#Image generation

D3D: Decoupled Diffusion Drafting Asynchronous Speculative Decoding Technology

D3D breaks the dependency on the hidden states of the target model through an independent diffuser, achieving asynchronous drafting and verification. In seven benchmarks, D3D combined with block denoising and auxiliary autoregressive supervision increases the average decoding speed of Qwen3-8B and Qwen3-32B by 5.00 times and 5.71 times respectively, outperforming DFlash (4.03 times and 3.67 times), and reaching 7.48 times acceleration on GSM8K. The code, model checkpoints, and benchmark scripts are open source.

Epoch Capabilities Index update adopts Bayesian model methodology

Epoch Capabilities Index (ECI) update adopts Bayesian model methodology, providing more reliable estimates of model capability uncertainty and the probability of comparing capabilities between models. The new method is based on four-parameter logistic (4PL) item response theory (IRT), using Claude 3.5 Sonnet (ECI 130) and GPT-5 (ECI 150) as anchor models, and achieves cross-temporal consistency through linear transformations to fix parameter location and scale.

Xiaomi Smart Camera 4 Pro supports one-click WeChat calls, with a direct price drop of 242 yuan after national subsidy

Xiaomi Smart Camera 4 Pro's launch price was 329 yuan, reduced to 252 yuan today after JD.com's government subsidy. It now supports physical call buttons for one-click WeChat calls, enabling two-way calls between the camera and WeChat on smartphones or the Mi Home app.

FactEmbed: Enhancing Composed Image Retrieval Performance through Decomposed Embeddings

FactEmbed decouples query understanding from embedding construction, simulating pre-retrieval visual modifications using decomposed latent vectors, significantly improving performance in composed image retrieval. The method outperforms existing technologies in the CIR benchmark, optimizing decomposed representations through intermediate target imagination, and achieving efficient inference using global-level embeddings and mean pooling of latent vectors.

Amazon Bedrock launches Kimi K3 inference service in India

Amazon Bedrock now supports inference for Kimi K3 within India, meeting strict data localization requirements. Customer Ultrahuman enables their AI health assistant to handle over 14,000 daily conversations through API calls, while keeping health data within AWS, reducing costs by 80% and improving multi-turn conversation speed by 85%.

Reviso: Not All Visual Evidence Should Be Given Equal Attention in Video Caption Generation

Reviso is an intelligent video subtitle framework that prioritizes key visual evidence through hierarchical planning and active perception learning, enhancing subtitle quality and downstream video understanding capabilities. Multimodal large language models (MLLMs) generated video subtitles may overemphasize minor details while ignoring important context and key events.

uni-robot-agent: Open-source robot use agent unified framework achieves zero-shot operation breakthrough

The uni-robot-agent framework enables open-source weight robots to surpass proprietary models using agents in zero-shot operation, with its onboard Qwen3.8-Flash-Next scoring 31.39 in the RoboDojo evaluation, exceeding GPT-6 Astra-RoboProbe's 28.97 score and numerous VLA/WAM baselines, and performing excellently in 19 real tasks. Analysis indicates that effective robot use requires combining four general capabilities, suggesting future training should synergistically develop these capabilities.

WeFair: Fidelity-Aware Alignment Technology Based on Human Feedback, Used for Personalized Query Rewriting in Short Video Search

WeFair improves personalized query rewriting through a human feedback phase (demonstration, preference, and validation) based on fidelity perception, reducing intent drift and enhancing search effectiveness on short video platforms. This technology addresses the need for compact query rewriters in short video search, recovering user personalized intent from ambiguous queries under strict latency constraints. WeFair-2B outperforms strong rewriting baselines in overall accuracy and intent preservation in offline experiments, while online A/B testing shows a relative increase of 2.593% in effective video play rate and a relative decrease of 2.350% in query rewriting rate.

Venus-DefakerOne2: A broader visual forensics base model

Venus-DefakerOne2 extends detection to multiple spoofing forms and media types through alternating LoRA and full-parameter fine-tuning, as well as entropy-based test adaptive, achieving SOTA performance in six benchmark tests including DeepFake faces (96.7%), AI-generated images (93.3%), and tampered documents (87.6%), significantly outperforming expert models and predecessor DefakerOne.

LARC framework implements continuous space latent reasoning to unify multimodal models

The LARC framework alleviates the bottleneck of applying linguistic reasoning in image generation for unified multimodal models by reasoning on continuous hidden states, improving generation quality and achieving test-time scaling without discrete token bottlenecks. The framework includes two stages: curriculum supervised fine-tuning (SFT) and information gain reinforcement learning (RL). In text-to-image generation benchmark tests, LARC improved performance by 7% over BAGEL on GenEval and demonstrated clear test-time scaling behavior.

HiFOR: A hierarchical predictive framework for visual language action models

HiFOR guides action generation by hierarchically predicting future states and retrieving relevant future information, enhancing robotic manipulation capabilities. The framework jointly predicts short-term state evolution, semantic milestones, and final goal states through hierarchical dependency masks (HDM), establishing cross-temporal dependency relationships; structured perception latent world modeling organizes future potential representations along temporal, perspective, and spatial dimensions, promoting fine-grained retrieval; action-guided decomposition world retrieval adaptively retrieves relevant future information based on action representations during the denoising process, providing targeted guidance for action generation.

2009 Sony Walkman runs ESP-NOW communication with native WiFi chip

FrameForge: Utilize video base model priors for unified image generation

FrameForge achieves adaptive conditional image generation by modeling the priors of pre-trained video models through dynamic time experts and intermediate reasoning paths, achieving superior performance to comparative methods on DreamBench, COCO2017, and GEdit-Bench.

Kimi K3.1 Pro Released: Open-Weight Multimodal AI Model

Kimi K3.1 Pro is an open-source multimodal AI model by Moonshot AI, with 2.8T parameters, 104B activation parameters, and a context window of 1M tokens, demonstrating excellent performance in areas such as coding, 3D creation, and financial research. Compared to Kimi K3, it adopts Gated DSA layers to improve long text processing efficiency and has outperformed competitors like Claude Fable 5.1 and GPT-6 Astra in benchmarks such as Terminal-Bench 4.0.

HairDeck: Generate animation-ready cartoon hairstyle cards from a single image.

HairDeck uses diffusion Transformer to generate cartoon hairstyle cards and spring bone animations from a single image, with accuracy and speed superior to existing methods. It treats hairstyles as artist-defined original sets and uses diffusion Transformer to denoise and generate each card as a single token hairstyle.