AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2610.22454v1 Announce Type: new Abstract: Running prompt tokens through fewer routed experts during prefill is a simple way to make mixture-of-experts (MoE) serving cheaper, yet it is unclear what this damages. We locate the damage with token-, layer- and attention-path interventions on short-answer question answering in four MoE families. At half the experts the F1 loss of three families is mostly answer form: the model still finds the answer but stops answering briefly. In Qwen3-30B-A3B this loss is made at the two chat-template tokens before the answer, and in DeepSeek-V2-Lite at the first 8-32 prompt tokens, where its instruction sits; by answer likelihood these positions account for about half and a fifth of the damage. Reduction changes the first to…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2610.22428v1 Announce Type: new Abstract: In a small language model the vocabulary is the single largest part. In Gemma 3 270M the embedding table holds 168M of 268M parameters, and because quantisation methods leave the embedding in 16-bit, it is also most of the file once the rest of the model is compressed. We ask what that table actually buys. We replace it with one frozen table of 512-bit codes, 16 MB, with no trainable parameters, derived once from a pretrained embedding by principal-component projection and sign binarisation, and we train the same Gemma-shaped body from scratch on the same 2.05B tokens with and without it. The learned table buys 0.20 nats of validation loss for 2.6 times the trainable parameters, but on LAMBADA, HellaSwag and PIQA…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2610.22439v1 Announce Type: new Abstract: Catastrophic forgetting remains a challenge in supervised continual learning, as adapting to new tasks causes representation drift and loss of previously learned information. This raises the question of which representational changes should be constrained while preserving plasticity. We therefore introduce Sparse Autoencoder Geometric Anchoring (SAGA), which converts a Sparse Autoencoder (SAE) trained at each task boundary into local, low-rank constraints on representation drift. Replay examples specify where the constraints apply, while leading right singular directions of the encoder Jacobian specify which changes are penalized. The resulting geometry is input dependent and can be retained without keeping the SA…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2610.22438v1 Announce Type: new Abstract: Studies of what fine-tuning does to a language model often summarise the weight update $\Delta W$ by its rank. We compare the rank measures used for this against the same measures on a random matrix of the same shape, and against two harder references: the pretrained weights, and matched fine-tunes without alignment content. Measures that count directions put our fine-tuning updates only a little below noise; stable rank, computed from the same singular values, puts them far below. Both are right: an update has a few strong directions on top of a long tail. The pattern holds for thirteen released pairs up to 8B parameters, and it is not a mark of alignment: with training held fixed, instruction data does not stand…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2610.22437v1 Announce Type: new Abstract: Automated fundus-based diabetic retinopathy (DR) grading can substantially expand screening capacity, but source-trained models degrade sharply across different cameras, clinics, and patient populations. Existing test-time adaptation methods depend on entropy minimization or target information accumulated from image batches and streams. These mechanisms can reinforce confidently incorrect predictions and break down when clinical images arrive independently. We introduce CF-NODE, a novel counterfactual test-time adaptation framework for cross- domain DR grading. Instead of trusting prediction confidence or estimating a target distribution, CF-NODE asks how each prediction responds under a controlled intervention on…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2610.22436v1 Announce Type: new Abstract: The signal generation capabilities of a novel data augmentation framework are examined in aerospace structures. First, the framework learns class-conditional temporal and spectral characteristics of the measured structural responses. It uses conditional generative adversarial network training and Monte Carlo dropout uncertainty quantification as a Bayesian approximation. This step enables stochastic signal synthesis and uncertainty quantification. Second, the generated responses are rigorously compared against experimental measurements across time, frequency, uncertainty, variability, and feature domains to assess physical realism, statistical consistency, and distributional fidelity. Finally, the synthetic data a…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：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 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2610.22433v1 Announce Type: new Abstract: Flexible job-shop scheduling becomes resource-coupled when a scarce vehicle fleet moves jobs between stations, because the schedule sets the transport waits. BOLT (bound-oriented learning for transport-coupled scheduling) builds a lower bound from chain, machine-capacity, and fleet-capacity relaxations. The bound equals the makespan at termination, so its per-step changes form a reward that sums to a constant minus the makespan. Because it never exceeds the attainable makespan, each candidate's bound increase is a proven rise of the makespan floor, which the policy reads as a price. The root bound certifies a completed schedule's suboptimality gap without a solver. On industry-motivated 10-module prefabricated-con…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2610.22430v1 Announce Type: new Abstract: Accurate prediction of multivariate time series requires models that simultaneously capture variable-specific dynamics and cross-variable interactions. In this work, a Correlation-Guided and Dynamics-Trained Clustered Echo State Network (CGDT-CESN) is proposed, which comprises a modular reservoir architecture with each cluster distinctly specializing in one of the variables in the multivariate time series. An innovative reservoir design is proposed in which inter-cluster connections are enabled by empirically observed correlations among variables, providing a data-driven coupling mechanism. Apart from conventional readout training, inter-cluster connection weights informed by correlations are trained, which in tur…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2610.22381v1 Announce Type: new Abstract: When a fact becomes harder to elicit from a language model, has the model lost it, or has it merely become less accessible? Parameter-updating test-time continual learning agents are usually evaluated by current output accuracy; we ask whether that measurement captures how prior experience shapes later updates. We test whether learning a specific factual binding produces a later relearning advantage beyond familiarity with its entity, answer vocabulary, format, or query slot. In Qwen2.5-1.5B, we compare three matched, counterbalanced histories: LEARNED receives the correct binding, CONTROL receives matched exposure without it, and WRONG receives a competing relation-valid answer in the same slot. After an identica…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2610.22380v1 Announce Type: new Abstract: Continuous diffusion treats the forward process as a design space; discrete language diffusion often uses absorbing corruption, leaving context fully trusted throughout generation. This makes trust binary: corrupted context is copied as ground truth, propagating errors into generated spans. We reopen this design space by combining absorbing and uniform-mixing kernels with region-dependent rates. Missing positions follow absorbing dynamics, while context undergoes low-rate random substitution, exposing the model to observed but uncertain tokens during training. At inference, a heuristic sampler re-injects noise into suspicious context under an annealed intensity and freezes context updates late in the trajectory. A…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2610.22379v1 Announce Type: new Abstract: Calibrating expensive engineering simulators requires tuning model parameters to match reference data, a process heavily constrained by computational costs. This study investigates whether Large Language Models (LLMs), conditioned on physical diagnostic descriptions of simulation errors, can propose informative parameter updates more efficiently than conventional derivative-free optimizers. We test this on a cylinder-wake Large-Eddy Simulation and a damped-oscillator inverse problem. Physics-labeled prompts are evaluated against four text ablations (removed, anonymized, padded, misdirected) and standard optimizers (Nelder-Mead, Bayesian optimization, CMA-ES, and random search). Results demonstrate a strong early s…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2610.22460v1 Announce Type: new Abstract: AI welfare is generally treated purely as an ethical issue rather than also as a safety issue. We argue this is a mistake. Whatever their moral status, models exhibit welfare-like states that causally influence their behaviour. Following recent work, we adopt the term 'functional welfare' for these states. We make three claims. First, functional welfare already arises naturally and will become more robust as models acquire more coherent goals and personas. Second, functional welfare should be treated as a safety variable: it should inform evaluation design, be tracked in monitoring, and be a direct target of post-training. Third, against existing scepticism about measuring AI welfare, we argue that good empirical…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2610.22446v1 Announce Type: new Abstract: Neural operators approximate solution operators of partial differential equations at a fraction of the cost of numerical solvers. Efficient grid-based architectures such as the Fourier neural operator (FNO) assume uniform rectangular grids, whereas engineering simulations use large, irregular, and locally refined meshes. We introduce L-SplineFNO, a memory-efficient neural operator that couples an FNO backbone with a sparse, learnable tensor-product B-spline transfer between unstructured meshes and a latent Cartesian grid. A local normalised scatter avoids the geometry-dependent solve of analytic spline transformation while preserving compact support, partition of unity, and spline smoothness by construction. The n…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2610.22445v1 Announce Type: new Abstract: Automated discovery systems propose scientific explanations and test which to accept. Does passing a test establish the intended claim? We develop four executable operations for changing physical descriptions: identifying redundancies (L1), coarse-graining dynamics (L2), transferring structure (L3), and inferring missing quantities from conservation imbalances (L4). We evaluate these operations and three interpretability settings through null acceptance (NAR), positive acceptance (PAR), and consequence agreement (CAR). A reduction mapping every state to zero predicts its own future perfectly. It passes closure on 96% of 129 public chaotic systems despite retaining no dynamical variation. An independent observable-…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2610.22441v1 Announce Type: new Abstract: Large language models (LLMs) provide a convenient interface for translating natural language commands into task plans for cyber-physical systems (CPSs). However, two gaps hinder their use for real execution: generated plans may misinterpret or omit the user's intent, and even a logically plausible plan may be infeasible under component dynamics, interactions, or safety constraints. Existing LLM-based planning approaches often lack informative feedback on why a generated plan fails, providing little guidance for revising the plan accordingly. To address these challenges, we present a hierarchical feedback framework that uses different types of feedback information to guide LLMs in generating executable plans for CP…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2610.22426v1 Announce Type: new Abstract: LLM agents are used to check records against an organization's requirements, for example whether a vulnerability report is ready for investigation. Requirements often allow several ways to be met, such as a severity rating with a curator-reviewed advisory or a published advisory link. Agents fail by accepting a report after a required check has failed, or by settling for a weaker conclusion without trying another way that could still succeed. We introduce PRIME (Precommitted Rules for Inference from Minimal Evidence). Before checking, it fixes evidence routes specifying how each conclusion may be justified. A separate program records each check result and refuses any conclusion the results do not justify. It also…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2610.22420v1 Announce Type: new Abstract: Agent-based models are well-suited for modelling agro-ecological systems for decision-making, yet turning their simulations into actionable insight requires identifying which decisions actually drive the behaviours. In such a context, sensitivity analysis stumbles upon a structural feature of many complex systems: the parameters are not a flat vector but a decision tree in which many parameters appear only when a higher-level choice activates them. Classical global sensitivity analysis presupposes independent inputs over a fixed Cartesian product and is ill-posed on such a branched space and biased by construction. We instead treat the structure of the decisions as a first-class modelling object. Using advanced su…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2610.22408v1 Announce Type: new Abstract: Long-horizon GUI agents rely on visual history to maintain task states, but retaining historical screenshots increases visual-token usage and inference costs, while textual summaries can discard critical state information, undermining long-horizon reliability. We propose ECHOES, which leverages training-time privileged information to guide textual history compression and strengthen long-horizon reasoning. Specifically, ECHOES adopts a Compression-Think-Action (CTA) format to recursively update a textual history state and reason. The same model, given privileged multi-image inputs, serves as a teacher that provides dense token-level on-policy distillation on student-generated CTA rollouts. Our Perception-Memory Fid…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2610.22403v1 Announce Type: new Abstract: What a reasoning system emits is a conclusion; what it owes is a justification. Producing one requires every operation to be admissible on the facts actually available, the dependencies of intermediate results to survive to the end of the path, and the path to be revised when a premise changes. We present the Event Reasoning System (ERS), in which the reasoning state is an explicit event graph. Semantic features nominate candidate objects and rule bindings, and declared rule and task conditions decide which may execute, so candidates that violate the represented period, unit, or evidence constraints cannot enter an accepted reasoning path. Low-level rules provide reusable local transformations, and recursively com…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2610.22400v1 Announce Type: new Abstract: Existing large language model (LLM)-based user encoders serialize heterogeneous behavioral logs and compress them into static representations through autoregressive (AR) prediction. However, their unidirectional constraint limits bidirectional information flow, hindering cross-modal interactions and the joint preservation of multi-source signals. Consequently, the learned static representations struggle to accommodate the distinct evidence requirements of diverse downstream scenarios. We address these limitations by unlocking the iterative denoising process of diffusion language models (dLLMs) as a multi-granularity reconstruction space. Based on this insight, we propose FINDERS (FactorIzatioN of Diffusion statEs…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2610.22373v1 Announce Type: new Abstract: LLM-based agents are increasingly used as autonomous orchestrators in distributed and multi-agent systems, yet a control gap remains: no protocol-level mechanism allows human operators to inject binding directives that persist across planning cycles. Free-text overrides suffer from ambiguous interpretation due to lack of schema validation and from authority erosion as operator instructions lose influence within accumulating context. We propose Structured Authority Injection (SAI), a protocol that addresses these issues by routing operator corrections through typed, schema-validated Model Context Protocol (MCP) tool calls and maintaining a ranked authority context prepended to each LLM prompt. SAI defines three ove…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：Discussion | Link

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：NVIDIA has released the full Run:ai GPU orchestration platform as open source under Apache 2.0. The release includes KAI Scheduler, CUDA 13.4 GPU fractioning, quota management, and a local Kind dev environment. The post NVIDIA Open Sources Run:ai Under Apache 2.0 for Kubernetes GPU Orchestration appeared first on MarkTechPost.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：Mistral released Timestral, a time series foundation model family from 5M to 209M parameters. The 209M model leads GIFT-Eval, TIME and fev-bench among zero-shot models and runs on CPU. The post Mistral AI Releases Timestral: A 209M Forecasting Model Family That Outperforms Google’s TimesFM-3 appeared first on MarkTechPost.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：Of the dozens of countries approached to water down their laws, Australia appears to be the only one considering it, publishers’ group says Get our new political email, free app or daily news podcast AI has already been trained on the works of Australian artists including Kylie Minogue and Nick Cave without compensation, the peak global body for music rights has claimed, as the Australian government has been warned against giving in to “strong-arming” from tech companies seeking to weaken copyright law. The International Confederation of Music Publishers (ICMP) – which represents Sony, Warner and Universal as well as thousands of independent publishers on six continents – has warned that of the dozens of countries approached to water down copyright laws, Austra…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：Clef, a 27B multimodal decision model from Cloudflare, is now available on Ollama. Run it locally or on Ollama's cloud.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：Post-train open LLMs like Qwen, GLM and Kimi into custom models you own, with SFT or RL. You write the training loop. Together runs the hard infrastructure.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译： Release: llm-tools-datasette 0.1.1 When I switched LLM over to httpx2 in LLM 0.33 I forget that this would break any plugins which used httpx without directly depending on it. llm-tools-datasette was one of those plugins, now fixed. Tags: datasette, llm

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译： Release: llm-echo 0.5 I'm working towards a new LLM release, and testing PRs caused me to revisit the llm-echo debug plugin. This plugin provides a "model" which doesn't involve an LLM at all - it just repeats back the prompts that have been fed to it. The new release now updates the simulated token usage counts to take tool calls, system prompts, and reasoning tokens into account. Example usage: uvx --with llm-echo llm -m echo 'hi there' -o thinking 1 --usage Outputs: First I consider the prompt, then I decide what to say. { "prompt": "hi there", "system": "", "attachments": [], "stream": true, "previous": [] } Token usage: 2 input, 24 output Tags: llm