推理成本

斯坦福大學與加州大學伯克利分校的研究者發佈了 TokenGate，這是一個可插入現有大語言模型的學習式 Token 剪枝模塊。它通過一個小型 MLP 門控為輸入文檔中的每個 Token 打分並只保留得分最高的一部分，從而縮短長上下文預填充的首 Token 延遲（TTFT）1.4 至 11.3 倍，峯值顯存降低 1.5 至 3.4 倍，且不損失準確率。研究在 Qwen3-1.7B 與混合注意力的 Qwen3.5-2B 上驗證，代碼與檢查點以 Apache-2.0 許可開源。

Kyutai 推出 CADRE 系列開源因果擴散視頻自編碼器，專為交互式世界模型設計。基於 CADRE 的世界模型在單張 H100 上以 20 fps 運行，動作響應延遲低於 230 毫秒。該系列包含 7 個自編碼器，每個約 4.76 億可訓練參數，外加凍結的 8600 萬參數 DINOv3 ViT-B/16。在多數基準測試中，CADRE 在延遲-質量前沿上表現優異，駕駛場景 FVD 降至 162.6，遠低於 Wan 2.2 的 599.7。權重採用 CC BY-NC 4.0 非商業許可，代碼為 MIT。

Meta 研究團隊（論文作者含 Chao-Yeh Chen、Tiffany Chen、Umar Iqbal 等項目負責人）發佈 EgoHand，一個面向第一人稱（自我中心）視頻的單目三維手部重建模型。該模型在 1400 萬張圖像上訓練，數據集融合了合成數據、野外視頻與多相機動作捕捉；採用 SOMA-Hand 參數化表示，並以 Transformer 編碼器處理 2D 手部裁剪圖，同時引入相機線索與輔助 2D 分支以提升幾何一致性和圖像對齊。在 HOT3D、ARCTIC 與 H2O 上的零樣本評測顯示其泛化能力突出，關節位置、根節點平移與加速度誤差均低於對比基線，推理延遲約 9.69 毫秒；盲測用户偏好研究也顯示其重建手部姿態優於 Apple EgoDex 與 Ropedia Xperience-10M。模型與源碼以 OpenMDW 許可證開放，允許免費商用。

AWS 博文介紹瞭如何在 Amazon SageMaker AI 上託管 Kokoro-82M 文本轉語音模型，並將智能體生成的每一句話在產生時立即流式送入合成，從而讓語音播放在完整回覆生成完畢之前就開始。文章還比較了通過 SSE 傳輸 base64 音頻與在同一雙向會話中複用原始二進制加 JSON 控制幀兩種方案的實際成本與取捨。

Liquid AI 推出專為實時請求路徑設計的推理引擎 RIPL，可在單張 B200 上以 50 毫秒以內完成端到端生成。官方基準顯示，其 p95 延遲比運行在 vLLM 上的 Qwen3.5 低 5.6 至 28.4 倍，Shopify 已將其用於生產搜索場景。不過 RIPL 僅面向企業客户、閉源，且所有數據均為自報。

AWS 博客介紹了一種以實測數據替代猜測的自動擴縮容方法：在 Amazon SageMaker AI 實時端點上以自定義容器部署 Kokoro-82M 文本轉語音模型，通過對線上端點測量 Q_max（單實例在 SLO 內可承受的最大併發）和 T_total（端到端擴容耗時），再用算術推導出擴容閾值、縮容閾值以及兩段冷卻時間，從而避免因閾值設定偏保守造成 GPU 閒置浪費、或偏激進導致延遲 SLO 被擊穿卻不被察覺的問題。

NVIDIA 通過博客展示歐洲零售企業如何藉助開放模型與物理智能改造業務：Shopify 後訓練 Nemotron 模型將推理成本降低 90%、響應速度提升 7 倍；Zooplus 產品發現原型實現 86% 搜索準確率；Otto Group 在德國最大履約中心用 Omniverse 數字孿生在仿真中設計並優化倉庫運營；Nebius 在 GTC 柏林展示三套零售藍圖。

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Google, Red Hat and IBM released llm-d 1.0, an open-source Kubernetes-native stack for distributed LLM inference. It adds multi-tenant flow control, zero-downtime upgrades and agent-aware routing across vLLM, SGLang, TPUs and GPUs. The post Google Cloud Ships llm-d 1.0 With Cache-Aware Routing for TPU and GPU Fleets appeared first on MarkTechPost.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2610.26903v1 Announce Type: new Abstract: Action-conditioned world models support planning and policy evaluation by predicting future states. However, learning an accurate one-step predictor can require substantial training computation. We introduce Beckmann World Models (BWM), which learn a direct map from noise, visual history, and actions to future frames without a pretrained generative teacher. We adapt the terminal-map conservation law of Beckmann Transport Models to action-conditioned video prediction, training directly from noise-data pairs without conditional populations of generated samples required by DriftWorld. However, transport consistency on interpolated inputs does not ensure accurate prediction from the pure noise used at inference. We ad…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2610.26937v1 Announce Type: new Abstract: Large clinical language models often require multi-GPU infrastructure, limiting local deployment. We introduce CERTA, a decision-level statistical certificate that determines when a quantized model may substitute for its native BF16 reference and escalates decisions that cannot be certified to it. Across eleven instruction-tuned models, both general-purpose and domain-adapted, from three families (7-72B), we evaluated 2,500 clinical-verification decisions from de-identified patient contexts (2,484 patients), with patient-disjoint calibration and testing. In the higher-power operational analysis, round-to-nearest 8-bit quantization at BF16 storage served 99.8-100% of held-out decisions across all eleven models; for…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2610.27000v1 Announce Type: new Abstract: Deep generative models provide an effective modern solution to alleviating the problem of data scarcity by synthesizing realistic time series. However, despite the considerable progress achieved by existing deep time series generators, two key challenges remain: (1) learning hierarchical representations for heterogeneous temporal patterns; and (2) coordinating the generation process of heterogeneous temporal dynamics. To address these key bottlenecks, in this work, we propose ORBIT, a unified deep generative framework for time series. Specifically, we develop two key components: the Frequency-Hierarchical VQ-VAE (FH-VQ-VAE) and the Frequency-Band Autoregressive Transformer (FBAR). The former learns hierarchical re…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2610.26948v1 Announce Type: new Abstract: Conversational recommender systems have recently adopted vision-language models to match user dialogue intents with multimodal product information. However, extending these methods to many product domains faces a dilemma: deploying a separately adapted VLM per domain scales cost linearly with the number of domains and requires routing each dialogue to the right model, while naively merging all domains into a single VLM degrades accuracy because product characteristics vary widely across categories. We propose LightCRS, a lightweight, query-conditioned framework for unified multi-domain multimodal conversational recommendation. LightCRS precomputes multimodal product representations once offline with frozen encoder…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2610.26913v1 Announce Type: new Abstract: The adoption of Large Language Models for radiology report structuring has been largely dominated by either proprietary cloud-based models or large open models requiring high-end GPUs for deployment, which is a critical bottleneck for clinical adoption in radiology workflows that demand data privacy and offline operation. To address this, we present MedPAO-Assist, an edge-deployable agentic framework that generates structured radiology reports directly from radiologist dictation and voice commands, requiring only $\approx3.3$ GB peak RAM and achieving an average end-to-end latency of $\approx31$ seconds on a standard laptop CPU through an asynchronous, multi-threaded execution pipeline. The system currently suppor…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2610.26904v1 Announce Type: new Abstract: Recent studies have proposed reinforcement learning with verifiable rewards (RLVR) methods that enable LLMs to generate high-quality RTL circuits from natural-language specifications. Existing approaches optimize circuit PPA (Power, Performance, Area) by aggregating multiple objectives into a single scalar reward, making it difficult to simultaneously generate diverse Pareto-optimal solutions across different trade-offs such as low power, low latency, and small area. However, in practical design, the relative importance of each objective varies depending on product requirements and design constraints; thus, obtaining a diverse and high-quality candidate set is beneficial in that designers can choose a preferred tr…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Learn how i14 trained and served Laplace 3B, a linear attention model, on AWS Trainium2 using native PyTorch. Its recurrent state stays fixed at 29.5 MB per sequence regardless of context length, avoiding the growing key-value cache of transformer models and keeping serving memory predictable.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯： My latest vibe coded game experiment is a Command & Conquer style RTS (Real Time Strategy) game called Battle Drones (play it here). Unlike my previous experiments, this one is actually fun to play. I'm somewhat embarrassed to admit that I got there by telling Claude to "Make it a LOT more fun". It also supports multiplayer between nearby devices using audio to synchronize game state! Here's what I've built so far, and some of the things I learned along the way. Battle Drones How I built this v1: the initial prototype v2: full sprites v3: varied terrain v4: the fun update v5: Battle Drones goes 3D v8: Archipelago v10: Goliath, and agent battles Agent battles v11: Random Maps v12: Multiplayer via sound Some thoughts Battle Drones My initial goal was to build an…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Deepgram worked with the AWS Forward Deployed Engineering team to port its Nova-3 speech-to-text model to AWS Trainium2 for offline batch inference. This post covers porting to the AWS Neuron stack, kernel-level tuning, a data-parallel Rust runtime, and the throughput and cost results on batch transcription.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：vLLM's prefill-decode disaggregation splits LLM inference across engine instances but must transfer the KV cache between them. This post introduces a push-based NIXL connector that moves transfer coordination off the critical path, delivering up to 3x better TTFT and 30% better TPOT in benchmarks on Amazon EC2 P5en instances with AWS EFA.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Multi-turn agentic workloads reprocess growing conversation context each turn, driving up latency. See how bi-directional KV cache transfer lets prefill and decode nodes reuse previously computed context across turns, cutting time to first token by up to 1.6x for Qwen3-32B and 3.3x for GLM-5-FP8 on Amazon EC2 P5en instances with EFA.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：This white paper explains how edge AI and physical AI help cities move beyond passive monitoring. It shows how urban infrastructure can sense, reason, and act on real-time conditions across public safety, mobility, and infrastructure management. What you will learn about: How the shift from smart cities to cognitive cities depends on infrastructure that reasons and acts, rather than infrastructure that only monitors. Why edge AI supports low-latency decisions, keeps sensitive data within city boundaries, and reduces dependency on centralized cloud infrastructure. How computer vision, multimodal sensing, and generative and agentic systems work together to support public safety, mobility, and infrastructure applications. How a tiered edge architecture assigns mon…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2610.22509v1 Announce Type: new Abstract: Reliable 3D person detection is important for rescue robotics to give first responders situational awareness. Yet most multimodal 3D detection research targets automotive scenarios in which pedestrians mostly appear in a narrow range of upright, near-road poses. It is therefore unclear how much of the reported performance transfers to rescue settings, as a person may be lying, partially occluded, or in unstructured indoor and outdoor environments. To investigate this gap, we introduce TriSAR-3D, a multimodal person detection dataset recorded with a high-resolution 128-channel LiDAR, an RGB camera, and a thermal camera. It captures varied poses in indoor as well as outdoor locations at different times of day to stu…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2610.22499v1 Announce Type: new Abstract: Human communication is inherently multimodal, conveying intent not only through linguistic and vocal cues but also through visual signals. However, existing conversational systems have mainly focused on text or speech, leaving out the visual feedback that is essential for natural interaction. In this paper, we propose JAVIS, an end-to-end streaming framework for real-time audio-visual conversational agents. Our key idea is to let the voice and the face speak from a single representation. On top of a shared LLM, a Joint Refined Head produces a unified audio-visual representation, which is fed into dedicated streaming branches for speech and face generation. This end-to-end design avoids intermediate bottlenecks, en…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2610.22529v1 Announce Type: new Abstract: Autoregressive foundation language models predominantly target high-resource Indo-European languages, imposing computational and morphological penalties on under-represented African languages. Generic multilingual tokenizers routinely exceed fertility rates of 3.2 tokens per word on agglutinative Bantu languages, degrading context efficiency and inflating latency. We present Pearl-Chat, an 8,473,122-parameter ($\sim$8.5M) causal decoder-only transformer engineered for Luganda (Oluganda, ISO 639-2: lg), a low-resource Niger-Congo Bantu language spoken by over 10 million people in East Africa. Built from first mathematical principles in JAX and Flax NNX, Pearl-Chat uses explicit functional state decomposition (nnx.s…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2610.22435v1 Announce Type: new Abstract: Distributed Transformer inference across co-located edge devices is fundamentally communication-bound, as exchanging activations between sequence-parallel partitions dominates inference latency under commodity edge bandwidths. Existing compression schemes reduce this cost but retain a structural bottleneck: the received data must still undergo key/value projection before attention can proceed, serializing computation behind communication. This paper presents Transformer Residual Activation Codebook Encoding (Trace), a framework that addresses these limitations. Trace places a Vector Quantizer (VQ) at the post-attention residual of every Transformer layer and precomputes codebook-indexed key/value representations.…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2610.20818v1 Announce Type: new Abstract: Unified multimodal generation covers discrete, continuous, and hybrid paradigms. Discrete approaches with single-codebook visual tokenizers align naturally with text modeling but have limited representational capacity. Continuous and hybrid approaches retain richer visual representations, but they model text and images in heterogeneous spaces with different training objectives, potentially introducing optimization conflicts between modalities with misaligned representation spaces. These choices expose a central question: how to efficiently model high-capacity visual representations alongside textual content in a shared optimization space within a single backbone. We present Intern Lumina U2, to our knowledge the f…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2610.20641v1 Announce Type: new Abstract: Long chain-of-thought decoding is memory-bound: the KV cache of the generated tokens grows linearly with the test-time compute being spent. Evicting cache entries does not fix this, because a model never trained on a cache with entries removed generates longer, often up to the length limit. We instead train the model to compress its own output. AbridgeKV compresses each completed block of generated text into the KV entries of a few learned pause tokens. These are extra input tokens with trained embeddings that produce no output. Once the pause tokens have encoded the block, AbridgeKV frees the block's original cache; subsequent tokens attend to the pause tokens' KV entries in its place. Three novel choices make th…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2610.20682v1 Announce Type: new Abstract: We introduce TurboMamba, a language-model architecture for faster inference, faster training, and better token prediction. A global Mamba-3 model runs once per completed token block. A small Transformer uses this global context and earlier tokens within the block to predict the next token. Three lightweight additions improve local predictions: direct access to the previous block's last token, a small correction to next-token scores, and a learned mixture with recent-token frequencies. We compare twelve small-scale implementations on public FineWeb-Edu, with comparable parameter counts and shared training-budget caps. The baselines include Transformer, Mamba-3, Jamba, and Zamba. The Jamba and Zamba versions use Mam…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2610.20637v1 Announce Type: new Abstract: We expand the exponential kernel of attention into a truncated Taylor series of $n$ terms and factorize each term into a tensor-power inner product, which collapses the causal history into exactly $n$ recurrent states, each updated by one rank-one outer product per token and independent of context length $N$. The recursion is lossless with respect to the truncated kernel ($2.2 \times 10^{-16}$ in float64), and the states are additive across chunks ($5.7 \times 10^{-14}$), so prefill admits a parallel scan. Measured exponents are $t \propto N^{2.28}$ for softmax against $N^{0.91}$ for states, with a crossover at $N \approx 728$ and $20.8\times$ at $N = 8192$; per-token decoding latency is constant at $7.3\,\mu$s ag…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2610.20636v1 Announce Type: new Abstract: Sampling from continuous flow-based generators such as flow matching models requires numerical ODE or SDE integration, making inference cost depend on the number of function evaluations (NFEs). In practice, the sampling budget is inherited from prior work or selected through expensive FID-versus-NFE sweeps, using FID to assess image-generation quality, requiring sample generation and evaluation at multiple budgets. This makes sampling-budget selection dependent on repeated empirical evaluation. We therefore ask a complementary question to solver design and timestep allocation: for a fixed pretrained model and solver, what numerical resolution is sufficient? We introduce FLOWBUDGET, a training-free estimator of sol…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2610.20681v1 Announce Type: new Abstract: Formal inequality proving requires mathematical reasoning and exact computation, often connected through intermediate lemmas and goal reformulations. We introduce IneqAgent, an agentic framework combining LLM reasoning with symbolic computation for inequality proving in Lean4. Lemma-level Monte Carlo Tree Search coordinates lemma construction, goal reformulation, and symbolic backend selection. Complementary sum-of-squares, Bernstein, and successive difference-substitution backends produce exact certificates for local Lean proof generation. The agent integrates these proofs with LLM-generated steps and uses Lean feedback to construct complete proofs checked against the original theorem statements. On four benchmar…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2610.20669v1 Announce Type: new Abstract: Reward-guided discrete diffusion enables test-time alignment with downstream objectives, but applying Sequential Monte Carlo (SMC) guidance at every denoising step is computationally expensive. Active guidance steps require additional reward evaluations and, for gradient-based proposals, value-gradient computations. Sparse guidance reduces this cost by guiding only a subset of timesteps, but commonly used schedules are fixed heuristics whose effectiveness can vary substantially across tasks. We propose VISTA, a training-free method that automatically selects guided timesteps under a fixed budget. VISTA formulates sparse guidance as approximation of the ideal full-guidance probability path and derives an estimable…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2610.19201v1 Announce Type: new Abstract: We present LidarVerse, a real-time unified LiDAR world model for sensor simulation across tasks and sensors. Existing LiDAR simulators largely follow one of two complementary paradigms: reconstruction-based methods preserve the geometry of a captured scene but require lengthy per-scene optimization, whereas generative methods amortize learning across data but lack the consistency needed for long-horizon rollouts. LidarVerse brings both paradigms into a single, unified conditional generative framework. A universal tokenizer maps LiDAR range sequences into a shared latent space, where a bidirectional teacher learns a common interface for conditioning on a LiDAR prefix, an HD-Map, a persistent spatial cache, and opti…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2610.19026v1 Announce Type: new Abstract: Sparse attention reduces the KV-cache traffic that dominates long-context LLM decoding, but practical methods largely operate at coarse granularity. Token-level selection offers finer control, yet presents two challenges: low-dimensional scoring may lose query--key structure needed for accurate ranking, while gathering scattered selected tokens can offset the resulting latency benefit. We introduce Joint Subspace Sparse Attention (JSSA) to address both challenges. For selection quality, JSSA learns a shared low-dimensional query--key subspace by minimizing token-score preservation error. We upper-bound the resulting non-convex objective with a tractable marginal objective that admits a closed-form spectral solutio…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2610.18880v1 Announce Type: new Abstract: High-throughput perturbation screens increasingly use machine-learning models to predict the effects of gene combinations that were never measured. A difficult case arises when both genes in a test pair were seen individually during training, but their combination was not. In this setting, standard OOD methods often fail because neither gene appears unfamiliar on its own. We therefore compare each model prediction with a simple additive prediction obtained by summing the two observed single-gene effects. The difference between them, which we call additive disagreement (AD), measures how much extra interaction effect the model introduces for an unseen combination. Across eight prediction methods and three Perturb-s…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2610.14136v2 Announce Type: new Abstract: Iterative sampling in diffusion models can lead to error accumulation due to exposure bias. The denoiser is trained on real images interpolated with noise, but at inference its inputs are constructed from its own imperfect predictions from the earlier steps, something it has never seen at training time. This might be one reason diffusion models often struggle without additional help, such as CFG. We introduce a correction step for diffusion models which attempts to reduce this training-inference gap. The corrector takes the base model's prediction as input and is trained against the same ground-truth target. This makes correction an explicit learning task, with training inputs provided by the base model. During sa…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Multimodal agents commonly generate freeform reasoning before each action. For small models, limited model capacity can result in lengthy reasoning that provides little useful guidance for action generation while incurring substantial inference cost. To address this challenge, we introduce Selection-based Structured Reasoning (SSR), a framework that reformulates reasoning as selection instead of open-ended generation. SSR represents recurring high-level reasoning as pre-specified, reusable natural-language candidates. At each turn, the model selects from the reasoning candidates based on their…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Marktechpost ranks the 9 best AI gateways for 2026. We compare Bifrost, Portkey, LiteLLM, Kong, TrueFoundry, Cloudflare, Vercel, OpenRouter and Orq.ai on latency, pricing, licensing, governance and deployment. The post 9 Best AI Gateways in 2026: Bifrost, Portkey, LiteLLM, Kong and 5 More Ranked appeared first on MarkTechPost.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯： Release: llm-gemini 0.35 I added support to llm-gemini for the new Gemini 4 Argon model, made available today via the Gemini API and for customers of their $100/month subscription plan. Here are the low, medium and high pelicans. As expected, they are all excellent: Gemini has a track record of producing great SVGs, and are the only lab where I know their staff have invested in SVG specifically (and who have boasted about their pelicans before.) Here's the "high" illustration, which cost me 17.166 cents: The pricing is interesting. At launch, Argon is $2/million input and $10/million output - the same price as GPT-6 Sol, half the price of Claude Opus 5.5 and 1/5th the price of Claude Fable 5.1 and GPT-6 Astra. But on December 1st Argon is set to double in pric…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：AWS engineers share kernel optimizations for fused Mixture-of-Experts (MoE) models on Amazon SageMaker AI: Swap-AB for WGMMA utilization, Triton backend routing for FP8 quantization, and eliminating Triton JIT recompilation. Together they deliver up to 10% higher throughput and up to 9% faster Time to First Token on H200 GPUs.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2610.12561v1 Announce Type: new Abstract: Memory allows large language model (LLM) agents to use past experience, often stored as textual records, when responding to requests. For embodied agents that control robots, visual and spatial observations introduce a broader choice of memory modalities, affecting both the information available for subsequent tasks and the model inference costs of constructing and using memory. We introduce MeMoREval, a benchmark for studying this problem through a controlled experience-request protocol. Agents first experience a sequence of events without knowing the subsequent tasks, and subsequently they use memory to respond to information and action requests without receiving new observations. The benchmark comprises 53 task…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2610.12516v1 Announce Type: new Abstract: Interleaved multimodal in-context learning (ICL) lets frozen large vision-language models (LVLMs) acquire new tasks from a handful of image-text-answer demonstrations, yet it remains fragile: demonstrations bind to the wrong images, redundant exemplars crowd out informative ones, and noisy answers are copied verbatim into predictions. We present AVA, a training-free framework that organizes the demonstration pipeline of multimodal ICL into three composable stages. A Thread-Resolved Decomposer (TRD) segments the interleaved context into per-sample threads and re-stitches them with explicit boundaries, restoring image-text binding. An Influence-scored Demonstration Selector (IDS) estimates each candidate's marginal…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2610.12514v1 Announce Type: new Abstract: Autoregressive video diffusion models maintain a growing attention key-value (KV) cache, making memory a key bottleneck for long video generation. Recently, clustering-based quantization has emerged as an effective method to compress video KV caches by grouping similar key and value vectors then quantizing residual errors. However, when later frames attend to the compressed history, small reconstruction errors can compound as the video grows. Beyond the within-layer similarity exploited by clustering, we find strong dependencies across cache layers in video models. This motivates Coral-KV - Calibrated Offline, Residual-coded, and Adapted Locally - a KV-cache compression framework that uses cache states in each lay…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2610.12582v1 Announce Type: new Abstract: A latent recurrent language model applies a shared block of layers repeatedly, so one checkpoint can trade inference compute for accuracy by changing the loop count. At one loop, however, such models typically fall well short of a non-recurrent model of the same size, a one-loop tax that makes a separate non-recurrent model the better choice whenever latency matters. We present Elastic Latent Recurrence (ELR), a recipe for training looped language models without this tax. At one loop, an ELR model costs the same to serve as a non-recurrent model of the same size and, trained on the same data, reaches similar accuracy. Each additional loop then buys more accuracy for more inference compute. Three choices make this…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2610.12570v1 Announce Type: new Abstract: Speculative decoding accelerates large language model inference by using a lightweight drafter to propose multiple tokens that are subsequently verified in parallel by the target model. Recent diffusion-based drafters make this paradigm particularly attractive: deep attention-based neural backbones provide strong predictions, while drafting multiple future positions in parallel avoids the sequential cost of autoregressive generation. This parallelism, however, comes at a cost. Tokens within a draft block are predicted without access to the realized identities of preceding draft tokens, removing intra-block dependencies that would naturally be available under autoregressive generation. We introduce DCOCO (DFlash Co…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2610.12530v1 Announce Type: new Abstract: Training-free feature reuse accelerates diffusion transformer inference by replacing full denoising computation at selected steps with cached approximations. Existing methods mainly improve the reconstruction of skipped features, but we find that once a stable first-order reconstructor is used, increasing reconstruction complexity brings limited gains, whereas the placement of exact-computation steps has a much larger effect on fidelity. More importantly, absolute shallow-probe variation is jointly affected by input-trajectory displacement and network response strength, and therefore does not directly reflect cache risk. We address this confounding by normalizing probe-output variation with the corresponding input…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2610.12495v1 Announce Type: new Abstract: Small language models trained on a single local machine leave little room for architectural trial and error. Kairos combines bidirectional gated-DeltaNet linear attention and sliding-window attention over shared projections (LiZAttention2), block-wise Attention-Residual aggregation, a sparse Mixture-of-Experts (MoE) feed-forward layer and a multi-scale byte-level codec, trained with a uniform-noise denoising objective over one byte space shared by text, image, audio, video, lidar and control streams; this report asks whether the combination optimizes at all before asking whether it is useful. We give code-derived algorithms for each component, including a cross-session recurrent-state memory gate, then run converg…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2610.12494v1 Announce Type: new Abstract: In this article, we propose algebraic integer number formats (AINF) as a framework for highly configurable and accurate compressed computation. A key property of AINF is its straightforward reduction to purely integer arithmetic, enabling error-free multiply-accumulate operations. We develop a matrix multiplication engine that exploits this property, obtaining performance within a predictable factor of the most efficient numerical counterparts on modern hardware accelerators. Another key advantage of AIQ is the freedom to select algebraic integers tailored to the numerical characteristics of a given use case, offering optimization opportunities that are fundamentally unavailable in floating-point or fixed-point fo…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Today’s engineers face an unprecedented acceleration in AI hardware complexity, as explained in the recent research article “Revisiting Edge AI: Opportunities and Challenges.” The article examines the rapid growth of edge AI and the challenges it creates, including resource constraints, model architecture limitations, and network demands across edge-AI deployments. The acceleration is driven by a fundamental shift in how modern AI models are built and scaled. As the models have become much larger and more complex, they are computationally more demanding because they contain more parameters and require more calculations. To meet the demands of scaling deep neural networks, the industry is increasingly developing AI chips that are designed for specific tasks. One…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2610.10787v1 Announce Type: new Abstract: Language models trained with long-horizon agentic reinforcement learning can generalize knowledge through reasoning, express precise actions, and pursue goals over many steps, raising the ceiling on what an embodied agent can understand and decide. Physical interaction, however, remains the domain of action policies, which provide dense, low-latency control. We present NavGPT-3, a harness that connects the two models, with an OS-like runtime built above it: reasoning, acting, and monitoring run as threads with their own context, tools, and permissions, while the runtime schedules them and decides which thread controls the robot's motion, so that the robot can react to sudden real-world events through interruption…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2610.10563v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) often answer visual reasoning questions by relying on linguistic priors rather than task-relevant visual evidence. Textual chain-of-thought reasoning can partially mitigate this issue by encouraging models to decompose visual questions into intermediate evidence-seeking steps, but generating these steps autoregressively increases inference cost. Latent reasoning avoids explicit rationale generation, but existing approaches provide limited control over what intermediate states encode, making it difficult to impose separate supervision for planning, grounding, and evidence selection. We propose Structured Latent Visual Reasoning (SLVR), a training framework that bridges expli…