Benchmark suites are crucial for advancing computer vision research, providing not only curated datasets but also standardized evaluation protocols for reproducible comparison. The railway domain lacks such resources, hindering progress in automated train operation. To address this gap, we present RAIL-BENCH, the first perception benchmark suite designed specifically for railways. RAIL-BENCH comprises five challenges - rail track detection, object detection, vegetation segmentation, multi-object tracking, and monocular visual odometry - each tailored to railway-specific characteristics and including a curated dataset from diverse real-world scenarios, evaluation metrics, and public scoreboards; we demonstrate the first three challenges in this paper. We further introduce LineAP, a novel segment-based average precision metric for rail track detection that decouples geometric accuracy from instance-level grouping and employs a track-width-based distance threshold approximating a fixed real-world distance, addressing key limitations of existing line detection metrics. Our benchmark suite is publicly available at https://www.mrt.kit.edu/railbench/.
Scientific diagrams help researchers communicate complex methods and relationships, but creating them requires substantial effort in content organization, layout design, and visual refinement. Automated diagram generation can reduce this workload. Reference examples can guide this process by showing how scientific ideas are organized and presented visually. Diagrams from accepted papers provide a rich source of such examples, but their utility as a large-scale reference resource remains underexplored. We introduce DiagramBank, a diagram-text reference resource containing 57,100 scientific diagrams from 26,751 accepted AI/ML papers. Each diagram is paired with its caption, paper title, and abstract, with citing paragraphs included when available. We combine multi-stage filtering, automated checks, and human audits, with an estimated diagram-selection precision of 93.67%. Retrieval experiments show that citing paragraphs complement captions with information specific to individual diagrams. Under a fixed generation pipeline, replacing PaperBanana's curated reference pool with DiagramBank increases the overall PaperBanana score from 4.62 to 7.88 on PaperBananaBench. Retrieved references also outperform random references on BizGenEval scientific figures. Additional evaluations with different judges and renderers, together with a separate blind human evaluation, demonstrate the utility of DiagramBank for automated diagram generation. Code: https://github.com/csml-rpi/DiagramBank.
Recent advances in model architectures, compute, and data scale have driven rapid progress in video generation, producing increasingly realistic content. Yet, no prior method systematically measures how faithfully these systems render human bodies and motion dynamics. In this paper, we present HumanScore, a systematic framework to evaluate the quality of human motions in AI-generated videos. HumanScore defines six interpretable metrics spanning kinematic plausibility, temporal stability, and biomechanical consistency, enabling fine-grained diagnosis beyond visual realism alone. Through carefully designed prompts, we elicit a diverse set of movements at varying intensities and evaluate videos generated by thirteen state-of-the-art models. Our analysis reveals consistent gaps between perceptual plausibility and motion biomechanical fidelity, identifies recurrent failure modes (e.g., temporal jitter, anatomically implausible poses, and motion drift), and produces robust model rankings from quantitative and physically meaningful criteria.
Audio platforms have evolved beyond entertainment. They have become central to public discourse, from podcasts and radio to WhatsApp voice notes and live streams. With millions of shows and hundreds of millions of listeners, audio platforms are now a major channel for misinformation. Yet existing fact-checking pipelines are mostly designed for written claims, overlooking the unique properties of spoken media. We argue that audio misinformation is not merely textual content with transcripts: it is structurally different because it is both spoken - carrying persuasive force through prosody, pacing, and emotion - and conversational - unfolding across turns, speakers, and episodes. These dual properties introduce verification difficulties that traditional methods rarely face. This position paper synthesizes evidence across modalities and platforms, examines datasets and methods, and highlights why existing pipelines fail on audio. We argue that advancing fact-checking requires rethinking verification pipelines around the spoken and conversational realities of audio.
LLM-based RTL code generation methods increasingly target both functional correctness and PPA quality, yet existing approaches decouple the two objectives, optimizing PPA only after full correctness is achieved. Sequential multi-agent pipelines, evolutionary search with binary correctness gates, and hierarchical reward dependencies all discard partially correct but architecturally promising candidates. Moreover, existing methods reduce the multi-objective PPA space to a single scalar fitness that obscures the trade-offs among area, delay, and power. To address these limitations, we propose COEVO, a co-evolutionary framework that unifies correctness and PPA optimization within a single evolutionary loop. COEVO formulates correctness as a continuous co-optimization dimension alongside area, delay, and power, enabled by an enhanced testbench with fine-grained scoring. The framework allows PPA-promising but partially correct candidates to guide the search toward jointly optimal solutions, and further employs four-dimensional Pareto-based non-dominated sorting to preserve the PPA trade-off structure without manual weight tuning. On VerilogEval 2.0 and RTLLM 2.0, COEVO surpasses all agentic baselines across four LLM backbones. With GPT-5.4-mini, COEVO achieves 97.5\% and 94.5\% Pass@1 and attains the best PPA on 43 out of 49 synthesizable RTLLM 2.0 designs.
Mixture-of-Experts (MoE) models have become the dominant architecture for large-scale language models, yet on-premises serving remains fundamentally memory-bound as batching turns sparse per-token compute into dense memory activation. Memory-centric architectures (PIM, NMP) improve bandwidth but leave compute underutilized under MoE's low arithmetic intensity on high batch sizes. Speculative decoding (SD) trades idle compute for fewer target invocations, yet verification must load experts even for rejected tokens, severely limiting its benefit in MoE especially on low batch sizes. We propose ELMoE-3D, a hybrid-bonding (HB)-based HW-SW co-designed framework that unifies cache-based acceleration and speculative decoding to offer overall speedup across batch sizes. We identify two intrinsic elasticity axes of MoE---expert and bit---and jointly scale them to construct Elastic Self-Speculative Decoding (Elastic-SD), which serves as both an expert cache and a strongly aligned self-draft model accelerated by high HB bandwidth. Our LSB-augmented bit-sliced architecture exploits inherent redundancy in bit-slice representations to natively support bit-nested execution. On our 3D-stacked hardware, ELMoE-3D achieves an average $6.6\times$ speedup and $4.4\times$ energy efficiency gain over naive MoE serving on xPU across batch sizes 1--16, and delivers $2.2\times$ speedup and $1.4\times$ energy efficiency gain over prior accelerator baselines.
Large language models (LLMs) face significant challenges in processing long contexts due to the linear growth of the key-value (KV) cache and quadratic complexity of self-attention. Existing approaches address these bottlenecks separately: Multi-head Latent Attention (MLA) reduces the KV cache by projecting tokens into a low-dimensional latent space, while sparse attention reduces computation. However, sparse methods cannot operate natively on MLA's compressed latent structure, missing opportunities for joint optimization. In this paper, we propose Latent-Condensed Attention (LCA), which directly condenses context within MLA's latent space, where the representation is disentangled into semantic latent vectors and positional keys. LCA separately aggregates semantic vectors via query-aware pooling and preserves positional keys via anchor selection. This approach jointly reduces both computational cost and KV cache without adding parameters. Beyond MLA, LCA's design is architecture-agnostic and readily extends to other attention mechanisms such as GQA. Theoretically, we prove a length-independent error bound. Experiments show LCA achieves up to 2.5$\times$ prefilling speedup and 90% KV cache reduction at 128K context while maintaining competitive performance.
Recent advances in unified multimodal models (UMMs) have led to a proliferation of architectures capable of understanding, generating, and editing across visual and textual modalities. However, developing a unified framework for UMMs remains challenging due to the diversity of model architectures and the heterogeneity of training paradigms and implementation details. In this paper, we present TorchUMM, the first unified codebase for comprehensive evaluation, analysis, and post-training across diverse UMM backbones, tasks, and datasets. TorchUMM supports a broad spectrum of models covering a wide range of scales and design paradigms. Our benchmark encompasses three core task dimensions: multimodal understanding, generation, and editing, and integrates both established and novel datasets to evaluate perception, reasoning, compositionality, and instruction-following abilities. By providing a unified interface and standardized evaluation protocols, TorchUMM enables fair and reproducible comparisons across heterogeneous models and fosters deeper insights into their strengths and limitations, facilitating the development of more capable unified multimodal systems. Code is available at: https://github.com/AIFrontierLab/TorchUMM.
We provide a computational complexity lens to understand the power of machine learning models, particularly their ability to model complex systems. Machine learning models are often trained on data drawn from sampleable or more complex distributions, a far wider range of distributions than just computable ones. By focusing on computable distributions, machine learning models can better manage complexity via probability. We abstract away from specific learning mechanisms, modeling machine learning as producing P/poly-computable distributions with polynomially-bounded max-entropy. We illustrate how learning computable distributions models complexity by showing that if a machine learning model produces a distribution $\mu$ that models the distribution generated by a cryptographic pseudorandom generator at least as well as the uniform distribution does, then $\mu$ must be close to uniform. We view training as compression that removes the randomness from the data, keeping only its structure, and inference as adding randomness back to generate new outputs. A computationally bounded model cannot distinguish pseudorandomness from true randomness, so training removes both, treating anything it cannot efficiently predict as noise. The same holds at inference, where the randomness added back can be, and in practice is, pseudorandom. In the appendix, we make the connection to compression precise and, using a characterization of pseudoentropy by Vadhan and Zheng, show that the best loss achievable by an efficient model is the next-bit pseudoentropy of the data.
The low-degree algorithm is a cornerstone in computational learning theory. For product or Gaussian distributions, it shows that efficiently learnability follows from Fourier concentration. However, a longstanding obstacle towards building such a theory over nonproduct distributions is that we can no longer rely on having closed-form expressions for a good basis of orthogonal functions. This hints that the analysis of the low-degree algorithm might be brittle to the underlying distributional assumptions. We refute this intuition by showing that the low-degree algorithm provably succeeds for a large class of graphical models under mild high-temperature conditions. As an application, for nearly every Ising model that is known to rapidly mix, we obtain learning algorithms for every function class for which the Fourier approach succeeds for product distributions (e.g. low-depth circuits, halfspaces, intersections, monotone, among others) with no significant loss. Our framework is based on a strikingly clean connection with the coordinate-by-coordinate localization scheme of Chen and Eldan introduced for establishing rapid mixing in high-temperature models, as well as other analytical transference principles to product distributions.
Implicit neural representations (INRs) commonly employ Fourier features to alleviate spectral bias and represent high-frequency signals. Fourier encodings, however, use the same frequency representation across spatial locations despite the spatially varying frequency content of natural signals. We propose Adaptive Frequency Implicit Neural Representation (AFINR), a spatially adaptive frequency-conditioning framework for Fourier encoded INRs. A sampling compatible Fourier dictionary first defines the explicit frequency support, and a learnable spatial control field then modulates the admitted Fourier components before decoding. The control field is parameterized in the discrete cosine transform (DCT) domain to provide a compact and continuously queryable spatial representation. AFINR can be combined with different coordinate decoders, including ReLU, SIREN, CAFE, and CAFE+. Experiments on Kodak and DIV2K show consistent average improvements across these decoder families. In particular, AFINR-CAFE+ improves CAFE+ by 3.95 dB on Kodak and 3.50 dB on DIV2K. Ablation studies characterize the effects of adaptive-field parameterization, DCT coefficient retention, and frequency-response parameters, while learned spatial responses show position-dependent use of the admitted Fourier components.
We study structured abstraction-based reasoning for the Abstraction and Reasoning Corpus (ARC) and compare its generalization to test-time approaches. Purely neural architectures lack reliable combinatorial generalization, while strictly symbolic systems struggle with perceptual grounding. We therefore propose a neuro-symbolic architecture that extracts object-level structure from grids, uses neural priors to propose candidate transformations from a fixed domain-specific language (DSL) of atomic patterns, and filters hypotheses using cross-example consistency checks. Instantiated as a compositional reasoning framework based on unit patterns inspired by human visual abstraction, the system augments large language models (LLMs) with object representations and transformation proposals. On ARC-AGI-2, it improves over the base solver LLM (Grok-4, 16.0%) to 24.4% on the public evaluation set, and to 30.8% when combined with ARC Lang Solver via a meta-classifier. These results support the claim that in the evaluated settings, allocating test-time compute to object abstraction, neural-guided transformation proposal, and consistency filtering can improve accuracy over unstructured sampling-based scaling without task-specific finetuning of the system. We open-source the code: (https://github.com/CoreThink-AI/arc-agi-2-reasoner).
Video multimodal large language models achieve strong results on existing benchmarks, but answer accuracy alone does not establish whether they can locate the evidence needed to answer a question. We introduce VideoZeroBench, a challenging long-video benchmark with manually annotated question-answer pairs spanning 13 video domains. Questions target fine-grained cues, fleeting events, and evidence distributed across multiple segments. Temporal intervals and key-frame boxes are annotated where applicable. All questions undergo two rounds of cross-verification for answer validity and evidence quality. Our five-level diagnostic protocol compares answering with and without evidence hints, then combines answer correctness with independently evaluated temporal and spatial grounding. Across 19 evaluated models, the best standard QA accuracy is 24.8% (Level-3), achieved by Gemini-3.7-Flash. No model exceeds 1.8% when correct answers and accurate spatio-temporal localization are jointly required (Level-5). Analyses of atomic abilities, evidence spans, input modalities, and thinking-with-videos inference further characterize where the evaluated systems struggle. These findings motivate more precise evidence search and localization for long-video question answering. Our code and data are publicly released.
Reconstructing high-dimensional spatiotemporal fields from sparse sensor measurements is critical in a wide range of scientific applications. The SHallow REcurrent Decoder (SHRED) architecture is a recent state-of-the-art architecture that reconstructs high-quality spatial domain from hyper-sparse sensor measurement streams. An important limitation of SHRED is that in complex, data-scarce, high-frequency, or stochastic systems, portions of the spatiotemporal field must be modeled with valid uncertainty estimation. We introduce UQ-SHRED, a distributional learning framework for sparse sensing problems that provides uncertainty quantification through a neural network-based distributional regression called engression. UQ-SHRED models the uncertainty by learning the predictive distribution of the spatial state conditioned on the sensor history. By injecting stochastic noise into sensor inputs and training with an energy score loss, UQ-SHRED produces predictive distributions with minimal computational overhead, requiring only noise injection at the input and resampling through a single architecture without retraining or additional network structures. On complicated synthetic and real-life datasets including turbulent flow, atmospheric dynamics, neuroscience and astrophysics, UQ-SHRED provides a distributional approximation with well-calibrated confidence intervals. We further conduct ablation studies to understand how each model setting affects the quality of the UQ-SHRED performance, and its validity on uncertainty quantification over a set of different experimental setups.
Multimodal Large Language Models (MLLMs) have shown strong performance on video question answering, but their application to long-form videos is constrained by limited context length and computational cost, making keyframe sampling essential. Existing approaches typically rely on semantic relevance or reinforcement learning, which either fail to capture evidential clues or suffer from inefficient combinatorial optimization. In this work, we propose an evidence-driven keyframe sampling framework motivated by an information-theoretic perspective. We consider maximizing the conditional mutual information between the selected frames and the answer given the query as an idealized objective, and use a modular singleton-gain surrogate to motivate a tractable frame-wise selection criterion. Guided by this motivation, we train a query-conditioned evidence scoring network using annotated answer-supporting segments. A contrastive objective encourages greater aggregate score mass on frames from evidence regions than on background frames, providing a practical evidence-based criterion beyond semantic similarity. Experiments on long-form video understanding benchmarks show that our method consistently outperforms prior sampling strategies under comparable frame budgets. With Qwen2.5-VL-7B under the same 32-frame budget, our method improves over uniform sampling by 10.1 points on LVBench and 4.4 points on the long-video subset of VideoMME.
Training-only privileged-modality learning uses an expensive modality during training while keeping a single-modality deployment path. We study chest radiograph (X-ray) classification with same-patient computed tomography (CT) available only during training. JDCNet adds an auxiliary CT-teacher target, the teacher's argmax label or its softmax distribution through a Kullback--Leibler term (soft-KL), only on samples whose teacher confidence exceeds a threshold; the deployed model has the same ResNet-18 computation graph as the supervised baseline. On 510 same-patient pairs from the public BIMCV-COVID19 releases of the Valencian Region Medical ImageBank (113 COVID-19, 397 non-COVID), with patient-level five-fold cross-validation and three seeds, 15 of 16 adaptively explored JDCNet configurations improved mean balanced accuracy (BA) over the supervised baseline (average $+0.020$), but none remained significant after Holm adjustment. In a pre-registered experiment with 240 batch-matched supervised restarts on the same splits, batch size had no detectable effect on the baseline (BA $0.620$ versus $0.625$), and when both methods selected one of 16 runs per cell on the validation partition, JDCNet exceeded supervised training by $+0.037$ BA (95\% confidence interval $+0.016$ to $+0.058$; patient-level $+0.007$ to $+0.068$). Logit distillation and contrastive alignment did not help. Teacher diagnostics indicate that the gate acts mainly as CT-informed sample weighting. All models, including JDCNet, performed at chance on an external radiograph set. Confidence-gated CT supervision thus gives a small within-cohort advantage on one public cohort and a binary task; generalization requires independent paired replication.
Token-level sparse attention mechanisms, exemplified by DeepSeek Sparse Attention (DSA), achieve fine-grained key selection by scoring every historical key for each query through a lightweight indexer, then computing attention only on the selected subset. While the downstream sparse attention itself scales favorably, the indexer must still scan the entire prefix for every query, introducing an per-layer bottleneck that grows prohibitively with context length. We propose HISA (Hierarchical Indexed Sparse Attention), a plug-and-play replacement for the indexer that rewrites the search path from a flat token scan into a two-stage hierarchical procedure: (1) a block-level coarse filtering stage that scores pooled block representations to discard irrelevant regions, followed by (2) a token-level refinement stage that applies the original indexer exclusively within the retained candidate blocks. HISA preserves the identical token-level top-sparse pattern consumed by the downstream Sparse MLA operator and requires no additional training. On kernel-level benchmarks, HISA achieves up to speedup at 64K context. On Needle-in-a-Haystack and LongBench, we directly replace the indexer in DeepSeek-V3.2 and GLM-5 with our HISA indexer, without any finetuning. HISA closely matches the original DSA in quality, while substantially outperforming block-sparse baselines.
The rapid proliferation of Generative Artificial Intelligence (GenAI) is reshaping pedagogical practices and assessment models in higher education. While institutional and educator perspectives on GenAI integration are increasingly documented, the student perspective remains comparatively underexplored. This study examines how students perceive, use, and evaluate GenAI within their academic practices, focusing on usage patterns, perceived benefits, and expectations for institutional support. Data were collected through a questionnaire administered to 436 postgraduate Computer Science students at the University of Hertfordshire and analysed using descriptive methods. The findings reveal a Confidence-Competence Paradox: although more than 60% of students report high familiarity with tools such as ChatGPT, daily academic use remains limited and confidence in effective application is only moderate. Students primarily employ GenAI for cognitive scaffolding tasks, including concept clarification and brainstorming, rather than fully automated content generation. At the same time, respondents express concerns regarding data privacy, reliability of AI-generated information, and the potential erosion of critical thinking skills. The results also indicate strong student support for integrating AI literacy into curricula and programme Knowledge, Skills, and Behaviours (KSBs). Overall, the study suggests that universities should move beyond a policing approach to GenAI and adopt a pedagogical framework that emphasises AI literacy, ethical guidance, and equitable access to AI tools.
With the rapid advancement of underwater net-working and multi-agent coordination technologies, autonomous underwater vehicle (AUV) ad-hoc networks have emerged as a pivotal framework for executing complex maritime missions, such as multi-target tracking. However, traditional data-centricarchitectures struggle to maintain operational consistency under highly dynamic topological fluctuations and severely constrained acoustic communication bandwidth. This article proposes a scene-adaptive embodied intelligence (EI) architecture for multi-AUV ad-hoc networks, which re-envisions AUVs as embodied entities by integrating perception, decision-making, and physical execution into a unified cognitive loop. To materialize the functional interaction between these layers, we define a beacon-based communication and control model that treats the communication link as a dynamic constraint-aware channel, effectively bridging the gap between high-level policy inference and decentralized physical actuation. Specifically, the proposed architecture employs a three-layer functional framework and introduces a Scene-Adaptive MARL (SA-MARL) algorithm featuring a dual-path critic mechanism. By integrating a scene critic network and a general critic network through a weight-based dynamic fusion process, SA-MARL effectively decouples specialized tracking tasks from global safety constraints, facilitating autonomous policy evolution. Evaluation results demonstrate that the proposedscheme significantly accelerates policy convergence and achieves superior tracking accuracy compared to mainstream MARL approaches, maintaining robust performance even under intense environmental interference and fluid topological shifts.
Surface electromyographic (sEMG) signals provide information about muscle activity and function during movement. Fatigue alters multiple properties of these signals, with patterns that vary across individuals and contraction intensities. However, physiological insights into fatigue remain underused in sEMG modeling, particularly for cross-subject recognition. We introduce FatigueFormer to recognize fatigue states defined by ratings of perceived exertion (RPE). The model incorporates physiologically motivated trend grouping into sEMG encoding by organizing descriptors into increasing- and decreasing-trend streams and combining inter-window context with within-window feature interactions. To assess fatigue-state discriminability across contraction intensities, we further present an sEMG fatigue dataset collected from 30 participants at four levels of maximum voluntary contraction (MVC) and benchmark representative machine learning and deep learning methods. We evaluate performance offline under leave-one-subject-out (LOSO) and within-subject protocols and use the SWIFTIES dataset for external validation. Results support FatigueFormer's effectiveness across the examined contraction intensities and both datasets, while indicating that fatigue-related cues vary across MVC levels. An exploratory adaptation analysis shows higher FatigueFormer scores with more labeled target-user data on complete target recordings, which include calibration samples.