让下一篇重要论文，不再错过。

This work develops a physics-informed multimodal deep learning framework for 10- to 110-minute-ahead probabilistic photovoltaic power forecasting. The forecasting model is built on a four-branch architecture that separately encodes plant-level temporal history and inverter-level spatial cloud dynamics through a graph attention encoder with a learned adjacency, known-future solar geometry, and the current meteorological state, fused through gated cross-attention. The geometry branch adds two forward-looking physical signals, spatial cloud heterogeneity and inverter ramp-down activity, each empirically weighted toward the horizon where it is most predictive. The decoder anchors its prediction to a smart persistence baseline, learning a horizon-conditioned correction, and the resulting quantile forecasts are calibrated online through a kernel-weighted adaptive conformal calibration step. The proposed model outperforms all 14 baselines, achieving a forecast skill score (FSS) of 0.2950, 0.099 above the next-best model. A branch-composition ablation shows that every branch contributes positively and the model retains substantial skill in challenging overcast and variable sky conditions (FSS 0.198 and 0.255).

Traffic cameras support useful analysis, but their outputs can reveal private information. Replacing images with text reduces direct visual exposure. It does not place a formal bound on disclosure. The published reinforcement learning and mixture-of-experts framework refines scene descriptions through relevance, coverage, and brevity rewards. It does not account for repeated releases under a fixed privacy budget. This paper proposes budgeted semantic release as an extension of that framework. Four scene experts first process isolated video chunks. Their outputs are mapped to a fixed, bounded semantic schema. A reinforcement learning controller selects which expert summaries to release and how much privacy budget to spend. The controller uses public task requests and previous private releases. A separate privacy filter enforces the total budget. Calibrated noise is added before the summaries are converted to text. Under explicit chunk isolation and bounded-event assumptions, the complete release transcript satisfies an event-level differential privacy bound. The design also supports reuse of previous summaries without new disclosure. An evaluation protocol covers traffic utility, privacy attacks, release freshness, and computational cost. Illustrative tables show the intended reporting format. They do not establish empirical gains. The proposed contribution is a task-aware release interface with auditable privacy accounting for repeated traffic descriptions.

Context: Generative AI (GenAI) and Large Language Models (LLMs) are increasingly used for academic tasks in software engineering and beyond, including systematic literature reviews (SLRs). However, whilst their capabilities are rapidly developing, there is no guarantee they can meet the rigour, reliability, and transparency that SLRs require. Objectives: To support researchers intending to conduct SLRs using GenAI, or those conducting empirical studies to evaluate how well GenAI supports SLR tasks. Methods: First, we conducted a rapid review to identify studies that propose guidelines for evaluating and using GenAI and LLMs to support SLRs. Second, we drew on thought experiments, relevant guidance from the literature, and our own experience from conducting SLRs and evaluating tools, to develop recommendations for how to use and assess GenAI in the context of SLRs. Results: We classify methodological issues for the roles of evaluation and reviewing into four categories spanning SLR practice adjustments, general secondary-study standards, GenAI evaluation practices and core empirical rigour. Building on this, we introduce GUEST (GenAI Use and Evaluation in SLR Tasks) which is a comprehensive framework of 51 recommendations designed to guide researchers through planning, executing and transparently reporting GenAI-assisted literature reviews and validation studies. Conclusion: Current empirical evidence indicates that GenAI cannot be relied upon to perform unsupervised systematic reviews so requires human oversight. Nevertheless, it can offer cost-effective assistance for repetitive screening tasks and secondary validation. By standardizing how these tools are deployed and evaluated, the GUEST framework provides a necessary methodological baseline for trustworthy GenAI-assisted research in software engineering.

Deep audio classifiers can achieve strong predictive performance, but their hidden representations remain difficult to interpret. Existing audio explainability methods often focus on input-level attribution, such as waveform segments, spectrogram regions, or acoustic features, and provide limited insight into what hidden neurons encode. Interpreting hidden neurons at the concept level can provide a more meaningful view of what an audio model learns internally. This paper investigates whether hidden neurons in audio classifiers can be associated with human-understandable symbolic acoustic concepts. A model-agnostic neurosymbolic framework is presented for analyzing the final hidden layer of audio classifiers, containing 32 neurons, through symbolic concept induction. The framework is evaluated on two audio classification settings: music genre classification using GTZAN dataset and musical instrument classification using IRMAS dataset. Results show that several hidden neurons can be associated with meaningful induced concepts, and most confirmed neuron-concept pairs are statistically supported using the Mann-Whitney U test. These findings suggest that symbolic concept induction is a promising direction for explaining latent audio representations beyond input-level attribution.

Complex questions in retrieval-augmented generation require evidence spread over several documents, and an answer is reliable only when the retriever finds all of it. Chain embedding retrievers collect such evidence step by step, re-encoding the question together with the passages retrieved so far, and we find that they are already strong: trained only on gold histories, a small chain embedding retriever that calls no language model outperforms graph-based systems and is competitive with a search agent. This training, however, leaves a gap. At test time the retriever conditions on its own retrievals, which soon contain mistakes: by the third step, about half or more of the states it visits hold a wrong passage, and these passages lower its chance of retrieving a missing gold passage well beyond what the difficulty of the states explains. We propose on-policy state training, which trains the encoder on the states it reaches itself. At every epoch the current encoder retrieves chains for the training questions; each state it visits, including those built on its own mistakes, is labeled with the earliest gold passage still missing while the other missing gold passages are masked, so that no correct continuation is penalized; and the encoder is updated contrastively on these states mixed with teacher-forced ones, so that its training distribution follows it as it learns. The resulting retriever retrieves complete evidence more often than teacher-forced training and the systems we compare, and it transfers without further training to harder long-chain variants of HotpotQA and 2WikiMultiHopQA that we construct. On the same states, it recovers from its own mistakes far more often, and controlled comparisons attribute the gain to training on the states the encoder currently reaches.

Reinforcement learning with verifiable rewards (RLVR) improves language-model reasoning by scoring sampled responses with a rule-based verifier and reinforcing those that pass. Where a classifier's training couples predicted probability to labels, nothing ties an RLVR policy's confidence in a response to its reward: aligned training would drive responses with the same advantage toward equal confidence, yet the advantage is blind to confidence. Under this sequence-confidence misalignment, a success the policy barely found earns the same update as one it produces with near certainty, and a confident error is corrected no harder than an exploratory one. We propose SCARL (Sequence Confidence-Aligned Reinforcement Learning), which reshapes, but never re-signs, each advantage with the alignment gap between the response's group-relative confidence and the outcome its advantage certifies, normalized into shares of each class's advantage budget. Misaligned samples absorb the force, responses with the same advantage are driven toward equal confidence, and repairing the misalignment doubles as a remedy for the entropy collapse that erodes exploration. SCARL provably reduces to its base estimator when a class's confidences agree, adds no extra passes and one hyperparameter. On Qwen3-4B-Base it lifts average Pass@32 by 2.4 points over DAPO and is best among nine compute-matched methods on both coverage and per-draw accuracy; applied unchanged across four estimators and four backbones, it improves 14 of 16 settings while preserving policy entropy and widening the confidence-correctness separation. Our code is available at https://github.com/kezhh163/scarl.

Despite growing capabilities, LLMs remain susceptible to prompt injections: malicious inputs that can manipulate or hijack models. In particular, it has recently been observed that LLMs can exhibit role confusion (Ye et al., 2026), where models attribute the source of text based on its style instead of its labeled role. Malicious text in tool outputs (for instance, a malicious webpage accessed by an agent) can leverage role confusion to impersonate the user, an attack we call role spoofing}. In this work, we seek to understand and mitigate role spoofing. We study how models track "who said what" in a conversation, showing that they use cues from both content (e.g., semantics and writing style) and structure (e.g., control tokens and formatting). We show that LLMs are highly susceptible to role spoofing attacks that combine both fake structure and content. Additionally, in a toy setting, we show that adversarial training which teaches the model to ignore content-based injections does mitigate content-based attacks but leaves the model susceptible to structure-based attacks. This can explain why frontier models, with increased resistance to many injection attacks, can still be susceptible to role spoofing. Finally, we propose a new method for detecting role spoofing using linear probes trained to predict roles in a conversation, and show that it is effective across different settings.

Mathematical supervision for language models is typically flattened into isolated problem-solution pairs, discarding the curricular organization and evidential structure of the original sources. We introduce TOME-Math (Textbook-Oriented Mathematical Evidence), a large-scale corpus that converts 2,118 textbooks spanning the core areas of university-level mathematics subjects into approximately 380K structured proof-supervision records while preserving chapter order, proposition-proof links, dependency references, and source provenance. Leveraging these structural signals, we explore curriculum learning across multiple mathematical subjects and characterize scaling patterns with supervision volume and source breadth. At full scale, fine-tuning on TOME-Math raises the unweighted mean score across our held-out evaluations and established public benchmarks by 16.7 percentage points over the base model, while exceeding all three public instruction-data baselines evaluated in aggregate. Our findings highlight structured textbooks as both a scalable source of mathematical supervision and an empirical framework for studying the impact of data organization on mathematical reasoning. We will release the corpus to facilitate further research on structured mathematical supervision.

The last year has seen a shift in AI-assisted mathematics, with frontier language models producing proofs of and counterexamples to long-standing open conjectures. However, studying only the current set of major breakthroughs provides an incomplete picture of LLM capabilities and the computational resources needed to achieve reported results. To address this, we introduce a new dataset, OpenConjecture, which collects conjectures from mathematics papers published on the arXiv since February 2026. We use these conjectures as a source of open mathematical problems, and apply frontier GPT models to a random sample of 200 of these conjectures over three passes using a reproducible protocol without problem-specific mathematical guidance. Rather than attempt expert verification of these candidate solutions, we analyze the types of problems for which LLMs produce solutions and the characteristics of these solutions. The models we test produce candidate solutions for roughly 60% of the conjectures, with counterexamples about 1.3 times more common than proofs. We estimate solution novelty, assess how solutions cite and relate to existing literature, and analyze whether the proposed resolution relies on either an error in or underspecification of the conjecture. We find that models sometimes propose resolutions that are outside the authors' intent (e.g., proposing the trivial group as a counterexample) and that a number of proofs follow closely from existing results, but that some resolutions exhibit at least moderate novelty. Our findings underscore the need for evaluations that go beyond correctness to assess fidelity to the intended statement, attribution, and the nature of the mathematical contribution.

Large language model (LLM) agents for personal health read wearable data and recommend, but do not learn about the individual in a way that can be audited or falsified. We present EpiCoach, an agentic system that treats one athlete, a cross-country mountain biker, as the subject of accountable N-of-1 science. Claims about the athlete live in an evidence-gated hypothesis registry: each must issue a probabilistic prediction about a future session before it occurs, and its belief moves only through computed evidence from a logged statistical fit. Predictions come from a mechanistic digital twin inferred from heart rate, GPS and barometric altitude: a lagged heart-rate response model, a fitness-fatigue model with learned time constants, and a latent technical-descending skill state, measured on discovered trail segments. The agent prescribes the next training week as a constrained experiment maximizing information gain subject to load and safety constraints, around two instrument rides. We evaluate the system two ways over eighteen months of data. A rolling-origin replay benchmark shows the twin beats standard forecasters on heart rate but not segment time, and the agentic loop matches a static model. A live prospective phase runs the weekly cycle: in its first three weeks the ledger sealed 20 predictions, scored 14, the descent forecast calibrated after one correction, the climb forecast pessimistic as the athlete improved, and the safety officer vetoed the agent twice. Every correction is preserved in the registry, a template for auditable, falsifiable personalization in digital health. We release the registry, benchmark and protocol.

The Control Barrier Function (CBF) method has been widely adopted in solving safety-critical control problems. However, the existence of a CBF is only a sufficient condition for system safety. The recently proposed Taylor-Lagrange Control (TLC) method addresses this limitation by providing a necessary and sufficient condition, but it is still vulnerable to the feasibility preservation problem (e.g., due to the inter-sampling effect when time is discretized). In this paper, we propose a robust TLC (rTLC) method to address the feasibility preservation problem and show how to use it to solve optimal control problems. Specifically, the rTLC method expands the safety function to an order higher than its relative degree using Taylor's expansion with Lagrange remainder, which allows the control to explicitly show up at the current time instead of a future time in the original TLC method. This implies that the safety constraint remains satisfied over the entire discretization time interval that follows. Moreover, the rTLC method naturally addresses the feasibility preservation problem with only a single hyper-parameter (the discretization time interval size during implementation), compared to significantly more parameters for its counterparts. Finally, we illustrate the effectiveness of the proposed rTLC method through an adaptive cruise control problem, and compare it with existing safety-critical control methods.

Low-bit quantization enables efficient deployment of large language models by reducing memory footprint and computational cost. Achieving high accuracy at low precision requires selecting quantization ranges, linear transformations, and weight rounding decisions. Existing approaches typically optimize these components independently using local reconstruction objectives, which fail to account for the varying impact of quantization errors on downstream predictions. Direct optimization of task-level metrics would provide a more faithful objective, but is challenging due to the discontinuous nature of quantization operations and the high computational cost of evaluating their downstream effects. In this work, we derive a Hessian-guided approximation of the output change induced by joint weight and activation quantization. Based on a tractable Fisher approximation, we formulate a unified post-training quantization framework that enables the joint optimization of quantization ranges, linear transformations, and weight rounding under a common output-sensitivity objective. The resulting method remains practical for modern large language models and consistently outperforms state-of-the-art transformation and rounding methods across both channel-wise and block-wise quantization settings.

Tokenization that partitions time series into subsequences has become a foundational paradigm in modern time series modeling. However, we find that current tokenization strategies inherently introduce spectral distortions, forcing the learned representations to diverge from the true underlying patterns such as trend, periodicity, and seasonality, thereby impairing model performance. Through theoretical analysis from a frequency perspective, we derive the boundary conditions under which such distortions occur. To overcome this distortion, we propose TimeFT, a nearly distortion-free frequency-based tokenizer for time series data. TimeFT obtains tokens through frequency-domain partitioning, frequency shifting, and Nyquist sampling. The method is parameter-free, incurs negligible computational complexity, and can serve as a drop-in replacement for existing tokenizers. Our extensive experiments on diverse tasks such as forecasting, classification, and anomaly detection demonstrate that TimeFT consistently and significantly improves performance.

Scaling critic capacity is a promising direction for improving off-policy reinforcement learning (RL). However, recent work shows that larger critics are prone to overfitting and instability in replay-based bootstrapped training. In this paper, we propose using Low-Rank Adaptation (LoRA) as a structural regularizer for critic learning from scratch. Our approach freezes randomly initialized base matrices and optimizes only the corresponding low-rank adapters, thereby constraining the learned weight changes to low-rank residuals. We evaluate our method on state-based continuous-control tasks, using SAC with SimbaV2 and BRC on DMC-Hard, and FastTD3 with its SimbaV2 variant on IsaacLab. Empirically, LoRA reduces critic loss during training and improves overall policy performance, achieving the best or competitive results on most tasks. Extensive experiments demonstrate that our low-rank updates provide a simple and effective form of structural regularization for critic learning in off-policy RL.

As the effects of climate change become increasingly apparent, the demand for renewable energy sources such as wind power continues to grow. However, renewables' variable and intermittent nature presents significant challenges in their integration into energy grids. Artificial intelligence (AI) has emerged as a powerful tool to address these issues. Still, its adoption in the energy sector has been hindered by the opacity of many AI models, which often function as black boxes. This paper introduces a carefully adapted GradientSHAP approach to provide interpretability for multivariate, multistep wind power forecasting -- a largely underexplored area. This capability is critical for day-ahead grid management and, to the best of our knowledge, this is the first study to apply GradientSHAP in the context of wind power forecasting. To address the inherent dimensionality, we developed novel visualizations that deliver both local and global explanations, uncovering intricate relationships between environmental factors, site-specific conditions, and temporal dynamics. While GradientSHAP is not an out-of-the-box solution, our findings demonstrate that, with thoughtful handling of SHAP values and domain expertise, it can offer valuable insights into model behaviour, supporting more informed and trustworthy decision-making. Nevertheless, its complexity poses challenges for practical implementation. Future research should focus on streamlining these interpretability methods to make them more actionable for routine deployment in critical energy applications.

Radiological risk stratification and management planning are essential downstream tasks in medical imaging. Automating these tasks is challenging because clinical guideline criteria are distributed across prose, tables, and cross-referenced definitions. We present Guideline-derived Decision Graph (GDGraph), a framework that decouples guideline compilation from case evaluation. During compilation, a large language model partitions guidelines into section-based chunks, extracts local decision subgraphs with linked definitions, and aggregates related branches into an executable decision graph. During inference, a fast System One model answers localized clinical questions while deterministic traversal resolves Boolean logic, turning opaque single-pass predictions into a traceable decision path without task-specific training. Across 347 cases spanning renal cyst, adnexal mass, and thyroid nodule guidelines, GDGraph improves System One accuracy from 57.3% to 90.8%, outperforming retrieval-augmented GPT-4o (80.1%) and graph-guided GPT-4o with chain-of-thought (82.7%) at substantially lower latency and cost. The source code will be available.

Looping in transformer models reuses weights by repeatedly applying the same transformer, or parts of it, making the model deeper without increasing its parameter count. Whether looping is useful depends on which constraint dominates: model size, training compute, or autoregressive inference efficiency. We study these trade-offs jointly in dense decoder-only transformers trained from scratch, varying which parts of the model are looped, how many loops are applied, and how information is passed between loops. Our experiments span models with up to 1B parameters, trained on up to 155B tokens with up to $1.07\times10^{21}$ FLOPs and 32 loops. We find that looping the full transformer generally gives the strongest quality at a fixed parameter budget, whereas looping a middle block of layers gives a better return when training FLOPs are constrained. Adding loops is not uniformly beneficial: gains eventually saturate, reverse, or become unstable. This motivates asking whether forcing every loop to use the same weights limits the benefit of deeper looping. We address this by adding small loop-specific low-rank adapters that improve quality, with larger gains as more loops are added. Looped transformers also suffer a decoding slowdown proportional to the number of loops. Parallel Loop Transformers address this by passing hidden states between loops across adjacent token positions, allowing loop stages to run concurrently. However, in our experiments the original formulation does not consistently retain the quality gains of ordinary looping. We find that preserving the current-token embedding and separately normalizing it and the previous-token hidden state before combining them recovers strong performance across model scales and training budgets. Together, these results show that effective looping requires matching the design to the resource constraint and inference setting.

Objectives: To evaluate the accuracy and calibration of Decision and System One models on rheumatology examination questions and diagnostic vignettes. Methods: Two benchmarks were analysed: 172 rheumatology questions from Spanish specialty-training examinations (expanded RheumaMIR dataset) in Spanish and English, and 70 English diagnostic vignettes from RheumBench with 5-18 candidate diagnoses, 52 of which included the reference diagnosis. Four System One models (Jev 1.13, Clef, Microsoft-Decision-1, Laya) and GPT-6 Luna (OpenAI Decisions API) were compared with GPT-6 Sol and two local generative models. The primary outcome was accuracy; secondary outcomes included calibration, discrimination, accuracy of answers with probability >=0.90 and language differences. Results: In RheumaMIR, Jev's accuracy was 93.0% in Spanish and 91.9% in English, below GPT-6 Sol (99.4%; Holm-adjusted P<=0.005); GPT-6 Luna reached 97.7%, Clef 91.9-93.0% and Microsoft-Decision-1 86.0-87.8%, without detectable language differences. Jev's answers with probability >=0.90 (76-77% of answers) were 98.5% correct. In RheumBench, accuracy was lower: GPT-6 Sol 76.9%, GPT-6 Luna 63.5%, Clef 59.6%, Jev 50.0% and Microsoft-Decision-1 40.4% (each System One model below GPT-6 Sol, Holm-adjusted P<=0.045; chance 9.6%). Jev became overconfident (mean probability 0.659; over/underconfidence index +0.159), and its answers with probability >=0.90 (25% of cases) were 84.6% correct, against 95.5% for GPT-6 Luna (42%). Laya performed near chance in both benchmarks. Conclusion: The best-performing System One models were highly accurate on examination questions but less accurate on diagnostic vignettes, remaining below GPT-6 Sol. Jev's high-confidence predictions were less reliable on vignettes, highlighting the need for task-specific evaluation and calibration.

Multi-agent reinforcement learning (MARL) in real-world use cases may need to adapt to external natural language instructions that interrupt ongoing behavior and conflict with long-horizon objectives. However, conditioning rewards on instructions introduces a fundamental failure mode as Bellman updates couple value estimates across instruction contexts, leading to inconsistent values when instructions interrupt macro-actions. We propose Macro-Action Value Correction for Instruction Compliance (MAVIC), which corrects Bellman backups at instruction boundaries by correcting the incoming instruction objective and restoring the continuation value under the current objective. Unlike reward shaping, MAVIC modifies the bootstrapping target itself, enabling consistent value estimation under stochastic instruction switching within a unified policy. We provide theoretical analysis and an actor-critic implementation, and show that MAVIC achieves high instruction compliance while preserving base task performance in increasingly complex cooperative multi-agent environments.

We present Vampire-Hammer, a hammer for the Lean interactive theorem prover that discharges goals using the Vampire automated theorem prover and reconstructs proofs checked by the Lean kernel. Vampire-Hammer uses the Lean-auto framework to process goals and premises before dispatching them to Vampire for proof search. Doing so, we rely on standard TPTP problem formats and annotated TSTP proofs that support proof reconstruction. With a 10-second budget on 196,083 eligible Mathlib theorems, Vampire-Hammer solves 21,158 problems not solved by other evaluated tools within the same budget.

Many everyday robot manipulation skills are affordance-dependent, with success determined by whether the robot contacts the functional object region required by the subsequent action. Current simulation data generators obtain contacts from generic grasp estimators or per-object manual contact annotations, but generic estimators rank stable grasps without task semantics and often select contacts that are misaligned with the downstream action, while manual contact annotations must be rewritten for each new object and task. To solve these challenges, we introduce AffordSim, a scalable data generator and benchmark that integrates open-vocabulary 3D affordance prediction into simulation-based trajectory generation. Given a natural-language task description, AffordSim synthesizes a task-relevant scene, emits affordance queries, grounds them on object surfaces, samples region-conditioned grasps, and selects executable candidates with motion planning. It further randomizes object pose, texture, lighting, image noise, and cross-viewpoint backgrounds for sim-to-real transfer. We instantiate AffordSim as a 50-task benchmark across diverse manipulation skills, five robot embodiments, and 500+ rigid and articulated objects. AffordSim achieves 93% of the trajectory collection success rate of manual contact annotations on affordance-critical tasks and 89% on hard composite tasks. Vision-language-action policies trained on AffordSim data transfer zero-shot to a real Franka FR3, reaching 24% average success.

Deep learning models for coronary vessel segmentation in X-ray angiography often perform poorly on data from centres that were not represented in training. Apart from differences in equipment, the labels of the largest public dataset (ARCADE) are incomplete, as only the segments defined in the SYNTAX score are annotated. In this study, we evaluated whether self-training with pseudo-labels can improve performance on external data without additional manual annotation. Pseudo-labels were generated from two sources, namely the predictions of an nnU-Net model trained on ARCADE and a contrast map obtained by subtracting a pre-contrast frame from the same sequence. The nnU-Net predictions were extended along the contrast map, and pixels detected only in the subtraction image were assigned an ignore label and excluded from the loss. Six models were trained and tested on ARCADE and on two external datasets (XCAD and XACV). All first-round models initialised with the baseline predictions performed better than both the baseline and a control model fine-tuned for the same number of epochs. The model trained on the XCAD pool improved the macro-averaged Dice score by 2.7 points (95% CI 2.3-3.2), while the control decreased it by 0.6 points. A second round of self-training did not lead to further improvement. When an external model trained on 50 fully annotated images was used to generate the initial labels, the XCAD Dice score increased from 0.623 to 0.745 without any XCAD labels, although performance on XACV did not improve because large main vessels were missed. These results suggest that the benefit of self-training depends largely on the sensitivity of the model used to generate the initial pseudo-labels.

TorchTPU is an open-source collaboration between Google and Meta that introduces a native and principled PyTorch backend for Google TPUs. It enables seamless out-of-the-box model execution and TPU migration while delivering industry-competitive inference and training performance through eager execution optimizations, torch.compile integration, and native hardware acceleration.

Power capping is a common GPU energy lever in LLM serving, and it appears to work: the cap is set, the GPU reports drawing less than it, and the energy budget is met. We show the cap does little for the phase that dominates LLM serving: autoregressive decode. Across four attention paradigms (GQA, MLA, Gated DeltaNet, and Mamba2) on an NVIDIA H200 under vLLM eager execution, decode kernels wait on HBM and the GPU idles between kernel launches, so decode draws less than half of the GPU's 700W rating and throughput stays within a few percent under every cap we set. The cap engages only when a large batch runs a long generation. Locking the SM clock instead lowers power without slowing memory-bound decode and recovers up to 32% of decode energy at minimal throughput loss. We identify three architecture-dependent frequency-scaling classes and find that, once prefill is measured without prefix caching, the recurrent architectures pay no prefill penalty: their linear-time mixing undercuts quadratic attention on long prompts, so their efficient decode adds to the prefill saving and lowers total request energy from the first output token at large batch.

Robots executing long-horizon manipulation tasks from natural-language instructions must reason about both semantic task structure and geometric feasibility. Hierarchical approaches combining Vision-Language Models (VLMs) with Task and Motion Planning (TAMP) offer a promising solution, but VLM-generated subgoals may rely on prior knowledge without sufficient observational support. This can lead to the omission of task-relevant subgoals or attempts to execute instructions whose requirements cannot be met in the environment. We propose Evidence Acquisition and Feasibility Gating (EAFG), a framework for evidence-gated task and motion planning that acquires visual evidence to specify appropriate task plans and assess whether given instructions can be fulfilled. EAFG first acquires evidence by having a VLM generate subgoals and a robot execute action sequences planned by TAMP for these subgoals. For feasibility gating, the acquired evidence is used to decide whether to proceed with task planning, acquire further evidence, or halt. When proceeding, the VLM generates task subgoals conditioned on the acquired evidence, and TAMP computes low-level actions. We evaluate EAFG in three cooking scenarios involving explicitly specified required objects, underspecified instructions, and instructions requiring an absent object. EAFG improves task completion over a VLM-TAMP baseline in the explicit and underspecified scenarios and enables appropriate halting when a required object is absent.

Large language model serving is limited by facility power. Energy per token determines how many tokens a datacenter can serve, while a latency target bounds how quickly each user receives them. During decode, every weight is read from memory for every generated token. Batching amortizes this read across users but makes no individual user faster. Speculative decoding does: a drafter proposes several future tokens, and the target model verifies them in a single forward pass that reuses the same weight read. Because every drafted token must be verified whether or not it is accepted, the energy speculation saves depends on how many drafted tokens are accepted. This saving is hard to pin down. It varies across target models from different attention families and across drafting schemes, and it depends on the text being served. Every drafter we evaluate accepts fewer tokens on conversation than on code, and every trained drafter accepts fewer on Romansh, a low-resource language, than on English. We measure speculative decoding under production serving conditions (SGLang, CUDA graphs enabled) on H100 and H200 GPUs, at batch sizes up to 64 across 5 corpora. On dense models, verification, not drafting, dominates the energy cost. The saving shrinks as the batch grows, because batching has already shared the weight read that speculation would divide among the accepted tokens. At large batch sizes, block drafters push verification past the balance point between arithmetic and memory traffic into the compute-bound regime, where the saving becomes a loss, and a drafter with low acceptance raises energy per token. Meeting a tighter latency target with speculation then costs additional energy. Larger batches lower energy per token without speculation. Speculation adds to that saving only when acceptance is high, and on the model we tested it leaves little headroom for latency-preserving DVFS.

Decoding sensory-evoked functional magnetic resonance imaging (fMRI) data is a central analytical tool in cognitive neuroscience. Here we ask whether self-supervised learning (SSL), which has been scarcely explored in this domain, can yield representations that support strong downstream performance. To do so, we adapt a joint embedding predictive architecture (JEPA) to train participant-specific encoders on brain data alone. The encoders never see the stimulus images or any representation derived from them. Applied to the Natural Scenes Dataset (NSD), we evaluate our learned brain embeddings on the downstream tasks of brain captioning and image reconstruction, as well as cross-participant generalization. Our self-supervised approach achieves competitive performance with parameter-rich supervised pipelines that are trained end-to-end with access to image and language data. We further find that encoders trained independently for different participants can be aligned fully unsupervised, using neither images nor stimuli shared between them. After alignment, a neural decoding head trained on one participant can be applied to another without fine-tuning and retains most of its within-subject performance on image reconstruction and brain captioning. By removing the need for images and shared stimuli, our approach is a step towards pooling fMRI data across participants and, eventually, across datasets.