Skip to content
Live
#Image generation
Oct 23Fri
  2. Hugging Face Daily Papers65

    Different tasks, different time steps: temporal task-aware quantization for diffusion language models T²Quant

    T²Quant framework predicts accuracy sensitivity through minimal unlabeled calibration prompts, allocating activation precision within a fixed bit-width budget, improving existing quantization methods by 6.7 percentage points across 3 diffusion language models and 6 benchmark tests without increasing average accuracy budget.

  3. Hugging Face Daily Papers65

    RLSplat: A feedforward 3D Gaussian splatting method with linear resource budget control.

    RLSplat achieves linear reduction in latency, memory, and model size for feedforward 3D Gaussian splatting by assigning Gaussians through regional allocation and using local attention decoding. In zero-shot evaluation, RLSplat outperforms previous budget-controlled methods under all budgets, surpassing the strongest baseline even with a 4x reduction in Gaussian count, and achieves a 4.1x speedup and a 9.6x reduction in peak memory at low budgets.

  4. The Verge · AI75

    Canva releases its first AI image model Canva Craft, planning and designing before generation

    Canva releases its first AI image model Canva Craft, planning and designing before generation; this model uses a two-stage architecture, supports 2K resolution and over 30 aspect ratios, can be used for social media and marketing content creation, and has now been launched globally.

    Same story · 3 outlets

    How the accounts differ:TechCrunch states the model supports 30 aspect ratios; The Verge mentions 'over 30' aspect ratios; The Decoder specifies 30+ aspect ratios.

  5. TechCrunch · AI62

    Design platform Canva launches its first image generation model, Canva Craft

    Canva releases its first image generation model, Canva Craft, which works in two stages: first, it parses user prompts and creates a plan containing spatial relationships of elements, relative proportions, visual hierarchy, and text generation information; second, it generates images with the highest resolution of 2K and supports 30 different aspect ratios.

    Same story · 3 outlets

    How the accounts differ:TechCrunch states the model supports 30 aspect ratios; The Verge mentions 'over 30' aspect ratios; The Decoder specifies 30+ aspect ratios.

  6. Hugging Face Blog

    Hugging Face releases OlmoEarth v1.3: Global satellite embedding model achieves new milestones

    Hugging Face releases OlmoEarth v1.3, a satellite embedding model, offering global pre-computed embeddings (10m resolution, 64 and 128 dimensions), available to users without login or technical knowledge. The model performs best in 27 evaluations, with 128-dimensional embeddings scoring highest in 20 evaluations and 64-dimensional embeddings leading in 18. Training costs are reduced by 53% compared to v1.2 and 18% compared to v1, with corresponding reductions in carbon emissions. Weights, data, and code are all open source.

Oct 22Thu
  1. Hugging Face Daily Papers65

    Future Chunk Prediction (FCP) enhances the physical plausibility of autoregressive video generation.

    Future Chunk Prediction (FCP) improves autoregressive video diffusion models by introducing future chunk supervision, generating videos that better adhere to physical laws and reducing training costs. This method, under the teacher forcing framework, predicts temporally separated video chunks without relying on intermediate visual context, directly utilizing training videos for supervision, requiring no additional pre-trained visual encoder, and not altering autoregressive inference.

  7. Hugging Face Daily Papers65

    Can SpatialScout's VLM agents proactively explore and map 3D scenes?

    SpatialScout evaluated the performance of VLM agents in active 3D object mapping, revealing significant flaws in their precision metric map construction. Claude Opus 5.5 scored an average overlap of 41.71% in this benchmark test, with 47.23% of target IoU below 0.5 and only 3.25% exceeding 0.9, showing a significant gap between recovering rough layouts and building complete, precise metric maps.

Oct 21Wed
  1. AWS Machine Learning Blog58

    vLLM enhances the TTFT performance of multi-round agent workloads through bidirectional KV transmission.

    vLLM's bidirectional KV transmission mechanism reduces redundant calculations by allowing the decoding node to return previously computed KV cache to the pre-filled node in subsequent dialogue turns. In multi-round benchmark tests on AWS EC2 P5en instances, it improved the TTFT of Qwen3-32B by 1.6x and zai-org/GLM-5-FP8 by 3.3x. This feature is implemented by extending the NIXL KV connector and utilizing a KV cache-aware router to coordinate KV reuse across dialogue turns.

  3. AWS Machine Learning Blog34

    Building an AI agent semantic layer on AWS using Strategy Mosaic and Amazon Bedrock AgentCore.

    Strategy Mosaic, as a semantic layer, models C360 domains on Amazon Redshift and Amazon Aurora without ETL using two linked models. Its metric syntax captures the business definition of agent reasoning and exposes the model to AgentCore-hosted Strands agents via the Mosaic MCP server, supporting user identity propagation to achieve end-to-end row-level and object-level security.

  6. MIT Technology Review · AI58

    Goodfire researcher Nick Cammarata releases disruptive blog: The nature of neural networks might be easier to understand than previously thought

    Goodfire researcher Nick Cammarata published a blog post stating that LLMs might be easier to understand than previously thought, causing shockwaves in the AI world. Cammarata believes that the mechanisms of neural networks may not be as difficult to decipher as previously thought, a view that is particularly noteworthy against the backdrop of frequent LLM proxy out-of-control incidents.

  8. The Verge · AI70

    Adobe Lightroom mobile fixes photo eye-blink issues with a single AI tap

    Adobe Lightroom mobile app has added AI features, allowing users to fix closed eyes in photos with a single click. This feature uses generative AI to intelligently replace closed eyes with open ones, referencing other images in the user's Lightroom library to ensure the matching of eye color, size, and shape. Free users can use this feature twice for free, after which they will be prompted to subscribe to the Adobe Creative Cloud plan.

  9. vLLM Blog

    Ant Group and the vLLM community open-source Humming: A general-purpose high-performance quantized inference kernel library

    Ant Group and the vLLM community open-source Humming, a high-performance quantized inference kernel library. Humming supports NVIDIA GPUs starting from the Turing architecture and CUDA-compatible devices like the T-Head Zhenwu 810E, providing extensive quantization support covering various integer and floating-point types, bit widths, and scaling schemes. It significantly outperforms existing implementations such as vLLM Marlin, FlashInfer, and DeepGEMM on multiple representative workloads.

  12. a16z News70

    OpenAI has acquired Orchestra Bio, but hardware design remains a challenge for AI.

    OpenAI has acquired Orchestra Bio. Current cutting-edge models like GPT-6 Astra, Fable 5.1, and Grok 4.6 can generate CAD, design PCBs, and describe assembly, but hardware design benchmarks like CAD Arena, EE Bench, and LuxoBench show that improvements are still needed. AI in hardware design faces the lossy problem of the interface between the digital and physical worlds, even if it can generate designs, a lot of work is still required.

Oct 20Tue
  4. MIT News · AI70

    Teaching AI to recognize symmetry could enhance the reliability of prenatal diagnosis.

    The E(3)-Pose deep learning model developed by institutions such as MIT embeds the principle of left-right symmetry of the fetal head, allowing it to capture high-resolution images during motion in prenatal MRI scans, assisting doctors in more reliably diagnosing brain abnormalities. The model integrates physical principles into the neural network architecture, effectively addressing the issue of inconsistent slice angles and coverage gaps in images caused by fetal movement. Its application could potentially be extended to other difficult-to-image anatomical structures and the field of autonomous driving, and it is currently being optimized to support imaging of early fetuses (second trimester).

Oct 19Mon
Oct 18Sun
  1. MIT News · AI75

    MIT researchers develop multimodal AI model to provide 'clear' view for materials science

    The multimodal AI model developed by MIT researchers combines 3D atomic structures with natural language descriptions, generating rich structural language descriptions from experimental research papers and first-principles calculation databases, helping AI learn the key properties of materials. The model outperforms text-only models in identifying solid-state lithium-ion battery electrolyte materials and can learn geometric structure representations, providing new research tools for materials science.

Oct 17Sat
  1. Google Research

    Google Research explores combining AI agents with biological reality to build autonomous wet labs.

    Google Research releases the VERID framework, enabling AI agents to run in physics-based, safe, and resource-efficient experiments; demonstrates closed-loop intelligent agent scientific discovery on adapter and de novo protein design prototypes; through three rounds of design-test-iterate cycles, AI-driven rational and de novo design will increase confirmed target hit rates to 33.5% and 42.1% on myoglobin and α-thrombin, respectively.

Oct 16Fri