artificialintelbulletin.com

Tag: cs.LG

  • An all-transistor physical-learning transformer can be trained to perform in-context learning

    An all-transistor physical-learning transformer can be trained to perform in-context learning

    [Submitted on 8 Oct 2026]

    View PDF

    Abstract:Most systems trained by equilibrium propagation or coupled learning are in the same class as multi-layer perceptrons: while they may be universal function approximators, they struggle to learn associative tasks which are easy for transformers. Equilibrium propagation relies on a bidirectional flow of information through the physical system between input and output. The reverse flow is broken by more complex nonlinear systems, such as those performing multiplication which is needed to express dot-product attention. Here we explicitly restore this bidirectional flow by introducing extra circuit elements for this purpose into a double or dyadic circuit. We then use these ideas to construct an attention mechanism exploiting the exponential current law of sub-threshold MOSFET devices. We show that in simulations this circuit can be trained to perform a simple in-context learning task, despite using realistic reverse components which transmit only an approximate gradient. For this training to succeed we need cross-entropy loss (not mean squared error). We generate nudges appropriate for this loss using a novel floating circuit element, based on the same MOSFET sub-circuit used for softmax. We train the resistors in this circuit using the Lion optimiser, which can be implemented using one capacitor per parameter to store local memory of past gradient estimates.

    Submission history

    From: Michael Abbott [view email]
    [v1] Thu, 8 Oct 2026 18:01:05 UTC (739 KB)

  • Data-driven Optimal Sensor Placement for Aerosol Monitoring in the UK

    Data-driven Optimal Sensor Placement for Aerosol Monitoring in the UK

    [Submitted on 8 Oct 2026]

    Authors:Talha Ansar (1), Waqar Muhammad Ashraf (2), Alejandro Coca-Castro (2), Manvendra Janmaijaya (2), Ramit Debnath (3), J. Scott Hosking (2) ((1) University of Engineering and Technology, Lahore, Pakistan, (2) The Alan Turing Institute, London, UK, (3) University of Cambridge, Cambridge, UK)

    View PDF HTML (experimental)

    Abstract:We develop a data-driven sensor-placement framework and apply it to aerosol monitoring in the United Kingdom (UK). A trained convolutional Gaussian neural process is embedded within the DeepSensor optimisation framework. Genetic optimisation with lazy evaluation and caching reduces mean computational time by 60% (10$pm$3 versus 25$pm$7 minutes) while producing sequential placement performance comparable to the greedy solver. Using the CAMS reference field to construct a retrospective oracle benchmark, Joint NLL improves by about 22% for Joint-MI-driven genetic placement after five locations for aerosol stations are identified. Seasonal and wind-regime analyses show that agreement between model-based criteria and oracle benchmarks varies with meteorological transport conditions. These results show a computationally efficient approach for data-informed expansion of environmental observing systems.

    Submission history

    From: Talha Ansar Ta [view email]
    [v1] Thu, 8 Oct 2026 19:25:38 UTC (1,478 KB)

  • ABLEIST: Intersectional Disability Bias in LLM-Generated Hiring Scenarios

    ABLEIST: Intersectional Disability Bias in LLM-Generated Hiring Scenarios

    [Submitted on 13 Oct 2025 (v1), last revised 8 Oct 2026 (this version, v2)]

    View PDF HTML (experimental)

    Abstract:Large language models (LLMs) are increasingly under scrutiny for perpetuating identity-based discrimination in high-stakes domains such as hiring, particularly against people with disabilities (PwD). However, existing research remains largely Western-centric, overlooking how intersecting forms of marginalization–such as gender and caste–shape experiences of PwD in the Global South. We conduct a comprehensive audit of six LLMs across 2,820 hiring scenarios spanning diverse disability, gender, nationality, and caste profiles. To capture subtle intersectional harms and biases, we introduce ABLEIST (Ableism, Inspiration, Superhumanization, and Tokenism), a set of five ableism-specific and three intersectional harm metrics grounded in disability studies literature. Our results reveal significant increases in ABLEIST harms towards disabled candidates–harms that many state-of-the-art models failed to detect. These harms were further amplified by sharp increases in intersectional harms (e.g., Tokenism) for gender and caste-marginalized disabled candidates, highlighting critical blind spots in current safety tools and the need for intersectional safety evaluations of frontier models in high-stakes domains like hiring.

    Submission history

    From: Hayoung Jung [view email]
    [v1] Mon, 13 Oct 2025 04:18:23 UTC (1,493 KB)
    [v2] Thu, 8 Oct 2026 22:37:37 UTC (1,389 KB)

  • Near-Minimax-Optimal Rates for Asynchronous TD Learning with Markovian Data

    Near-Minimax-Optimal Rates for Asynchronous TD Learning with Markovian Data

    [Submitted on 30 Sep 2026 (v1), last revised 9 Oct 2026 (this version, v2)]

    View PDF HTML (experimental)

    Abstract:We study the last iterate of standard importance-weighted temporal-difference (TD) learning from a single trajectory of a finite Markov decision process. The trajectory follows a behavior policy $b$ with an irreducible, possibly periodic state chain; a target policy $pi$ covered by $b$ is evaluated with action importance ratios bounded by $varrho$. Write $H=(1-gamma)^{-1}$, with $mu_{min}$ the minimum stationary probability and $mathfrak h_star$ the largest expected hitting time of the reverse behavior state chain. We prove that the last iterate achieves sup-norm error at most $varepsilon$ with high probability after $widetilde O(varrho H^3/(mu_{min}varepsilon^2)+mathfrak h_star)$ transitions for $0

    Submission history

    From: Yang Peng [view email]
    [v1] Wed, 30 Sep 2026 03:31:05 UTC (44 KB)
    [v2] Fri, 9 Oct 2026 17:16:04 UTC (61 KB)

  • Urban Power Grid Topology and Hierarchy Identification from Open Data

    Urban Power Grid Topology and Hierarchy Identification from Open Data

    [Submitted on 19 Jun 2026 (v1), last revised 9 Oct 2026 (this version, v2)]

    View PDF HTML (experimental)

    Abstract:Understanding the complex topology and hierarchy of urban power grid is crucial for energy prognosis, power flow management, and system resilience analysis. However, detailed grid information remains largely proprietary. This information, nevertheless, is crucial especially for analyzing the last-mile distribution networks connecting individual buildings. This paper addresses this challenge by developing an open-data-driven framework to identify urban power grid topology, from high-voltage transmission down to individual building connections. We integrate public infrastructure data (power-lines, substations, transformers, poles) to map the high and medium-voltage grid skeleton. We then leverage geospatial machine learning on OpenStreetMap building data to cluster loads of building energy demand. Upon the clustering, we develop the physical topology of the final distribution lines linking the clustered buildings and low-voltage distribution grids. Our derived grid topology incorporates physical and geographical constraints like voltage level and road networks, thus leading to reasonable topology and hierarchy of grid networks. We apply the developed framework to the districts of Alna in Oslo, Norway, and Waiheke Island in New Zealand, and we reconstruct the complete grid topology that connects all the buildings, power lines, and electricity infrastructure assets. With the developed framework, we provide a critical tool that facilitates power system analysis, e.g., power flow optimization, cascading failure simulation, and grid resilience against the penetration of distributed renewable generation. This work also opens the opportunity to build energy digital twins that fuse power assets and grid topology, geographic constraints, and fine-grained power demand profiles.

    Submission history

    From: Shiliang Zhang [view email]
    [v1] Fri, 19 Jun 2026 11:51:38 UTC (12,892 KB)
    [v2] Fri, 9 Oct 2026 13:49:37 UTC (13,449 KB)

  • S-Space: Exploring Spatial Workspace in Multimodal Language Models

    S-Space: Exploring Spatial Workspace in Multimodal Language Models

    [Submitted on 9 Oct 2026]

    View PDF HTML (experimental)

    Abstract:Multimodal language models (MLLMs) exhibit promising spatial reasoning capabilities, yet the internal mechanisms supporting them remain poorly understood. We uncover S-Space, a linear representation subspace in which object-token representations encode continuous coordinates along horizontal, vertical, and distance axes. Although we identify these axes by differentiating spatial-answer scores with respect to object-token activations, S-Space is intrinsic rather than induced by specific data or prompts, remaining readable under non-spatial questions. We show that S-Space functions as an internal spatial workspace of MLLMs. Perception encodes object locations into it, forming spatial representations that can be directly read out to support accurate spatial judgments. Internal reasoning transforms it for changing viewpoints. Verbal responses selectively access it, evidenced by causal interventions that alter spatial judgments while largely preserving non-spatial responses. Case studies further show that S-Space assigns locations to unseen entities and the observer, and connects physical directions with abstract linguistic meanings, suggesting both the capabilities and limitations of large-scale language training. Finally, we use S-Space as a diagnostic tool for spatial reasoning failures. Direction-word readouts reveal systematic coupling between cardinal and image-relative reference frames. More importantly, a perception-computation decomposition exposes a key bottleneck: MLLMs can form capable spatial representations, yet fall short in the spatial transformations required to reason reliably across viewpoint changes.

    Submission history

    From: Jialong Wu [view email]
    [v1] Fri, 9 Oct 2026 12:48:41 UTC (13,229 KB)

  • DiffusionART: Efficient, Stable and Scalable Reinforcement of Diffusion Models

    DiffusionART: Efficient, Stable and Scalable Reinforcement of Diffusion Models

    [Submitted on 8 Oct 2026]

    View PDF HTML (experimental)

    Abstract:Online reinforcement learning (RL) fine-tunes diffusion models with black-box rewards, but reverse-process methods such as Flow-GRPO are limited in efficiency by poor credit assignment, while forward-process methods such as DiffusionNFT are efficient yet unstable without carefully tuned exponential-moving-average (EMA) off-policy training. We show that NFT-style objectives contain a hidden forward–reverse consistency force that joint positive–negative training cancels only partially, and that EMA stabilizes training through restoration rather than off-policy rollouts. We introduce DiffusionART (Diffusion Reinforcement with Aggregation-First Reward Tilting), which aggregates each prompt’s rewards into a shared reward-improving direction for reverse-process states, removing the consistency force by construction, and adds a trust-region-masked second update for drift-adaptive restoration without EMA tuning. It requires no differentiable reward model, remains effective with fewer samples per prompt, and supports pairwise reward models (DiffusionART-Pairwise). Across image and video generation, DiffusionART trains efficiently and stably without per-task tuning. In particular, on HunyuanVideo-13B with equally weighted visual and motion quality rewards, DiffusionART reaches the late-stage mean reward levels of DiffusionNFT and Flow-GRPO-Fast with 12.02 and 11.72 times fewer GPU hours, respectively, while achieving 28.8% and 53.0% higher mean training rewards.

    Submission history

    From: Zhenglin Wan [view email]
    [v1] Thu, 8 Oct 2026 18:01:44 UTC (17,685 KB)

  • Recurrent Harness for Agentic Continual Learning

    Recurrent Harness for Agentic Continual Learning

    [Submitted on 8 Oct 2026]

    View PDF HTML (experimental)

    Abstract:Language model agents increasingly operate over long interaction streams, requiring online adaptation to distribution shifts through continual learning. However, existing agent harnesses typically either evolve their states only through forward information flow or rely on additional replay or validation data for harness optimization. To address this, we propose ReHarness, a recurrent harness framework for agentic continual learning that complements forward read and write with backward revision under a strictly online streaming protocol. We ask what information could have been captured differently in the harness state to better inform the current instance in the stream. Specifically, after each instance, we leverage the resulting trajectory as feedback to revise the reflections retrieved for that instance, thereby propagating feedback backward through the textual harness state. Across three continual learning benchmarks and three language model backbones, ReHarness consistently outperforms strong raw-context baselines, memory- and reflection-based methods, and prompt optimization approaches. Further analysis shows that ReHarness produces source-grounded and meaningful revisions, corrects overgeneralized or outdated experience under distribution shifts, and improves both stability and plasticity during continual learning.

    Submission history

    From: Yuxin Xiao [view email]
    [v1] Thu, 8 Oct 2026 19:44:43 UTC (422 KB)

  • Behind-the-Meter Photovoltaic Visibility from Net Smart Meters: Deployment Regimes and Operational Insights

    Behind-the-Meter Photovoltaic Visibility from Net Smart Meters: Deployment Regimes and Operational Insights

    [Submitted on 8 Oct 2026]

    View PDF HTML (experimental)

    Abstract:Distribution operators need visibility of behind-the-meter photovoltaic (PV) generation, yet most residential customers are observed only through net smart meters. Deep-learning-based PV disaggregation can restore this visibility, but its operational value depends on whether the model serves known customers, new customers, future periods, or new regions. We quantify this dependence using four deployment regimes that separate household transfer from temporal extrapolation, applied to Ausgrid smart-meter data with cross-dataset adaptation to the Pecan Street data. Using a fixed training protocol, we benchmark representative deep sequence architectures for PV disaggregation under regime-matched evaluation. At a fixed 48-hour context length, daylight mean absolute error (MAE) of the best model rises from 0.104~kW on seen households in the future test period to 0.185~kW on unseen households over the same period, and under a fixed training contract the deployment regime explains far more of the error variation than model choice. Under target-domain normalization, fine-tuning on five target-region households reduces source-model transfer error by 28%–36%. Long input windows help known-customer extrapolation, while their new-customer benefits vary by model. These findings suggest regime-matched error budgets, limited target supervision for model adaptation in new regions, and use-case-dependent context selection for energy data analytics.

    Submission history

    From: Jack Zheng [view email]
    [v1] Thu, 8 Oct 2026 07:37:32 UTC (172 KB)

  • EmoGavel: Grounding-Aware Reinforcement Learning with Verifiable Rewards for Multimodal Emotion Preference Learning

    EmoGavel: Grounding-Aware Reinforcement Learning with Verifiable Rewards for Multimodal Emotion Preference Learning

    [Submitted on 9 Oct 2026]

    View PDF HTML (experimental)

    Abstract:Multimodal emotion preference learning uses pairwise comparisons to identify which open-ended emotion descriptions align more closely with human judgments. However, existing methods primarily focus on the final preference decision and provide little explicit supervision for localizing and correcting erroneous content. To address this limitation, we propose EmoGavel, a Grounding-Aware reinforcement learning framework with Verifiable rewards for multimodal Emotion preference Learning. We first introduce grounded supervised fine-tuning (Grounded SFT), which exploits controlled-error construction information to jointly learn preference prediction, error localization, repair, and missing-evidence recovery. We then optimize these verifiable outcomes with grounding-aware group relative policy optimization (GA-GRPO), combining preference-gated grounding rewards with dynamic zero-variance rescue to prioritize preference correctness and recover learning signals from all-wrong groups. Experiments on EmoPrefer and controlled-error evaluation sets show that EmoGavel improves both natural preference prediction and controlled-error discrimination while maintaining strong error-grounding performance. Our code and model checkpoints will be released once the paper is accepted.

    Submission history

    From: Zilong Huang [view email]
    [v1] Fri, 9 Oct 2026 10:28:54 UTC (801 KB)