Machine Learning
Papers
Fresh from arXiv, typeset properly. Highlighted words trade on the market.
Thursday 13 August
Infrared (IR) spectroscopy is widely used for chemical sensing, but extracting reliable chemical information from spectra remains challenging. Conventional interpretation is labor-intensive, relies on prior knowledge and reference spectra, and is difficult to scale, whereas most machine-learning methods are tailored to individual tasks or datasets, require large labeled training sets, and transfer poorly across analytical objectives and experimental datasets. Here we introduce UltraIR, a foundation model for IR spectroscopy with more than 100 million parameters that enables simulation-to-real transfer learning for chemical sensing and analysis from molecules to complex samples. UltraIR is pretrained on approximately 60 million simulated IR spectra using spectral reconstruction, molecular fingerprint similarity alignment, and functional-group prediction, then adapted to downstream objectives with task-specific labels or targets. Across functional-group prediction, molecular structure elucidation, physicochemical property prediction, mixture-component identification and quantification, bacterial classification, medicinal-herb geographic origin traceability and constituent quantification, microplastics classification, and soil property prediction, UltraIR outperforms conventional machine-learning and task-specific deep-learning baselines. It performs strongly with limited labeled experimental spectra and in zero-shot inference for the same analytical task across Fourier-transform infrared spectrometers and laboratories, providing a route to adaptable, data-efficient chemical sensing from complex real-world samples.
Machine Learning
Where You Measure Decides What You Measure: Position Selection in Ablation-Based SAE Evaluation
Sparse autoencoders are meant to name the things a language model computes, and the usual way to check that a latent matters is to switch it off and see what changes. But a latent fires at many tokens, and the effect has to be measured at one of them. The convention is to measure where the latent fires hardest. That choice is almost never reported, and it is not made by the experimenter: it is made by the dictionary under evaluation. Change the dictionary and the measurement moves to a different token. We show this is not a detail. Take two sparse autoencoders released by Google for the same model and match their latents by decoder similarity: even among the pairs the two dictionaries encode almost identically, they pick different tokens for a large share of them. Two dictionaries compared under the usual protocol are therefore very often compared at different places. To separate the convention from the dictionaries we train six autoencoders from one initialisation, differing only in fitting choices, so that a latent means the same thing in each. Most of the variance such a comparison reads as "these dictionaries disagree about this latent" turns out to be the position instead: it falls from 7.6% and 11.9% of variance to near zero once every dictionary is measured at the same token. More evaluation data does not rescue it. Across a sixteenfold range of corpus sizes the dictionaries agree less about where to measure, not more, so the problem grows with scale. The correction is one line of evaluation code. We give the protocol an ablation-based causal number must report to be comparable across papers, and an audit of five published papers against it. In short: a causal number reported without its position describes the token it was taken at as much as the latent it was taken from.
Read the full abstract
Machine Learning
Neural Quadratic Forms: A Unified Minimal Model for Sudden Learning and Scaling Laws
Neural networks trained by gradient descent on a smooth cost function can nevertheless learn in steps: the cost holds on long plateaus and then drops abruptly. Meanwhile, training losses instead follow smooth power laws. Variants of both behaviors occur in architectures with very different microscopic structures, which is the signature of a few relevant collective variables. We show that a symmetry fixes what those variables are: a network layer is a sum over interchangeable units, so relabeling the units leaves it unchanged; given smoothness and the condition that a unit's gradient vanish at the origin, symmetry then enforces a universal leading form for the expansion about the near-zero weights present at the start of training, the quadratic $\Tr[WW^{\top}A(x)]$, in which every architectural detail is confined to a single “structure matrix" $A(x)$ that we compute for each architecture. Perceptrons, attention layers, mixtures of experts, and convolutions become one model at different $A$. Its training dynamics then close on the “order parameter" $M=WW^{\top}$ and, whenever the data matrices share an eigenbasis, reduce to a Lotka–Volterra equation whose modes switch on one after another. The smaller the initial weights, the further apart the switch-on times, and the plateaus appear as a singular limit of a smooth flow; when many modes are unresolved the same events merge into a power law in training time whose exponent the theory predicts. We confirm both numerically across training methods and architectures.
Read the full abstract
Computation and Language
RippleMem: From Isolated Retrieval to Associative Recollection for Long-Term Agent Memory
LLM-based agents increasingly rely on external memory to support long-horizon reasoning and interaction. However, the main bottleneck is not simply storing past experience, but recovering the right set of evidence when relevant information is distributed across many interactions. Existing approaches struggle with this access problem. Full-context methods require noisy long-context search, flat retrieval often returns isolated and incomplete records, and graph-based memory systems can be expensive to construct while compressing rich event context. We introduce RippleMem, a long-term memory system that replaces one-shot retrieval with adaptive associative recollection. Inspired by cue-dependent episodic retrieval and associative completion, RippleMem stores interaction history as cue-rich episodic memory units and organizes them in an event-centric memory graph. Given a query, it first recalls relevant memory anchors through hybrid cues, then expands from these anchors along semantic and structural associations to recover missing supporting evidence. In this way, initially recalled memories serve not only as answer context, but also as cues for completing the evidence needed to answer. Experiments on LoCoMo and LongMemEval-S show that RippleMem achieves the best overall performance across evaluated settings, improving LLM-as-a-Judge accuracy by 3.95% on LoCoMo and up to 11.87% on LongMemEval-S, while reducing graph construction cost by about 30x.
Read the full abstract
Artificial Intelligence
LLM-Guided Graph Generation for Structure-Based Local Improvement Methods
Large neighborhood search normally selects a random subset of decision variables for iterative optimization. To efficiently solve various problems, researchers tend to design variable selection strategies that take into account structural features across different domains. In this paper, we build an automatic pipeline that is problem-agnostic to all problems in the MiniZinc format. By prompting an LLM with our semantic guidelines, we guide the LLM to produce a graph generator that maps any instance of a problem type to a uniform weighted graph, where nodes represent decision variables and edges represent constraint relationships. These problem-agnostic graphs guide our structure-based local improvement (SLIM) framework for variable selection. Meanwhile, the weighted graph enables all problem instances to share the same generic graph representation, from which the same graph features can be extracted and used for configuration selection. We evaluated our pipeline on instances across 20 MiniZinc competition problems, finding that algorithm selection achieves a 39.6% average problem-weighted win rate against a one-shot Gurobi baseline, more than doubling the best single configuration (19.3%). A post-hoc configuration and a feature ablation indicate a headroom of up to 44.0%, demonstrating that LLM-based semantic generation enables effective automated structure and feature extraction for constraint optimization.
Read the full abstract
Machine Learning
Training AI Scientists to Replicate Research
The replicability of papers is a cornerstone of scientific knowledge, ensuring the reliability of existing results and providing a base for further experiments. The act of replication typically illuminates details that were previously underspecified, and thus requires similar hypothesis-driven exploration to open-ended research. In this work, we develop Replica, a scalable task space for paper replication. To provide reward signal, we introduce an auto-generated rubric-based judge that has low noise and agrees with human assessment of replication quality. We post-train Faraday, a 27B-parameter "AI Scientist" agent that leverages coding agents as tools, surpassing the performance of Claude Opus 4.8 and GPT-5.5 on held-out replication tasks. Qualitative analysis of individual rollouts reveals that Faraday adopts a more scientifically-principled approach. We believe that our results provide a stepping stone towards AI agents capable of long-horizon scientific innovation without requiring complex harnesses.
Read the full abstract
Machine Learning
A Probe Direction Is a Property of Its Prompt
A model that behaves differently when it senses it is being tested would undermine the evaluations we rely on, so recent work has sought to read that sense directly from a model's activations. The standard instrument contrasts activations on prompts that announce an evaluation against prompts that do not, and reports how well the resulting direction separates held-out cases. That number is then compared across models and correlated with scale. We observe that the instrument has a free parameter its readings do not disclose: "a prompt that announces an evaluation" is not a prompt but a choice among many, and nothing in the method fixes which. Holding the task text fixed and varying only that choice, we find that the reported score, and even the direction in which it trends with model size, follows the prompt rather than the model; two published studies that disagree about the sign of that trend are both reproducible from a single design, by choice of prompt alone. Treating the prompt as a facet of a measurement design rather than an implementation detail, we find the model under study accounts for a small share of the variance in the number reported about it, and most of the rest lies in how each model responds to each prompt: collecting more evaluation items cannot repair the measurement, while varying prompts can. A further check finds that the split these probes are scored on is largely separable from surface form alone, so a direction carrying no information about evaluation at all still reproduces a substantial fraction of each published score. We conclude that a single-prompt design cannot support comparison between models, and we give the number of prompts a defensible comparison requires.
Read the full abstract
Computation and Language
It's How You Ask: Gender-Associated Linguistic Bias in LLMs
Professional communication is increasingly mediated by LLMs - but do these models serve all users equally? We show that when prompts contain linguistic features more commonly used by women (hedges, tag questions, collective reference), they systematically elicit shorter, less sophisticated, and less formal responses across three document types and four models. These effects persist after controlling for prompt complexity and feature carry-over. Explicit gender cues like sign-off names are encoded in the same representational space as linguistic dialect - suggesting shared underlying mechanisms - yet linguistic register is far more influential, producing large, consistent effects where names produce none. Our results further reveal that post-hoc mitigation is challenging: because these patterns are culturally embedded and outside conscious control, users cannot easily avoid them through strategic self-presentation, and mechanistic analysis reveals that linguistic features are encoded in early transformer layers and entangled with other features. Our work calls for upstream consideration of the influences of linguistic variation to mitigate disparate impacts of LLM-mediated workplace communication.
Read the full abstract
Computation and Language
Beyond Local Accuracy: A Protocol-Level Identifiability Audit for Controlled LLM Reasoning Evaluation
LLM benchmark scores can be precise even when the observation protocol does not identify the behavioral property they are intended to measure. In a controlled, solver-grounded setting, we formalize a protocol-level identifiability audit over a finite behavioral policy class: given policies H, observation support O, and estimand $\tau$, we test whether O separates every pair with different $\tau$. The audit requires zero model calls and resolves our diagnostic case: base-only observation collapses seven frozen deterministic policies into one equivalence class; full support yields seven classes and no cross-estimand collisions; every leave-one-out support retains a constructive collision witness. Empirically, both constrained-generation variants have pair-validity 1.0, yet base accuracy and selective-response fidelity diverge - 0.620 versus 0.324 across six balanced oracle-transition directions (cluster-bootstrap 95% CI [0.600, 0.642] vs. [0.304, 0.345]) - and the gap recurs on a second deterministic source (0.646 vs. 0.331). The audit also synthesizes a minimum identifying support $O^*$ for the frozen policy class: two cells instead of the full 36-cell tensor. This case shows how evaluation-design validity can be checked structurally before model inference and why base correctness does not determine intervention-response fidelity.
Read the full abstract
Software Engineering
Integration-First Structural Coverage for Embedded Software:Trace-Based Evidence, Hybrid Runtime Analysis, and Cross-Variant Consolidation
Structural coverage is widely used as evidence that testing is complete, yet in embedded projects it is predominantly collected at unit level, simply because that is where instrumentation and observability are inexpensive. This produces a mismatch. The most representative completeness signal would come from integration and system tests executed on the device under test, but classical instrumentation perturbs timing, memory footprint and concurrency behaviour, while purely trace-reconstructed coverage loses reliability for decisions and conditions as soon as the compiler optimizes aggressively. We address this mismatch from both ends. On the process side we describe an integrationfirst coverage strategy that treats integration and system tests as the baseline measurement and drives the residual gaps through an explicit closure loop, so that completeness is established as covered or justified rather than as covered alone. On the technical side we use embedded trace as the observation path and add hybrid runtime analysis (hRA): a minimal, semantics-preserving observability scaffolding that keeps decision and condition boundaries distinguishable in the trace stream of an optimized (-O3) build, while all coverage state and counting remain off-target. This converts object-to-source mapping from a heuristic reconstruction into reviewable evidence and makes branch, condition and MC/DC measurement practical on release-like binaries. Finally we describe Hyper Coverage, a consolidation layer that merges evidence across test levels, test runs, variants and build configurations, and that exposes source lines which remain untested in every relevant variant.
Read the full abstract
Data Structures and Algorithms
A minimum witness for the 3/2 configuration-linear-program gap in two-weight graph balancing, unique at its size
Restricted assignment minimizes makespan, the busiest machine's load, when each job has one size and a set of allowed machines. Its tightest studied relaxation is the configuration linear program, which fractionally gives each machine whole job sets that fit. Its integrality gap, the worst-case ratio of integral optimum to relaxation value, is open in general. On two-weight graph balancing (sizes 1 and 2, each job allowed on at most two machines) the gap is known: Jansen, Land, and Maack (2016) give both bounds. Their Table 1 instance attains 3/2, and their Corollary 11 bound of 2-s/b for sizes s < b matches it at {1,2}. We ask how small such an instance, a witness, can be. We give a six-job witness I* on the complete graph on four machines: unit jobs form a cycle through all four, and two weight-2 jobs take the remaining edges. I* has integral optimum 3 against relaxation value 2, one job fewer than the smallest earlier witness of this class. We prove I* minimum and unique at its size, on any number of machines: no instance with at most five jobs reaches gap 3/2, and at six jobs I* is the only witness, up to relabeling machines and adding unusable machines. At seven jobs uniqueness fails: we classify all thirteen witnesses, including the Jansen-Land-Maack instance. Eight jobs give 154, nine 1,662. At least four machines are necessary. Kartak et al. (2015) classified the extremal non-round-up instances of the same relaxation in one-dimensional cutting stock for small demand; the Discussion relates them. Recognizing witnesses at relaxation value 2, shared by all ours, is coNP-complete, so no min-max characterization with polynomially checkable conditions exists unless NP = coNP. Every feasibility decision behind the exhaustive claims was made twice, in floating-point and exact rational arithmetic, with identical results. We accept the pipeline's negatives only after it rediscovers I*.
Read the full abstract
Artificial Intelligence
StateBridge: Training-free Hidden-state Alignment for Latent Communication in LLM Multi-Agent Systems
Large language model based multi-agent systems usually communicate in text, i.e., using discrete tokens. However, text introduces a discrete bottleneck. Converting the sender's continuous hidden states into discrete tokens discards information that token identities alone cannot capture. Recent work proposes latent communication as an alternative, where agents transmit hidden representations directly without converting them to text. However, existing latent methods either inject working memory layer by layer across the transformers, or require trained projectors that limit portability. We propose StateBridge, a training-free latent communication approach that aligns the sender's final-layer hidden states to the receiver's input space via a closed-form orthogonal transformation. Lightweight norm calibration and vocabulary anchoring ensure compatibility with the pretrained input distribution. The aligned states are prepended to the input of the receiver agent as a continuous prefix. We evaluate StateBridge on math reasoning, code generation, and question answering with four models from two families. StateBridge achieves the best or tied-best score on 22 out of 26 model-task pairs, consistently outperforming the strongest baseline.
Read the full abstract
Machine Learning · Cross-listed from eess.SP
Foundation models for movement data: Are they ready for prime-time?
Foundation models (FMs) trained on large-scale accelerometer data have been proposed as general-purpose feature extractors for health monitoring, but systematic evidence of their advantages is lacking. We present the first comprehensive evaluation of four open-source accelerometer FMs against supervised baselines covering 19 tasks across the domains of activity recognition including activities of daily living, clinical monitoring, and physiological inference. We find task-dependent performance results: supervised models remain competitive with FMs on human action recognition (HAR), with no consistent advantage for either, while selected FMs lead on fall and stress detection and are the most robust to sensor-placement variation. As frozen feature extractors, FMs are strongest for demographic inference, whereas sleep staging performance remains near chance level for all models. The internal FM representations show strong similarity across layers, highlighting potential for future FM improvements. Linear and frozen probing reveals that UniMTS provides the strongest representations and is the only FM that surpasses the supervised baselines without finetuning. Concept discovery analysis shows all models capture high-intensity activities clearly but struggle with sedentary, complex or ambiguous activities. We provide scenario-based deployment recommendations. Furthermore, we identify FM-derived activity profile inference-moving beyond fixed category classification-as a promising research direction.
Read the full abstract
Game Theory
Keep, Customize, or Exit: Default Design and Token Pricing in LLM Reasoning Services
We study a large language model (LLM) service in which a provider chooses a per-token price and a default reasoning-token allocation, while a user may accept the default, customize the allocation, or exit. Larger allocations can improve accuracy but increase token cost and latency. We model this interaction as a Stackelberg game and derive the user's unique optimal customized allocation in closed form. For any price, the acceptable defaults form either an empty set or a compact interval. We characterize the provider's optimal default through a three-regime rule, reduce equilibrium computation to a one-dimensional price optimization, and prove the existence of the equilibrium. We further show that defaults affect the implemented reasoning allocation only when users value the convenience of avoiding customization; otherwise, every service-providing outcome implements the user's optimal customized allocation. Experiments with two compact open-weight reasoning models on five mathematics and science benchmarks support the accuracy-token model and show how model and task characteristics determine equilibrium prices, defaults, and reasoning allocations.
Read the full abstract
Computational Complexity
On the Structure of $(\min,+)$ Convolution
The $(\min,+)$ convolution is a central problem in fine-grained complexity, and it remains open whether it can be computed in truly subquadratic time. We study it through tropical polynomials, where $(\min,+)$ convolution is exactly tropical polynomial multiplication. We introduce the tropical decomposition width, $\operatorname{tdw}(A)$, which measures how finely a tropical polynomial can be decomposed into factors of small degree. We prove two modular convexity theorems showing that bounded tropical decomposition width forces convexity on arithmetic progression subpolynomials. This yields deterministic algorithms for computing $a\otimes b$ in $$O\left(n\max(\operatorname{tdw}(a),\operatorname{tdw}(b))^2\right)$$ when $\max(\operatorname{tdw}(a),\operatorname{tdw}(b))$ is given, and in $$O\left(ne^{\min(\operatorname{tdw}(a),\operatorname{tdw}(b))(1+o(1))}\right)$$ without prior knowledge of the width. Neither algorithm requires a decomposition of the input sequences. The same structural ideas give a randomized algorithm for Multiple-Sequence $(\min,+)$ Convolution: given $k$ sequences of length at most $n$, their convolution can be computed in $$O\left(kn^2\sqrt{\min(k,n)}\log^{1.5}(kn)\right)$$ time, improving the natural $O(k^2n^2)$ bound. Finally, we introduce interpolation algebras for tropical polynomials and show that classes with bounded tropical decomposition width admit interpolation algebras of finite generating rank, whereas distinguishing all tropical polynomials of degree at most $n$ requires generating rank $\lfloor n/2\rfloor+1$. We also prove that tropical decomposition width cannot decrease under any flat $\mathbb T$-algebra extension. Together, these results connect the tractability of $(\min,+)$ convolution with structural rigidity in tropical polynomial multiplication.
Read the full abstract
Computer Vision
How Good are Foundation Models in Longitudinal MRI Disease Progression Reasoning?
Magnetic Resonance Imaging (MRI) interpretation is fundamental to clinical decision-making, requiring radiologists to integrate multi-view anatomical planes across sequential timepoints while precisely localizing interval changes. However, existing vision-language benchmarks remain confined to single-timepoint, single-view interpretation, failing to capture the temporal-spatial reasoning essential to radiologic practice. We introduce the Time-Aware Multi-View MRI Benchmark, an evaluation framework unifying multi-view anatomical input, temporal reasoning across longitudinal scans, and structured localization guidance. The benchmark comprises 3,920 expert-verified question-answer pairs derived from 890 patients across over 3,200 longitudinal MRI timepoints, drawn from seven clinical cohorts covering glioblastoma, neurodegeneration, vestibular schwannoma, and brain metastases, in open-ended, multiple-choice, and binary formats, requiring models to identify anatomical regions of maximal change, characterize progression across sequences and views, and provide structured guidance specifying boundaries, imaging features, and confounders. Experiments across 16 vision-language models reveal moderate temporal alignment but systematic failure on change direction recognition and volumetric quantification, while multi-view inputs improve spatial localization yet degrade temporal reasoning in compact architectures. Our benchmark provides a systematic framework for evaluating progression tracking, interval change localization, and temporal ordering, which are essential for clinical deployment. Code, evaluation splits, and the dataset are available at: https://github.com/wafaAlghallabi/Time-Aware-MRI.
Read the full abstract
Logic in Computer Science
Completeness and incompleteness of basic matching logic
Basic matching logic is matching logic without definedness. Symbols are interpreted as set-valued operations, element variables denote singletons and are bound by $\exists$, and no connective uniformly internalizes totality. For basic matching logic without fixpoints over an arbitrary one-sorted finitary signature, we prove global completeness ($\Gamma\vDash\varphi$ iff $\Gamma\vdash\varphi$, for arbitrary, possibly infinite $\Gamma$) and, as a corollary, conservativity of the definedness extension. The proof localizes $\Gamma$ to a theory $\Delta_\Gamma$ and reduces semantic consequence and derivability to the same local relation: $\Gamma\vDash\varphi$ iff $\Delta_\Gamma\vDash_\text{loc}\varphi$ iff $\Gamma\vdash\varphi$. A double-cover construction establishes the semantic equivalence. Least fixpoints destroy effective axiomatizability. Over a signature with one unary and two binary symbols and no constants, validity is not recursively enumerable; hence no sound calculus with a recursively enumerable proof relation is even weakly complete, already for the empty theory and without definedness. The positive result is also sharp in the number of sorts. Global completeness fails with three sorts for a satisfiable $\Gamma$. Thus the completeness conjecture holds for one sort and fails in general. The negative results arise from sort flow, fixpoint effectivity, and, for hybrid logic, an obstruction to every well-founded calculus whose leaves are hypotheses or valid patterns and whose rules respect localization. This yields a matching-logic-independent dichotomy: the language with state variables bound by $\exists$ and $\forall$ over modalities of arbitrary arity is globally complete without nominals, while no calculus in that well-founded class is globally complete once nominals are added.
Read the full abstract
Artificial Intelligence · Cross-listed from stat.AP
Physics-informed distribution of relaxation times estimation and latent-space condition monitoring of solid oxide fuel and electrolysis cells from electrochemical impedance spectroscopy
Estimating the distribution of relaxation times (DRT) fromelectrochemical impedance spectroscopy (EIS) is an ill-posed inverse problem that is highly sensitive to regularisation choices. We propose a physics-informed convolutional autoencoder that estimates DRT directly from EIS data without spectrum-specific tuning. A discretised relation between impedance and the DRT is embedded in the training process, constraining the network to produce impedance-consistent distributions. The model resolves overlapping relaxation processes in synthetic two-ZARC spectra and accurately reconstructs measurements from three independent solid oxide fuel and electrolysis cell datasets, with range-normalised errors below 1.1%. Decoder-probe analysis shows that the learned latent representation is organised according to relaxation timescale. Distances in this latent space capture operating changes, hydrogen-shortage events, and long-term degradation. The same lightweight architecture is applied across all datasets without modification, providing consistent DRT estimation and an interpretable basis for condition monitoring.
Read the full abstract
Computation and Language
Refusing Intent, Not Form: Wrapper-Based Intent-Group Supervision for LLM Safety
A common way to improve jailbreak robustness is to train on harmful requests rewritten as role-play, translation, or other forms. When used only for harmful requests, these forms may become refusal shortcuts, weakening unseen-attack robustness and increasing benign over-refusal. We propose Wrapper-Based Intent-Form Augmentation (WIFA), which applies shared wrapper families to harmful and benign requests and groups variants by intent, encouraging decisions based on underlying intent rather than wrapper cues. WIFA supports two independent routes: WIFA-Boost prioritizes safety through two-stage training, while A-GCRT enforces consistent decisions across wrappers to mitigate over-refusal. Across three model families and two harmful training sources, both routes consistently improve safety while largely retaining capability. On Qwen–AdvBench, WIFA-Boost raises SB-avg5 from 22.1% to 63.7%, the best among compared methods; A-GCRT raises it to 46.7% while reducing OR-Bench over-refusal from 25.7% to 17.4%, unlike reproduced defenses whose safety gains increase over-refusal. Across three AdvBench-trained backbones, both routes substantially reduce ASR on 15 unseen attack families and under model-adaptive GCG and RandomSearch. Overall, WIFA provides reusable intent-group supervision across models and training sources, supporting high safety through WIFA-Boost and substantial safety gains with less unnecessary refusal through A-GCRT.
Read the full abstract
Machine Learning
The Time Value of Evolution
In evolutionary search, a weak child can be a valuable ancestor that makes high-fitness regions reachable. Immediate-return control is blind to this delayed utility, penalizing mutations through their immediate offspring even when they open productive future lineages. We formalize this hidden dynamic as the time value of evolution within a finite-horizon Markov decision process. To exploit it, we introduce Lineage-Value Policy Gradients (LVPG), a long-horizon actor-critic framework for automated trading policy discovery. Our architecture decouples search control into specialized policy heads over a shared generative backbone: a bootstrapped critic head estimates the value of finite-horizon lineage potential from multi-step mutation trees, while an actor head dynamically modulates mutation intensity over the remaining search budget. We isolate the impact of long-horizon credit assignment against immediate-return optimization across 90 paired runs under matched operators, lineage supervision, folds, seeds, and budgets. Path-based credit assignment substantially accelerates finite-budget search, increasing validation best-so-far AUC by 0.394 Sharpe units. LVPG also produces fewer temporary regressions than immediate-return optimization and recovers from them more often. Finite-horizon lineage value yields more selective non-monotonic search and stronger policies within identical resource constraints.
Read the full abstract
Machine Learning
Large-scale Testing Global Optimization Methods with Black-box Adversarial Attacks
Existing global optimization benchmark suites are of a moderate size and are based on a small number of analytical functions that date back even to the 1970s. This causes a risk of biasing the development of global optimization methods. We argue that the tasks related to the black-box adversarial attack (BBAA) can serve as valuable global optimization benchmark in many-dimensional space. We demonstrate the efficiency of several types of evolutionary algorithms and other metaheuristics in solving example BBAA problems. Thus, we take a step towards convergence of global optimization methods to the challenges and needs that arise in the modern machine learning field.
Read the full abstract
Human-Computer Interaction
More Than 63% of IEEE VIS Research Liable to be Retracted?! Ethics Approval Statements Protect Participants (and Researchers!)
We analyzed the ethics reporting in 255 IEEE VIS papers from 2024 and 2025, as published in TVCG. This analysis arose from our experience as readers and reviewers of IEEE VIS papers that such reporting is frequently incomplete or missing, as well as from investigations in which we ourselves had to answer challenges regarding ethics approval in our own work. Visualization research naturally often involves human participants, yet ethics approval and informed-consent procedures are not always explicitly reported. In our corpus, 189 papers (74.1%) reported on work involving human participants. Only 6 of them (3.2%) reported to have obtained ethics approval, an approval identifier, and having received informed consent from the participants, while 26 (13.8%) reported at least ethics approval and informed consent. These omissions do not imply that the empirical work was unethical or lacked approval. They rather show that current reporting practices make ethical approval difficult to assess. Beyond our alarming - yet true - paper title, we wish to raise awareness on how authors themselves may eventually be at risk for not properly reporting ethics. We argue that VIS should adopt clearer and more standardized ethics-reporting practices to protect participants, authors, reviewers, and editors.
Read the full abstract
Artificial Intelligence
NAS-Driven Hardware Accelerator Exploration for Edge AI and Quantization Effects on the Pareto Space
Edge AI deployment demands neural architectures that are simultaneously accurate, computationally efficient, and hardware-deployable - a challenge addressed by hardware-aware Neural Architecture Search (NAS). While recent works incorporate quantization directly into the NAS loop, these approaches expand search complexity and tightly couple architecture and quantization design. The simpler post-search quantization strategy has received little analytical attention: the effects of Post-Training Quantization (PTQ) on the NAS-discovered Pareto structure remain uncharacterised, and no framework combines quantized architecture mapping onto reconfigurable accelerators with automated hardware exploration. This paper addresses both gaps. First, a three-stage pipeline is proposed: a hardware-agnostic Pareto rank surrogate frontend on NAS-Bench-201, a quantization bridge with Pareto-aware filtering and feedback control, and an evolutionary Domain Space Exploration (DSE) backend on CGRA4ML for optimal hardware mapping. Second, an empirical study characterises how INT4 PTQ perturbs the NAS-Bench-201 Pareto space through formal stability metrics on ground-truth data for all 15,625 architectures, and demonstrates that an FP32 zero-shot surrogate outperforms a dedicated INT4-trained surrogate in Pareto space coverage across two standard search strategies.
Read the full abstract
Software Engineering
Refine After Generation: Toward Correct and Concise Patches in LLM-based Program Repair
Large language models (LLMs) have advanced automatic program repair (APR) to the point where agentic systems routinely resolve real-world, repository-level issues. Yet the generated patch has received little scrutiny beyond whether it passes tests. In this paper, we identify patch verbosity as a major yet overlooked concern in LLM-based APR. Characterizing 28 state-of-the-art approaches on SWE-bench Verified, we find that even successful patches are consistently larger and more complex than developer patches, with the median approach producing 121.78% more total changes, 80.91% more net changes, and 43.99% higher cyclomatic complexity. We further show that this verbosity is rooted in capability-oriented design choices such as iterative refinement and broad context, and can hardly be reduced by surface-level controls such as output format or minimality prompts. Motivated by these findings, we formulate post-generation patch refinement and propose RECAP, a lightweight, plug-and-play adapter that attaches to existing repair frameworks after generation. RECAP's refiner is trained via supervised fine-tuning and direct preference optimization with distilled reasoning traces, on a dataset of patch pairs we construct from multiple sources. Across four host systems, prompting, commit-untangling, and minimality-aware baselines reduce patch size only by sacrificing 49 to 217 resolved instances. In contrast, RECAP achieves a substantially better size-correctness tradeoff, cutting average total changes from +242.14% to +4.24% and net changes from +348.24% to -39.75% relative to developer patches while preserving or improving resolution by up to 42 instances. Our results indicate that minimality cannot be simply reduced to syntactic compression, and that decoupling minimization from generation offers a practical path to more reviewable repairs.
Read the full abstract
Cryptography and Security
VR-Themis: A Scalable Framework for Virtual Reality Application Clone Detection
Repackaging of mobile applications (aka app cloning) not only threatens the security and privacy of mobile users but also infringes upon the copyright of the original app developers. However, existing detection methods that primarily focus on mobile platforms (such as Android) fail to capture the essential features of virtual reality (VR). Consequently, they are inadequate for effectively detecting cloned VR apps, which have often been targeted by illegal users in the VR market. Considering the unique features of VR apps, this paper proposes a two-stage app clone detection framework, namely VR-Themis, based on Hierarchy-Object-Behaviour (HOB). Firstly, VR-Themis exploits the coarse-grained stage to cluster apps based on their retrievable statistical features, making this tool scalable to large-scale VR app datasets. Then, in the fine-grained stage, VR-Themis performs in-depth analysis of the suspicious apps (identified in the first stage) by calculating similarity using our defined HOB metrics. Our extensive experiments indicate that VR-Themis successfully detects 307 suspected clone apps from the collected 4,277 VR apps without false positives, demonstrating its effectiveness and scalability.
Read the full abstract
Hardware Architecture
ROLoad-PMP: Securing Sensitive Operations for Kernels and Bare-Metal Firmware
A common way for attackers to compromise victim systems is hijacking sensitive operations (e.g., control-flow transfers) with attacker-controlled inputs. Existing solutions in general only protect parts of these targets and have high performance overheads, which are impractical and hard to deploy on systems with limited resources (e.g., IoT devices) or for low-level software like kernels and bare-metal firmware. In this paper, we present a lightweight hardware-software co-design solution ROLoad-PMP to protect sensitive operations from being hijacked for low-level software. First, we propose new instructions, which only load data from read-only memory regions with specific keys, to guarantee the integrity of pointees pointed by (potentially corrupted) data pointers. Then, we provide a program hardening mechanism to protect sensitive operations, by classifying and placing their operands into read-only memory with different keys at compile-time and loading them with ROLoad-PMP-family instructions at runtime. We have implemented an FPGA-based prototype of ROLoad-PMP based on RISC-V, and demonstrated an important defense application, i.e., forward-edge control-flow integrity. Results showed that ROLoad-PMP only costs few extra hardware resources (< 1.40%). Moreover, it enables many lightweight (e.g., with negligible overheads < 0.853%) defenses, and provides broader and stronger security guarantees than existing hardware solutions, e.g., ARM BTI and Intel CET.
Read the full abstract
Machine Learning
EEG Decoding Using CNN and LSTM Network
Motor imagery (MI) brain–computer interfaces (BCIs) have emerged as a promising approach for establishing flexible communication pathways between the human brain and external devices , particularly for individuals affected by stroke or neurodegenerative disorders. Reliable decoding of motor-imagery electroencephalography (MI-EEG) remains challenging because EEG recordings contain substantial noise and exhibit complex, weakly informative relationships with the underlying brain activity. Although deep learning provides an effective means of learning representations directly from EEG signals, its application to MI-EEG feature learning remains comparatively limited. This study introduces a hybrid deep-learning architecture that integrates a convolutional neural network (CNN) with a bidirectional long short-term memory (bi-LSTM) network. The CNN is used to learn high-level spatial and temporal representations directly from raw MI-EEG recordings, whereas the bi-LSTM models temporal dependencies and relationships among the extracted features. The proposed approach is evaluated using both a publicly available dataset and a privately acquired dataset obtained with an EEG acquisition system. The experimental results indicate that the CNN&bi-LSTM architecture provides robust performance for both two- and three-class motor-imagery classification and demonstrates promising subject-independent decoding capability across the evaluated methods.
Read the full abstract
Robotics
Predictive Relative-Velocity Steering for Safe Robotic Manipulator Teleoperation in Dynamic Environments
Recent advances in teleoperation have enabled robotic manipulators to perform dexterous, human-arm-like motions. However, human operators may fail to avoid suddenly appearing obstacles promptly and effectively, particularly under network latency or limited attention, thereby creating safety risks. To address this issue, we propose a lightweight and modular framework for proactive collision avoidance, operating directly at the end-effector velocity-command level. After preprocessing the point cloud, the framework first predicts potential collisions based on time-to-collision (TTC) with integrated overshoot protection, and subsequently rotates the relative-velocity vector using Rodrigues' rotation formula. The deflection changes only the direction of the relative velocity while preserving its magnitude, thereby mitigating the deadlock problem commonly encountered by conventional artificial potential field (APF) methods. The prediction module compensates for point-cloud processing latency introduced by complex teleoperation pipelines, while the lightweight design enables the high-frequency control required for teleoperation. Simulations across diverse scenarios show that the proposed method achieves a higher end-effector collision avoidance rate than the baseline methods. Experiments on a physical robotic system further validate its collision-avoidance effectiveness.
Read the full abstract
Artificial Intelligence
Towards Context-Aware Clinical Motion Understanding in Daily Living at Home: Freezing of Gait Detection with Egocentric Vision
Understanding motion in daily living requires context beyond kinematics, because similar inertial patterns during activities of daily living (ADLs) can reflect intentional stopping, object interaction, or pathological movement impairment. Egocentric vision provides task-related context that may help disambiguate these cases. We investigate this challenge through freezing of gait (FOG) detection in Parkinson's disease (PD), a symptom strongly influenced by contextual factors during ADLs. Using synchronized egocentric video, wearable IMUs, and expert-annotated FOG labels collected from 13 PD participants in their homes, we evaluate frozen representations from pretrained ego-video and time-series foundation models, alongside an IMU-based TCN trained from scratch, under leave-one-subject-out evaluation. The IMU-based TCN achieved the strongest event-detection performance, reaching 42.3 F1 and 83.0 AUROC, compared with 32.6 F1 and 77.2 AUROC for V-JEPA2 ego-video features. Although ego-video alone did not outperform IMU-based sensing, it showed above-chance discrimination, and qualitative analyses suggest that egocentric vision may capture FOG-relevant information independent of IMUs. Together, these results support the use of pretrained ego-video representations to add contextual information to wearable-sensor-based clinical motion understanding in daily living.
Read the full abstract
Human-Computer Interaction
Print&Fold: Printing and Folding Shape-accurate 3D Models
This paper introduces Print&Fold, a tool to allow FDM 3D printing of complex models with less time and material while preserving shape accuracy. Key to this work is a folding algorithm that planarizes foldable faces internal to the 3D model. While folding techniques typically discretize a target model's surface, thereby fabricating low fidelity counterparts, our method preserves the surface features in the physical print. Our design tool allows users to unfold 3D models to be FDM-printed flat before manually folding these into their target shapes. We showcase a variety of applications and evaluate the material and time savings across a range of 3D models.