Tag
Explore by tags
Large-scale training corpus for knowledge- and reasoning-intensive video understanding: 315K video reasoning examples over 145K CC-licensed expert-domain videos, with human-in-the-loop chain-of-thought rationales to strengthen post-training for video reasoning. ([arxiv.org](https://arxiv.org/abs/2606.05259))
Provides a GGUF-ready QAT (Q4_0) quantized build of Gemma 4 12B that preserves near-bfloat16 quality while reducing memory footprint for local inference; compatible with Transformers-based and GGUF runtimes.
Decouples perception and reasoning for hours-long videos by streaming inputs into a three-tier Hierarchical Graph Memory and using an agentic Observation–Reason–Action retrieval loop; reduces reasoning context to ~2% of full video while improving benchmark accuracy.
GGUF-format QAT (quantization-aware training) build of Gemma 4 12B that reduces memory needs for local or lightweight inference while preserving near bfloat16 quality. Ready for any-to-any conversational pipelines and ecosystem deployment.
Provides a comprehensive benchmark for instruction-based audio editing across seven audio modalities and eight operation types, with 2,000 high-fidelity samples and a rubric that decomposes tasks into 17,741 verifiable criteria for multi-dimensional evaluation.
Simulates egocentric, embodied human–world interactions and enables customizable, self-evolving local scenes by defining anchor views and text-driven evolution. Uses exogenous viewpoints and full-body motion supervision to improve spatial grounding and interaction consistency.
Benchmark for long-horizon computer-use agents that must orchestrate GUI, CLI, and code operations within single trajectories across 114 real-world tasks. Evaluated on a real Ubuntu desktop and paired with a trajectory-aware judge that inspects deliverables, artifacts, and action traces—revealing a top PassRate of ~41.2%.
Models visual preference as distributions over rubric scores and introduces Z-Reward, a teacher–student framework that decouples reasoning-heavy judgment (teacher trained with GDSO) from efficient deployment (student via RISD). Demonstrates higher human-preference accuracy and works as a differentiable reward for text-to-image optimization.
Adds discrete audio tokens and an audio encoder to a 30B MoE text LLM so a single model can perform ASR, speech translation, TTS, text-to-audio and speech-to-speech while preserving text reasoning and long-context capabilities; supports thinking/instruct modes and up to 1M-token context.
A benchmark that evaluates interactive spatial reasoning for multimodal agents in realistic tasks. It unifies eight heterogeneous simulators under a simulator-agnostic protocol, provides 760 human-annotated tasks with vision-only partial observability, and uses text-based actions plus terminal-state verification to measure task success.
Turns raw datasets into verifiable multimodal news features via a multi-agent newsroom pipeline. Key innovations: (1) an Inspector that links each claim to data/code/external references for re-execution and audit; (2) multimodal asset generation (interactive maps, audio, visuals) tailored to the story.
End-to-end framework for controlled character animation that transfers motion from driving videos to reference characters without intermediate pose or background representations. Introduces the MotionPair‑60K end-to-end motion-transfer dataset, in‑context mask conditioning and mode‑specific RoPE for task unification, plus Bias‑Aware DPO to mitigate synthetic-detail errors.