arXiv:2606.15307v1 Announce Type: new Abstract: Hateful and propagandistic memes exploit the interplay between images and text to convey harmful intent that neither modality reveals alone. Although thinking-based multimodal large language models (MLLMs) have advanced vision-language understanding, their application to meme content moderation remains underexplored. We propose a reinforcement learning-based post-training method that improves classification performance and reference-based explanation quality in thinking-based MLLMs via task-specific rewards and Group Relative Policy Optimization (GRPO). Concretely, we (i) conduct a systematic empirical study of off-the-shelf MLLMs for hateful and propagandistic meme understanding across English and Arabic benchmarks, (ii) extend existing meme datasets with weakly supervised chain-of-thought (CoT) rationales via distillation and multi-LLM fine-grained propaganda annotations, (iii) introduce a GRPO-based objective with thinking-length regularization that jointly optimizes classification accuracy and explanation quality, and (iv) investigate self-supervised GRPO on unlabeled memes using consensus-based pseudo-labels. Experiments on the Hateful Memes and ArMeme benchmarks show that our approach improves over previously reported results on FHM accuracy (up to +2.1%, from 79.9% to 82.0%) and on ArMeme macro-F1 (up to +7.6 points, from 0.536 to 0.612 with explanations; +6.1 compared to the original ArMeme benchmark), while also generating natural-language explanations. On ArMeme, sequence-classification baselines remain stronger in terms of raw accuracy, whereas our approach provides more balanced per-class performance along with explanations. We publicly release our code, data extensions, and evaluation resources.
Science Journals
arXiv:2606.15308v1 Announce Type: new Abstract: While multimodal large language models (MLLMs) have shown strong visual reasoning abilities, serving a large model for every query is computationally expensive. MLLM cascades mitigate this cost by first querying a weak but cheaper model and deferring to a strong model when the weak model's output is unconfident. However, since the weak model's confidence directly controls compute allocation, these systems expose a new attack surface: an adversary can manipulate confidence so that their queries are consistently deferred to the strong model. Motivated by this vulnerability, we introduce the Forced Deferral Attack (FDA), an adversarial image attack that lowers the weak model's confidence and causes cascades to route queries to the strong model. FDA learns a universal border trigger by optimizing a temperature-flattened objective. This objective pushes the weak model's token distribution on triggered inputs toward less concentrated targets constructed from its clean responses. Across datasets, model families, and deferral metrics, FDA consistently increases strong-model routing while outperforming image-perturbation and prompt-injection baselines. These results show that MLLM cascades are vulnerable to attacks that manipulate compute allocation, forcing unintended strong-model usage without directly targeting answer correctness.
arXiv:2606.15309v1 Announce Type: new Abstract: Linear Variable Differential Transformers (LVDTs) are widely used as high-precision, contactless displacement sensors in industrial, metrological, and scientific applications. Their performance is typically characterised only within the central linear operating region, whereas their behaviour across large displacements, where geometric and electromagnetic effects introduce significant non-linearity, remains poorly researched. In this work, we present a comprehensive analysis of the full-range response of an LVDT, spanning its entire mechanical stroke. Using a combination of custom-developed finite-element modelling pipeline and dedicated laboratory measurements, we demonstrate that the LVDT response comprises several distinct dynamical regimes. We introduce an analytically unified expression that accurately reproduces the measured response over all displacement scales, including linear and non-linear ranges, capturing the underlying physical features of the device. The model achieves high fidelity across the full range and provides closed-form first and second derivatives, enabling unambiguous displacement reconstruction, even in the non-linear regime where the voltage is multivalued. The derivative structure further clarifies the contribution of geometric coupling, noise-dominated central behaviour, and envelope decay. This study establishes, for the first time, a systematic framework for modelling, interpreting, and utilising the full-range behaviour of LVDTs. It offers guidance for systems that undergo large quasi-static excursions, overload recovery, or long-range alignment.
arXiv:2606.15320v1 Announce Type: new Abstract: Multimodal large language models have made rapid progress in video temporal grounding, yet real-world applications routinely require localizing every event that satisfies compositional temporal and spatial conditions. Existing benchmarks fall short: they localize only a single moment per query, count without temporal conditions, or treat grounding and counting as disjoint tasks. We introduce CoMET-Bench for Conditional Multi-Event Temporal Grounding in long-form video, comprising 2789 queries over 600 videos averaging 33.8 minutes across five real-world domains, with each query composed from 4 temporal conditions, 3 spatial conditions, and a dedicated negative-query subset. We further propose a unified evaluation protocol jointly measuring counting, grounding, and negative-query recognition, including a new Rejection-F1 metric that prevents trivial gaming by lazy "always-empty" models. Benchmarking a broad suite of MLLMs, agent-based, and grounding-specialized methods reveals that existing approaches remain far from solving this task. Building on these findings, we propose CoMET-Agent, a training-free agentic framework that reformulates the task as structured search-and-aggregate, improving F1@0.5 by 6.1% over GPT-5 purely through structural reasoning. Failure analysis further surfaces three open directions: fine-grained entity tracking, position-uniform retrieval, and causal event pairing.
arXiv:2606.14666v2 Announce Type: replace Abstract: We give a brief exposition of a result of Song, Nguyen, and Lin (2026) that every election (with ranked preferences) has a Condorcet winning set of at most five candidates.
arXiv:2606.15330v1 Announce Type: new Abstract: Short-video platforms now expose clickable search entries beneath the video player, enabling users to easily express content-induced search intent. However, conventional query recommendation systems on short-video platforms suffer from latency constraints and objective misalignment, while recent generative approaches struggle with noisy content-side metadata and preference drift. To address these issues, we propose OneBar, an end-to-end generative framework for real-time query recommendation for E-Commerce video feeds. OneBar features three key innovations: (1) a collaborative-multimodal intent grounding module that fuses multimodal video understanding and behavior-derived collaborative anchors; (2) a Unified End-to-End architecture equipped with a prompt-compression mechanism for efficient online serving; and (3) a progressive preference learning strategy for efficient preference-internalization, which internalizes hierarchical behavior preferences into the generative policy, eliminating the need for a separately trained reward model. Compared with online base, OneBar increases Query Exposure by 16.91\% and Query Click by 18.68\%, while maintaining a slight Query CTR gain of 0.19\%. The additional search traffic further contributes to 20.36\% more guided orders and 21.67\% higher GMV.
arXiv:2606.15327v1 Announce Type: new Abstract: Diffusion Language Models (DLMs) have demonstrated strong scaling capacity as alternatives to autoregressive language models. However, their performance is highly sensitive to the choice of transition kernels, and poorly designed kernels can lead to issues like training instability, slow convergence, and biased sampling. In this paper, we study this sensitivity through a principled analysis of generalization error and identify three critical factors: asymptotic bias (difficulty in approximating the posterior distribution), exposure bias (error propagation during sampling), and optimization variance induced by kernel dispersion. We further compare different transition kernels: masking diffusion yields sparse and easier posterior-approximation targets, while uniform diffusion provides stronger sampling-side repair but induces harder approximation. Motivated by this trade-off, we revisit a previously overlooked variant, semantic DLM (SemDLM), where the transition kernel corrupts tokens to neighborhoods that are semantically similar. Our theory suggests that SemDLM can serve as a plausible middle ground by reducing the posterior approximation difficulty of uniform diffusion while retaining repair ability. However, we find that SemDLM suffers from a semantic basin problem, where sampling repeatedly stays within a semantic region and produces low-diversity text. To address this, we propose SemDLM+, which adds a global transition and a semantic-frequency penalty during sampling. Experiments on LM1B and OpenWebText show that SemDLM+ improves training dynamics and achieves competitive language modeling and generation quality with satisfactory diversity.
arXiv:2606.15333v1 Announce Type: new Abstract: LLM unlearning has emerged as a cost-effective alternative to full retraining for removing hazardous knowledge from pretrained models while preserving general utility. Recent RL-based methods such as RULE reformulate unlearning as learning a refusal behavior, but their on-policy optimization repeatedly samples from the same forget and retain/boundary prompts throughout training. We identify a critical inefficiency in this process: easy cases quickly converge and provide little useful gradient signal, while hard cases near the forget/retain boundary continue to produce low-reward rollouts that are discarded after a single use. To address this issue, we propose ReRULE, an off-policy replay enhancement for reinforcement unlearning. ReRULE stores low-reward hard-case rollout groups in a replay buffer during early GRPO training and reuses them in later stages through importance-sampled off-policy updates, redirecting computation toward boundary cases that still require learning. Theoretically, we show that ReRULE yields a tighter hard-case convergence bound than pure on-policy RULE. Empirically, ReRULE improves MUSE-Books Retain Quality from 46.3 to 56.2 while adding only 5--11% training time across benchmarks. Its limited improvement on the simpler TOFU setting further supports the intended conditional behavior: replay is most beneficial when the hard/easy disparity is pronounced.
arXiv:2606.15335v1 Announce Type: new Abstract: When distributed agents exchange text across organizational boundaries, privacy leakage arises not only from explicit identifiers but also from distributional signatures such as formatting conventions, vocabulary choices, and syntactic patterns. We propose DiSan(Disentangled Sanitization), a privacy-preserving sanitization framework and a built-in component of Intern-Shannon for multi-agent collaboration. DiSan uses a two-stream encoder to factorize text into a source-invariant role subspace that preserves task semantics and a source-identifying style subspace that remains local. Federated proto-type alignment and adversarial regularization enable joint training without centralizing raw text. Experiments show that identifier-level masking is insufficient: masking 19.2% of tokens reduces TF-IDF stylometric attribution by only 18.6%. By contrast, DiSan reduces answer-level PII exposure by 20 times while maintaining 83% answer faithfulness on a distributed multi-agent RAG benchmark, and lowers Enron stylometric attribution by 73.2% under TF-IDF and 70.6% under a neural probe.
arXiv:2606.15338v1 Announce Type: new Abstract: RGB sim-to-real for deformable manipulation has remained largely unsolved without real-world fine-tuning. We present SimWeaver, which trains zero-shot RGB VLA policies on 200 simulated demonstrations per task, reaching above 80% per-task and 91% average real-world success across 5 diverse deformable tasks including plastic-bag manipulation, without teleoperation or per-task calibration. SimWeaver combines a reliable measurement-backed simulator (SimWeaver-Sim) with an extensible asset framework supporting single-image generation(SimWeaver-Asset), a deterministic topology-aware trajectory synthesizer (SimWeaver-Syn), and a sim-to-real protocol with ISP-aware photometric augmentation (SimWeaver-Real). On silk grasping, the sim-trained policy reaches 100% under visual distribution shifts where real-data baselines drop to 9-70%, at two orders of magnitude lower per-trajectory cost. We will release SimWeaver and a representative asset subset. Project page: https://simweaver.github.io/
arXiv:2606.15358v1 Announce Type: new Abstract: Co-creative AI research increasingly seeks methods capable of representing how interaction dynamics evolve through time. While many existing approaches focus on observable interaction characteristics, interaction metrics, behavioral coding schemes, or activity traces, these methods often struggle to capture higher-order interaction dynamics, including how collaborative processes reorganize, stabilize, regulate, and evolve through time. This paper introduces Cognitive Trajectory Modeling (CTM) as a cognitive theory of interaction dynamics that conceptualizes cognition, interaction, and creative processes as temporally organized trajectories unfolding across cognitively meaningful attractor landscapes. CTM builds upon the theoretical foundations of the Enactive Model of Creativity and Creative Sense-Making (CSM), revisiting the role of sense-making curves and cognitive trajectories in representing co-creative interaction dynamics. We formalize this perspective through the Cognitive Trajectory Principle, which states that temporal representations are only theoretically interpretable as cognitive trajectories when their underlying states possess directional cognitive meaning. Building on this principle, CTM generalizes the notion of cognitive trajectories beyond any particular coding scheme and provides a broader framework for modeling interaction dynamics through trajectories unfolding across meaningful attractor landscapes. We further distinguish cognitive trajectories from interaction traces and situate CTM within a broader hierarchy of cognitive, interaction, and domain dynamics. More broadly, we argue that understanding co-creative systems requires methods capable of modeling how cognition and interaction dynamics unfold through time. CTM provides a foundation for studying interaction dynamics across co-creative AI and human-AI interaction.
arXiv:2606.15363v1 Announce Type: new Abstract: Self-improvement in AI agents has emerged as a key research frontier: systems that modify their own prompts, workflows, and decision rules based on accumulated operational experience. The state-of-the-art Self-Harness framework [1] achieves 14--21% improvement on Terminal-Bench-2.0 by mining failure clusters and patching the agent harness. However, Self-Harness optimises only one dimension -- the prompt harness -- leaving behavioural principles and workflow topology unchanged. We propose APEX (Adaptive Principle EXtraction), a three-layer co-evolution framework that simultaneously evolves: (L1) the harness via failure-mode patching, (L2) behavioural principles via success-trace distillation [2], and (L3) the agent workflow topology via structural fitness-based selection [6]. We implement APEX on Joe [13], a production-grade super AI Agent built on NVIDIA Nemotron and designed as an Edge AI Agent Factory for the NVIDIA Agent Challenge 2026, managing a 15-node compute fleet using 114 real task traces collected over 18 days. APEX achieves an APEX Health Score of 0.570 (+90% vs. baseline 0.300) in a single evolutionary run, distilling 6 novel reusable principles and selecting a research-first workflow topology scoring 0.900 (+20%). Our results demonstrate that multi-dimensional co-evolution substantially outperforms single-axis harness optimisation, at a cost of only 4 LLM calls (~270 s) on a local qwen2.5-coder:32b instance.
arXiv:2606.15373v1 Announce Type: new Abstract: This paper presents a hybrid model-based and model-free framework for active multi-view target recognition using forward-looking sonar. A convolutional neural network (CNN) provides data-driven observation likelihoods, while Radon-based orientation estimation enables viewpoint-aware sensing without requiring angle annotations. During training, an information-gain-based reward guides a Proximal Policy Optimization (PPO) agent to learn a belief-aware viewpoint selection policy offline. At deployment, the learned policy performs real-time viewpoint selection using only CNN-based belief updates, eliminating the need for computationally expensive online POMDP tree search. Experiments on a marine-debris forward-looking sonar dataset demonstrate that the proposed approach achieves competitive recognition accuracy while reducing sensing steps and motion cost compared to model-based baselines.
arXiv:2606.15379v1 Announce Type: new Abstract: Covering codes for insertions and deletions arise naturally in the study of synchronization errors and differ substantially from their classical counterparts in the Hamming metric. In this paper, we study covering codes under insertion and deletion operations. We first show that, in contrast to the equivalence between insertion and deletion correction, insertion covering and deletion covering are not equivalent. We then develop bounds and constructions for insertion and deletion covering codes, with particular emphasis on the large-alphabet regime. For insertion covering codes, we extend a recent combinatorial approach for single insertions and establish a new lower bound for arbitrary fixed insertion radius. For deletion covering codes, we relate the problem to hypergraph covering and prove that the elementary counting lower bound is asymptotically tight when the alphabet size tends to infinity. We further provide a construction of asymptotically optimal non-binary single-deletion covering codes by using differential Varshamov--Tenengolts (VT) codes together with a completion argument. In addition, we study covering codes for burst deletions. We prove that binary differential VT codes are not only capable of correcting two-burst deletions but also have the corresponding covering property, and hence form binary perfect codes for two-burst deletions. Finally, we extend this construction to non-binary alphabets and obtain explicit $q$-ary two-burst-deletion covering codes.
arXiv:2606.15340v1 Announce Type: new Abstract: In this work, we analyze the conforming and $C^0$-non-conforming Virtual Element Method for a fourth-order Steklov eigenvalue problem on a generally shaped, possibly nonconvex, polygonal domain. By employing an {\it enriching } operator, we derive the convergence analysis using the discrete $H^2$ seminorm, and the $H^1$ and $L^2$ norms. We use the Babu\v{s}ka--Osborn spectral theory \cite{BO} to prove that the numerical scheme approximates the spectrum without introducing any spurious eigenvalue. Moreover, we derive the optimal order of convergence for eigenfunctions and double order for eigenvalues. We assess the performance of the method on several numerical tests using different families of polygonal meshes.
arXiv:2606.15391v1 Announce Type: new Abstract: To address the urgent need for multi-channel high-speed electrical interfacing of thin-film lithium niobate (TFLN) photonic circuits, we realize a flip-chip packaging platform capable of simultaneously delivering 13 high-speed and 32 low-speed electronic signals to a centimeter-sized TFLN chip. The platform exhibits low flip-chip bonding loss and low inter-channel crosstalk over a broad bandwidth up to 50 GHz. Leveraging this packaging platform, we demonstrate high-speed electrical interfacing with two proof-of-concept TFLN photonic circuits, namely a 2x8 optical switch and an electro-optic comb-based transmitter. The switch achieves arbitrary 8-channel routing with ~3 dB insertion loss, < -20 dB crosstalk, and an equipment-limited switching time of <= 34 ps. The transmitter circuit includes a 50 GHz electro-optic comb generator with 2.8-dB flatness, a tunable microring to arbitrarily filter one comb line, and a modulator for data transmission at 20 Gbit/s. The packaging platform could significantly advance large-scale TFLN circuits in optical communications, microwave photonics, and photonic computing.
arXiv:2606.15396v1 Announce Type: new Abstract: Malicious content generated from large language models (LLMs) could pose severe safety risks and ethical concerns. While existing LLM safety guardrails excel in English or multilingual settings, they lack adaptation to Chinese-specific regulatory policies, cultural context and linguistic nuances, failing to support fine-grained risk classification for diverse deployment needs. In this paper, we introduce a 5-macro, 31-micro category fine-grained risk taxonomy for Chinese scenarios, and build CHILLGuard: a dedicated Chinese LLM content safety guardrail. To address the critical scarcity of high-quality annotated Chinese safety data, we propose a scalable multi-stage data construction pipeline: we expand multi-source corpus via retrieval-augmented generation, generate implicit harmful samples through prompt engineering rewriting, and refine high-quality data via multi-model voting-based label calibration. Based on this, we build CHILLGuardTrain, a large-scale training set with 405,007 samples, and CHILLGuardTest, a rigorously curated annotated test set with 51,745 samples. We then train CHILLGuard on CHILLGuardTrain under a generator-classifier collaborative framework via Model-aware Direct Preference Optimization. Extensive experiments under multiple settings demonstrate the state-of-the-art performance of CHILLGuard, e.g., a 15.92% improvement of F1 score over Qwen3Guard-8B-Strict on our benchmark. We will release our resources at https://github.com/cswbyu/CHILLGuard.
arXiv:2606.15404v1 Announce Type: new Abstract: We study the online fair division of indivisible items with additive utilities, where items arrive sequentially and must be irrevocably allocated upon arrival. Considering various fairness notions, we focus on designing online algorithms that produce fair or approximately fair allocations for any instance. We measure algorithm performance using the competitive ratio, defined as the worst-case ratio between the fairness guarantee achieved by the online algorithm and that of an optimal offline allocation with full knowledge of future arrivals. We examine a broad spectrum of models, including the allocation of goods or chores, normalized versus non-normalized utilities, and identical versus general utility functions. We address the majority of the unresolved cases by providing online algorithms or proving the limits of the competitive ratio achievable by online algorithms. In most cases, the algorithms are shown to be optimal.
arXiv:2606.15350v1 Announce Type: new Abstract: Many problems in modern scientific computing are challenging because of a \emph{curse of dimension}, where their mathematical formulation involves objects whose dimension is \emph{exponential} in the nominal "size" of the problem. Tensor networks can provide a compact representation for exponentially large vectors and matrices that arise in applications, but these representations do not always lead to reliable algorithms. This paper develops and analyzes techniques for randomized dimension reduction of tensor network data. These techniques support a suite of efficient algorithms for provably solving exponential-scale linear algebra problems, including trace estimation and eigenvalue approximation. The paper includes several stylized illustrations from quantum many-body physics with ambient dimension up to $2^{200}$.
arXiv:2606.15376v1 Announce Type: new Abstract: Multi-agent LLM systems -- coding agents, devops agents, document agents -- now routinely run several agents in parallel against the same git tree, Kubernetes cluster, or document. As soon as two of them mutate shared state, they enter the regime classical concurrency control has studied for decades, but classical mechanisms fit LLM agents poorly. A single agent transaction spans minutes of inference, read sets are broad and opaque rather than statically inferable, and the live state agents act on admits neither fork nor buffer, so writes take effect the moment they execute. Locks block long inference intervals; OCC abort-and-retry discards minutes of work on every conflict. This paper builds concurrency control on a capability classical transactions lack: the LLM inside each agent can judge whether a conflicting write invalidates its plan, and can repair exactly the operations that depended on it. Control therefore turns advisory: the runtime informs, the agent repairs. Our protocol, MTPO (Monotonic Trajectory Pre-Order), fixes a serialization order at launch, serves each read the order-filtered value, and applies writes speculatively in place; a one-way notification asks an affected reader to re-judge and patch its plan, while the framework mechanically undoes and reorders misplaced writes through the saga-style inverse each tool registers in advance. At quiescence the run is serializable in the pre-decided order. We realize MTPO as CoAgent, toolcall middleware whose privileged ToolSmith grows footprint-declared, undoable tools online. On ten contended workloads, CoAgent stays within 5\% of serial correctness at a $1.4\times$ speedup and near-serial token cost, where 2PL and OCC surrender nearly all concurrency gains; on a bash-only target system, it grows a 25-tool library online and lifts the task pass rate from 45/71 to 63/71 at $0.80\times$ the time and $0.86\times$ the cost.
arXiv:2606.15384v1 Announce Type: new Abstract: The advent of Large Language Models has catalyzed the emergence of interactive Business Intelligence (BI) systems. Although commercial BI products increasingly adopt semantic layers paired with natural language interfaces, they predominantly rely on manual configurations to define metrics and dimensions. Real-world deployments face critical challenges: (a) frequent JOIN operations degrade the accuracy of SQL generation; (b) wide schemas exacerbate the challenge of schema linking; and (c) the generation of dialect-specific queries and the accurate support for multi-round dialogues incur high computational costs and yield limited accuracy. We introduce CoeusBI, an industrial-scale interactive BI system that addresses these barriers through a novel Dual-Agent Architecture paired with a Hierarchical Schema Linking module: (1) an offline View Generation Agent that utilizes error-feedback to autonomously convert complex JOIN queries into simple single-view queries, which eliminates the need for manual semantic modeling; (2) a Hierarchical Schema Linking module that leverages vector retrieval over views to handle exceptionally wide schemas efficiently; and (3) a dynamic Routing Agent that evaluates dialogue contexts to route queries, dynamically invoking either the synthesis of new intermediate representations or targeted modifications of existing ones, before compiling the unified representation via a deterministic SQL compiler that is agnostic to dialects. Extensive experiments on both public datasets and production datasets demonstrate that CoeusBI achieves significant improvements in query accuracy, token efficiency, and user satisfaction relative to existing methods. CoeusBI is deployed as a standalone service on the data platform of Baidu and is widely used across multiple business lines supporting thousands of users daily, thereby evidencing strong practicality and scalability.
arXiv:2606.15390v1 Announce Type: new Abstract: LLM agents can improve without weight updates by accumulating natural-language skills from experience, but current systems entrust every decision about which skills to keep and how to apply them to LLM judgment alone. We argue that this conflates two distinct roles: generating a skill from experience is a creative act that judgment handles well, while deciding whether that skill actually helps requires empirical evidence across many tasks. Measuring per-skill causal contributions via randomized masking, we find that skill libraries exhibit pervasive causal heterogeneity: individual skills routinely help on some task types while hurting on others, yet their opposing effects cancel in aggregate, making them invisible to global curation methods. We propose ASSAY, a framework that separates generation from curation: it computes a per-skill causal attribution on a small development set, restructures the library offline, and suppresses skills with negative predicted effect for each test task. Across seven base models spanning four providers and two benchmarks (AppWorld and tau-bench), ASSAY consistently improves over prior skill-curation approaches. On AppWorld's hardest split, DeepSeek-V3 achieves 69.3% task-goal completion (47.4% relative improvement), a new state of the art among all published methods including weight-tuned approaches. On tau-bench retail, GPT-4.1 improves by 8.7% relative, advancing past o4-mini, o1, and GPT-4.5 on the public leaderboard without any weight modification. Ablation traces the dominant gain to per-task masking, confirming that the bottleneck is matching skills to tasks at inference time, not removing bad skills globally. Code is available at https://github.com/aiming-lab/assay.
arXiv:2606.16016v1 Announce Type: new Abstract: Bit-serial computation enables sequential processing of data at the bit level, providing several advantages, such as scalable computational precision. This approach has gained significant attention, especially for exploiting bit-level sparsity in AI workloads. While current bit-serial processors leverage bit-level sparsity to eliminate the computation associated with zero bits, they face a fundamental trade-off: either they suffer from low memory-access and computation efficiency caused by irregular patterns of non-zero bits, or they incur substantial area overhead from complex online scheduling mechanisms required to reorganize bit-level data and preserve memory access and computation regularity. Therefore, we present the SparseCol processor, designed to harness extensive bit sparsity while maintaining high hardware utilization across various AI applications, including CNNs, RNNs, and transformers. In contrast to traditional methods, SparseCol exploits structured bit-level sparsity, denoted by bit-column sparsity, without requiring any re-training. Furthermore, SparseCol implements a dynamic dataflow architecture that tackles hardware under-utilization issues commonly found in existing bit-serial solutions. Fabricated in 16nm CMOS node, SparseCol delivers 1320 BTOPS/W (BTOPS represents Binary Tera-Operations Per Second, calculated as #W bits x #A bits TOPS) peak efficiency while maintaining accuracy, outperforming SotA sparse processors in terms of efficiency by 6.8x. Comprehensive evaluations on CNN classification tasks and transformer architectures demonstrate system-level efficiencies of 745.02 BTOPS/W and 850.5 BTOPS/W, respectively.
arXiv:2606.15408v1 Announce Type: new Abstract: Liquid cooled supercomputers dissipate tens of megawatts of waste heat through cooling plants organized as parallel subloops that serve coolant distribution units. The number of subloops and the assignment of units to them are design decisions fixed at construction, yet they have not been systematically optimized for facilities at this scale. As electricity grids decarbonize, embodied carbon becomes a larger share of facility life cycle emissions and the cost of an unnecessary subloop becomes harder to justify. We present a framework that integrates operational energy from a validated control optimizer based on sequential least squares programming, embodied carbon from a bill of materials, and expected unplanned downtime from a per subloop reliability model. The framework is applied to the Frontier supercomputer, evaluating all 611 ways of partitioning its 25 coolant distribution units into two through six subloops. The life cycle cost and carbon optimum is found at two subloops holding 14 and 11 units, achieving 3,320.7 tonnes of carbon dioxide equivalent and $3.99 million over a seven year horizon, a saving of 50.2 tonnes and $100,000 compared to built four subloop configuration. The optimum remains on the Pareto front in all 15 scenarios of a one at a time sensitivity sweep. A semi-analytical decision rule generalizes the result, predicting four subloops for Aurora, two for El Capitan, and one for LUMI. When reliability is treated as a hard constraint set by operations policy, the four subloop Frontier deployment is consistent with the constrained optimum.
arXiv:2606.15409v1 Announce Type: new Abstract: Vision-based perception is fundamental to Space Situational Awareness and autonomous on-orbit operations such as rendezvous, docking, servicing, and navigation. However, progress in this area is limited by the scarcity of annotated space imagery and by challenging visual-domain characteristics including severe illumination changes, low signal-to-noise ratio, and high contrast. We address Stream 1 of the SPARK 2026 Challenge, which requires a single model for spacecraft classification, detection, and fine-grained component segmentation across multiple target types. We propose a compact architecture that integrates a MobileNetV3 encoder with a U-Net-style decoder, combining computational efficiency with accurate dense prediction. Detection is derived analytically from the union of predicted component masks, avoiding a separate bounding-box regression head in the single-spacecraft setting. Our method achieved an overall leaderboard score of 0.9482, with task-specific scores of 1.0000 in classification, 0.9788 in detection, and 0.8917 in segmentation. The proposed approach ranked second overall in the SPARK 2026 Challenge, demonstrating that lightweight encoder-decoder architectures can deliver strong multi-task performance for practical onboard space vision systems.