (100.3M QA pairs) over 19.7M image groups, annotated with short/long chain‑of‑thought and produced by rerunning the HoneyPipe curation pipeline with multi‑model rollouts and verifications.

GAE: Learning a Geometry-Native Latent Space for 3D-Consistent World Generation

Compresses a geometry-foundation model’s multi-level features into a compact latent that decodes jointly to RGB, depth, cameras and point maps — enabling a conditional flow to generate 3D-consistent video and novel views with measurably improved coherence.

Training Object Permanence in World Models

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).