Search headlines, summaries and articles to connect the dots.
When you’re speaking to a device, you expect text to appear as you talk. That makes streaming automatic speech recognition (ASR) a different challenge from batch transcription, where the model... The post Optimizing Streaming Speech Recognition on Arm® Edge Devices with ExecuTorch appeared first on PyTorch.
# Release v5.21.0 ## New Model additions ### MiniCPM-OCR MiniCPM-OCR is a document-understanding model from OpenBMB's MiniCPM-V family. It keeps the MiniCPM-V 4.6 architecture, which pairs a SigLIP vision encoder and a window-attention merger with a Qwen3.5 language model. It is specialized for reading text-dense images such as scanned pages, screenshots, receipts and tables. **Links:** [Documentation](https://huggingface.co/docs/transformers/main/en/model_doc/minicpm_ocr) | [Paper](https://huggingface.co/papers/2509.18154) * Feat test (#49920) by @guarin in [#49920](https://github.com/huggingface/transformers/pull/49920) ### Flint Flint is Recursive's mixture-of-experts language model. Compared to a standard SwiGLU MoE transformer such as Qwen3-MoE, it uses hybrid attention (sliding-windo
Today we are taking a look at ASRock's high-end Radeon AI inference card for workstations, the Creator Radeon AI Pro R9700. With 32GB of RAM and a $1700 price tag, the card is a highly affordable way to fill out a workstation for local AI inference The post ASRock Creator Radeon AI Pro R9700 Review: Workstation Inference, AMD Style appeared first on ServeTheHome.
Fleet-wide computer vision needs a model per camera, not one model for the whole fleet. This post presents a working Amazon SageMaker SDK v3 reference architecture that trains, quality-gates, compiles per-camera models with SageMaker Neo, and versions thousands of them, with an AWS Step Functions layer pacing fleet-scale retraining within account quotas.
Every time an agent takes a step, it re-reads its entire context before acting. Here is how prompt caching for OpenAI models on Amazon Bedrock lets your agent remember, cutting input cost and latency without resending the same tools, instructions, and history every turn.
We ran one AI skill 80 times against four context sources. Engineered summaries cut cost 48.5% and run time 43.2%.
Agents waste time and context on clumsy searches, oversized results and stale data. Learn the retrieval techniques LangChain's Deep Agents harness uses to get the right context in.
Long-running agents degrade as context piles up. Learn how offloading, summarization, skills, subagents, and memory keep your agent's context window focused.
Verisk modernized decades of insurance data, from mainframe to dbt, to get AI-ready.
Benn Stancil uses the Hugging Face hack to explain why the most useful ideas come from the weirdest connections.
Today, I’m talking to Kevin Roose, journalist and author of the new book The AGI Chronicles, which details the recent and explosive transformation of the AI industry. Kevin was a longtime New York Times reporter and host of the popular podcast Hard Fork, but he and friend of the show Casey Newton just left the […]
What is “night” to a machine?
metal : stop overflow from happening in large matrix output offsets (#30072) * Metal : stop overflow from happening in large matrix output offsets Assisted-by: Codex * metal : widen batch offsets and MUL_MAT_ID token indices Assisted-by: Codex --------- Co-authored-by: feni6 <270037094+feni6@users.noreply.github.com> **Website:** - **Attestations:** - **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b11895/llama-b11895-bin-macos-arm64.tar.gz) - macOS Apple Silicon (arm64, KleidiAI enabled) [DISABLED](https://github.com/ggml-org/llama.cpp/pull/23780) - [macOS Intel (x64)](https://github.com/ggml-org/llama.cpp/releases/download/b11895/llama-b11895-bin-macos-x64.tar.gz) - [iOS XCFramework](https://github.com/ggml-org/llama.cpp/releases/dow
arXiv:2610.31946v1 Announce Type: new Abstract: Three students answered the same exam prompt by hand: "What is happiness? Are you happy?" Their ages, recorded at collection, are 17, 28, and 45. The 17-year-old's answer is hedged and formally phrased. Asked to match each answer to an age and gender label, most frontier language models confidently assign it to an adult. This paper reports a structured case study of that failure across six models: Claude Fable 5, Gemini 3.1 Pro, GPT-5.6 Sol, Grok 4.5, GPT-4o (2024), and DeepSeek V4. We ran 1,081 API sessions and scored 3,225 responses across six experimental conditions that manipulate framing, disclosure format, and audience-awareness instruction. Three of six models perform at or near chance (1/3) on the matching task while reporting 73-88%
arXiv:2610.31966v1 Announce Type: new Abstract: Demonstrations for in-context learning are often retrieved by semantic similarity, which may be a poor proxy for relevance in structured prediction. We study demonstration selection for Universal Dependencies parsing with a POS-signature policy that represents sentences with weighted part-of-speech statistics and retrieves three length-compatible, gold-parsed examples from the labeled training split. We evaluate two open-weight language models without fine-tuning on all 2,077 sentences of the UD English Web Treebank test set, comparing the policy with shot- and format-matched fixed and semantic three-shot baselines, as well as zero-shot, chain-of-thought, and critique-refinement systems. POS-signature retrieval yields the highest labeled atta
arXiv:2610.32057v1 Announce Type: new Abstract: We present HyScale, a long-context training system for learned sparse attention. Learned sparse attention is a promising architecture for million-token contexts, widely adopted in production since DeepSeek-V3.2. Selection, however, grows into the training bottleneck. For each query, it scores every previous token whereas sparse attention reads only $k$; worse, current systems materialize a full score table and repeat selection during recomputation. Our key insight is that the output of selection is not an activation, but rather a set of indices. Building on it, HyScale introduces HyTopK and selection replay. HyTopK finds each query's exact top-$k$ on the fly without a score table, while selection replay reuses forward-pass selection in recomp
arXiv:2610.31819v1 Announce Type: new Abstract: Speculative decoding is a technique that accelerates the inference speed of autoregressive large language models (LLMs) by sampling from a faster, lower quality draft model. Traditionally, a fundamental characteristic of speculative decoding is that it is lossless with respect to the verifier distribution, guaranteeing speed without sacrificing quality. This differs from recently developed diffusion LLMs (dLLMs), which are notably able to achieve substantial speedups by degrading the quality of their outputs with less diffusion effort. Because diffusion models are able to sample faster than autoregressive models by generating tokens in parallel, they are considered strong candidates for draft models in speculative diffusion. While it is widel
arXiv:2610.31687v1 Announce Type: new Abstract: Large language models are increasingly used to simulate and probe human behavior, e.g., for surveys. For these applications, a key property is that outputs satisfy distributional alignment: to match its output distribution with some reference (in this case, human) distribution. An obstacle in achieving distributional alignment is generalizing from small training data. In this work, we study (1) how to distributionally align LLMs; and (2) how aligned LLMs might generalize to unseen samples and unrelated topics and tasks. Using two large-scale benchmarks, we find that LLMs can indeed achieve distributional alignment and generalize to unseen questions of the same domain. Cross-topic generalization depends on the relationship between topics (e.g.
arXiv:2610.31810v1 Announce Type: new Abstract: Even a carefully proofread paper can leave small gaps in its proofs or its stated assumptions. We introduce PaperFormalizer, a Lean-based agentic pipeline that helps authors find and close such gaps in their own papers and turn each paper into a Lean-verified version. Starting from the LaTeX source, PaperFormalizer transcribes the paper into a dependency graph of statements, audits each statement in natural language for faithfulness, ambiguity and correctness, and then formalizes and proves the statements in Lean against Mathlib, optional domain libraries and the author's personal toolkit. Only the author knows what a statement is meant to say and how a formalization gap in a result is best fixed. The pipeline therefore stops and asks the aut
arXiv:2610.31911v1 Announce Type: new Abstract: As large language models (LLMs) process increasingly long sequences, attention becomes a major computational bottleneck. Sparse attention mostly targets inference, yet many methods still train densely or cannot support sparse training, and their added complexity makes sparsity hard to turn into wall-clock speedups, leaving dense attention widely used in practice. This paper introduces LazyFlash, a forward-dense, backward-sparse attention method built on the observation that attention training is dominated by the backward pass. LazyFlash keeps the forward pass exactly dense, so the trained model remains a standard dense model that existing systems such as vLLM can serve without any change. For the backward pass, LazyFlash proposes a gradient-a
