AIAIAny
  • Search
  • Collection
  • Category
  • Tag
  • Daily AI
AIAIAny

Discover the Best AI Resources

Curated essentials, no noise — just what matters

AIAIAny

Curated AI Resources for Everyone

[email protected]

Powered by airss.app

Product
  • Search
  • Collection
  • Category
  • Tag
Resources
  • Blog
Company
  • Privacy Policy
  • Terms of Service
  • Sitemap
Copyright © 2026 All Rights Reserved.

Contents

Hugging Face
AI Model·2026
Icon for item

Ternary Bonsai 2 27B (Bonsai 2 27B)

Prism ML

Compresses a 27B-class multimodal model into end-to-end ternary weights to run 27B reasoning on-device: 5.9–8.6 GB deployed footprint, 262K-token context, ~98.2% of FP16 benchmark performance; ships MLX and GGUF packs and runs on Apple MLX and CUDA.

#qwen#llm#multimodal#safetensors#gguf+11
Hugging Face
AI Model·2026
Icon for item

openjev

AlexWortega

Turns Qwen3.5 into a 3-way NLI cross-encoder (entailment/contradiction/neutral) for zero-shot reranking, grading, content guarding, or action selection. Provides a pretrained Qwen3.5-4B checkpoint, helper utilities (OpenJevCrossEncoder, LatentMLPHead), and optional 35B MoE latent heads for per-task scoring.

#qwen#transformers#nli#reranker#nlp+5
AI Video Papers·2026
Icon for item

Can MiniMax-H3 Reason About the Physical World? An Evaluation of Omni-Modal Generative Model

Haoyu Zhao, Zihao Zhao +11·Affiliation: National University of Singapore, Affiliation: Fudan University +1

Evaluates whether MiniMax-H3 can infer latent physical events from incomplete multimodal evidence and produce videos consistent with those inferences. Builds a 517-instance benchmark across four reasoning scenarios (multi-view, audio disambiguation, video continuation, audiovisual integration) and quantifies modality-specific failure modes.

#multimodal#video#evaluation#research#reasoning+3
Hugging Face
AI Dataset·2026
Icon for item

Typed Decisions

LocalLLaMA

Benchmark for typed probabilistic decisions: given one shared state, a model answers multiple typed questions at once and returns full probability distributions (noul/choice/score). Contains four workflows with train/test splits and soft gold labels from teacher samples, designed to evaluate accuracy, calibration, and latency trade-offs.

#benchmark#evaluation#huggingface#parquet#pandas+3
Hugging Face
AI Model·2026
Icon for item

Needle 3

Henry Ndubuaku, Karen Mosoyan +6·Cactus Compute, Inc.

Runs locally on constrained devices to turn text into guaranteed-parsable JSON tool calls, typed structured extractions, or sentence embeddings. Delivered as a single compact weights file (8–29 MB) with a laddered 2–20-layer design, low-bit quantisation and calibrated confidence scores for on-device apps.

#foundation-model#llm#embeddings#ai-inference#ai-deploy+7
Hugging Face
AI Model·2026
Icon for item

Bonsai 2 27B — GGUF

Prism ML

A 27B-class language model packaged in GGUF with end-to-end ternary weights for on-device or single-GPU llama.cpp inference; reduces FP16 footprint to ~5.9–7.2 GB while retaining ~98% of baseline performance and supporting up to 262K tokens.

#gguf#llama.cpp#qwen#llm#multimodal+8
Hugging Face
AI Model·2026
Icon for item

Xing4.0-29B-A4B

XingChen-AGI, China Telecom Artificial Intelligence Technology Co., Ltd.

A 29B-parameter mixture-of-experts LLM for long-context reasoning and agent-style workflows, with native 256K context and Ascend NPU co-optimizations. Compatible with Transformers/vLLM ecosystems; suitable for long-horizon agents and domain fine-tuning.

#llm#moe#transformers#safetensors#huggingface+6
Hugging Face
AI Dataset·2026
Icon for item

Granary-v2

NVIDIA Corporation

Provides transcripts, translations, and multi-task text labels for speech across 48 languages and about 463,000 hours. The release contains manifests only; audio must be obtained from the original data providers.

#multilingual#ASR#translation#audio#speech+3
MLOps·2026
Icon for item

RayOrch: Programming and Executing Lineage-Controlled Multi-Grain Dataflows for Foundation-Model Data Preparation

Xiaochen Ma, Zimo Meng +14

Provides a programming model and distributed runtime that preserves parent–child lineage and ordered variable-cardinality expansions for 1→M→1 dataflow pipelines, enabling completion-driven cross-input GPU batching and ordered gathers for foundation-model data preparation. Demonstrates multi-GPU scaling speedups and lower end-to-end time versus Ray Data and Daft.

#foundation-model#mlops#training-data#ai-workflow#gpu+3
Hugging Face
AI Deploy·2026
Icon for item

Parallel Constrained Decoding for Apple Silicon (harshatheg/Qwen-2.5-1B-RLCD)

harshatheg

Evaluates multi-field JSON schemas in parallel to extract boolean or categorical field values from text, producing guaranteed-valid JSON and per-field calibrated confidences. Uses KV-cache broadcasting, sub-vocabulary logit slicing and token-tree disambiguation to cut latency (5.6x–7.0x on M4 Max) versus autoregressive decoding; requires Apple Silicon and MLX.

#qwen#json#benchmarks#ai-inference#ai-serving+4
Reinforcement Learning Papers·2026
Icon for item

ActionPiece: Rethinking Action Tokenization for Autoregressive Vision-Language-Action Models

Shijie Lian, Bin Yu +6

Introduces physical rank consistency (PRC) and ActionPiece, a learned action tokenizer that preserves local physical relationships via joint supervision of representation learning and quantization, improving autoregressive vision-language-action policy performance across multiple benchmarks.

#robotics#embodied-ai#vision#rl#multimodal+4
AI Agent Papers·2026
Icon for item

ScienceIDE: Turning World's Scientific Codebase into Agent Learnable Environments

Hejia Geng, Zesen Huang +43

Transforms scientific code repositories into executable, agent-learnable environments that support task generation, execution, and scientific verification. Agent-guided repository transformation produces verified interaction trajectories used to train the PhAI-IDE model family. Intended for research on agent learning, scientific-code repair, and training RL/SFT models.

#ai-agent#agent-skills#IDE#science#code+7
  • Previous
  • 1
  • More pages
  • 217
  • 218
  • 219
  • More pages
  • 260
  • Next