AI Agent Papers2026
Ruixun Liu, Yuxuan Wang +11School of Intelligence Science and Technology, Peking University, State Key Laboratory of General Artificial Intelligence, Peking University +2
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.
AI Image2026
Provides GGUF-quantized builds of Qwen-Image-2.1 for local text-to-image generation and ComfyUI workflows; includes multiple quantizations (Q4_K_M recommended), companion text encoders (BF16/Int8) and a VAE, and ships without a built-in safety filter.
AI Model2026
Generates a single, ready-to-send short message (email, text, or note) tuned to sound human; a 27B fine-tuned LLM with open Apache-2.0 weights, optimized to return one concise draft rather than multiple options or explanatory preamble.
AI Model2026
Provides quantized Qwen-Image-2.1-Turbo weights for text-to-image generation across GGUF, Safetensors, and MLX formats. It retains the model’s 8-step Turbo workflow, with options for different hardware and runtimes.
AI Model2026
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.
AI Image2026
Provides multiple quantized releases (GGUF, safetensors, MLX) of Qwen-Image-2.1 for local text-to-image generation; includes GPU- and Apple-Silicon–optimized quantizations, companion text encoders/VAEs, and recommended ComfyUI configurations.
Hangyu Ran, Yuhao Zheng +3Ant Group, The Hong Kong University of Science and Technology (Guangzhou) +2
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.
AI Model2026
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.
AI Model2026
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.
AI Model2026
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.
AI Dataset2026
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.
AI Image2026
A distilled LoRA adapter for Qwen-Image-2.1 that runs text-to-image generation and instruction-driven image editing in a few transformer passes (shipped as a 6-step r256 LoRA). Samples with a fixed sigma schedule, no classifier-free guidance; non-commercial research license.