Computation and Language
EvalMem: An Operation-Level Diagnostic Framework for Long-Term Memory Systems
Zeyu Liu, Jian Zhong, Rongduo Han et al. (+12 more)
Long-horizon interactions with LLM-based assistants require
memory systems that preserve and update user states, preferences, and interaction histories. Existing evaluations report end-to-end QA accuracy and cannot determine whether errors arise from encoding,
retrieval, or generation. We introduce EvalMem, an operation-level diagnostic framework with three parallel Examiners. For each query, the Encoding Examiner checks whether the target fact is stored, the
Retrieval Examiner assesses whether the native retriever returns usable evidence, and the Generation Examiner tests whether the model can answer from oracle evidence. Their outputs form fine-grained multi-label defect codes. To improve store-level diagnosis, we adapt agentic RAG with a recall-first strategy that searches using both the query and source evidence, increasing recall of present evidence on LoCoMo from 70.2% to 95.6%. Evaluations of seven
memory systems on LoCoMo, LongMemEval-S, and dynamic DynaMem-Bench identify
retrieval as the most frequently attributed failure layer; in default LoCoMo,
retrieval defects reach 22.1%, compared with 7.7% for encoding and 6.5% for generation. Guided by this diagnosis, MemWiki, a search-friendly auxiliary structure built from each system's
memory export, improves mean accuracy by 2.5 and 2.3 percentage points on LoCoMo and LongMemEval-S, respectively.
Read the full abstract ▾
All authors Zeyu Liu, Jian Zhong, Rongduo Han, Ziyang Wu, Shunye Tang, Chenghao He, Yaxuan Yang, Yihang Qiu, Ailing Wang, Xiao Liang, Guohuan Xie, Xiaokang Xue, Gongchen Li, Haining Zhang, Wei Wang
Machine Learning
List Counting Failures Are Not One Phenomenon
Iyad Ait Hou, Saad Mankarious, Aya Zirikly et al. (+1 more)
Counting the items in a bracketed list looks trivial, yet open-weight chat models often get it wrong. Prior work usually blames input bottlenecks such as subword fragmentation or
attention dilution, which predict that different models should fail in roughly the same way. Across seven instruct models on identical
prompts, however, wrong answers form distinct modes: Qwen and Gemma 27B often flip odd lengths to a nearby even integer, OLMo concentrates errors on a few mid-sized integers, and Llama tends to under-count. These modes are useful labels rather than a stable family law (Gemma 9B does not reproduce Gemma 27B's odd-to-even drop), and heavier subword fragmentation does not make counting harder on our
benchmark. When the model answers incorrectly, a linear probe can usually still recover the true count from the residual stream. Matching the same odd-to-even error also does not imply the same late-MLP magnitude fix: scaling a late MLP output helps Qwen modestly but is near null on Gemma 27B under the same protocol, while residual steering can move both only by trading odd gains for even losses. These results caution against transferring that magnitude fix across models without a transfer check.
Read the full abstract ▾
All authors Iyad Ait Hou, Saad Mankarious, Aya Zirikly, Rebecca Hwa
Machine Learning
A Synthetic Multivariate Refrigerator Time-Series Dataset for Predictive Maintenance
Islam Benamirouche, Feriel Fass and Djemel Ziou
We generated synthetic multivariate time series for 27 refrigerators with a simplified physicsinspired simulator at one-minute resolution. The simulator includes ambient-temperature variation, door use, thermostat and compressor operation, heat exchange, defrost, electrical consumption, and six progressive degradation types. Each refrigerator provides 15 to 20 sensor outputs according to its configuration. The
dataset contains 7,066,161 rows in 27 time-series files and 27 failure logs. The release also includes the Python generator, refrigerator configurations, and documentation. The data can support failure prediction, degradation analysis, and learning across refrigerators with different sensor-output sets.
Read the full abstract ▾
Computation and Language
Shaolong Chen, Ang Li, Mingjie Li et al. (+1 more)
Large
language models increasingly rely on long chain-of-thought (CoT) trajectories for complex
reasoning, but autoregressive generation brings substantial
memory and inference costs. Latent
reasoning models (LRMs) offer a more efficient alternative by compressing intermediate
reasoning into a small number of continuous latent vectors. Despite their efficiency, however, the
adversarial robustness of LRMs remains largely underexplored. In this work, we systematically evaluate the robustness of latent
reasoning across textual and
multimodal settings, covering eight models and six
benchmarks. We find that, across our evaluated settings, LRMs are generally less robust than explicit CoT baselines under
adversarial perturbations, with particularly severe degradation under white-box attacks. Further analysis reveals distinct failure modes across modalities: textual latent states exhibit brittle dynamics and high sensitivity to specific input patterns, while latent states in
multimodal models can remain largely invariant to input perturbations and have limited influence on final predictions. These findings expose robustness limitations of current latent
reasoning approaches and highlight the need to jointly consider efficiency and robustness when designing implicit
reasoning systems. We have open-sourced our code to facilitate reproduction of our research https://github.com/PKU-ML/latent-
reasoning-model-assessment.
Read the full abstract ▾
All authors Shaolong Chen, Ang Li, Mingjie Li, Yisen Wang
Information Retrieval
Guiding the coarse levels of semantic IDs makes the fine levels learnable
Bin Wang and Zhengyu Zhang
Generative
retrieval represents each item by a short Semantic ID and casts recommendation as autoregressive generation of that sequence. Because the tokenizer is trained independently to reconstruct an item
embedding, its codes are aligned with neither the downstream LLM nor the end task. Nearly every SID system therefore spends extra effort to bridge this gap–
alignment corpora,
reasoning/RL, or per-
token encoders to make codes legible, or learned tokenizer supervision to make them task-aware–yet the recovered meaning is content-derived and may not be the meaning the task needs. We introduce Guided SID, which instead makes the levels that matter most meaningful by construction: we force the coarse RQ-VAE levels to encode a predefined categorical attribute–chosen to be text-grounded (hence legible to the LLM) and task-relevant–by deterministic supervised index assignment (overriding nearest-neighbor selection with the attribute label) while keeping the codebooks learnable (they still receive reconstruction gradients). A trie-merge construction maps any high-cardinality or set-valued attribute onto the fixed code budget while keeping merged buckets semantically coherent. Guiding costs nothing intrinsically: collision and reconstruction match or beat the vanilla baseline despite pinning the coarse level. In a matched end-to-end A/B differing only in the SID encoding, the guided retriever improves recall@k at every list length we measure (1.36x at k=1, 1.39x at k=10), raises mean reciprocal rank from 0.0260 to 0.0355, and predicts the pre-defined attribute 4.2x more often.
Read the full abstract ▾
Computation and Language
Swiss-Knife: A Framework for Reconfigurable Externalised Multi-Objective Alignment at Decode Time
Agnibh Karmakar, Mayur Parvatikar, Shreyash Dhoot et al. (+5 more)
Decode-time
alignment methods steer a frozen
language model by scoring candidate continuations with an external reward and selecting the maximiser. We argue that this shared design is a single degenerate point in a much larger space. We introduce Swiss-Knife, a framework for externalised multi-objective
alignment in which the
alignment specification is a first-class runtime object: hot-swappable scoring blades, a batch normaliser, a pairwise aggregation operator, and a selection rule. Six axioms characterise the admissible aggregation operators, and we prove a representation
theorem: every operator satisfying them has the form $R_i = \sum_{j \neq i} g((\mu_i - \mu_j)/s(\sigma_i,\sigma_j))$, a two-parameter family containing probit and logistic comparison rules and pointwise argmax as named coordinates. Within it, pairwise aggregation is Lipschitz-stable under
adversarial reward contamination while argmax is not, and Candidate-Batch Normalization (CBN) makes the weight simplex invariant to the rescalings under which reward models are only ever identified. Our reference instantiation pairs DPO-LoRA blades with an uncertainty-aware pairwise tournament. Sweeping the helpfulness/honesty/harmlessness simplex, it attains the best balanced frontier of six decode-time methods (harmonic $F_1$ 0.797 vs. 0.750 for the strongest baseline, $p < 10^{-14}$) with the lowest refusal rate and highest helpfulness of any arm, and reconfigures its objectives in 0.05 ms with no gradient computation. Ablating CBN costs 0.217 $F_1$, and the metadata confirms the predicted mechanism: the lowest-variance blade retains 9% of its nominal 33% influence, and the collapse follows the predicted ordering.
Read the full abstract ▾
All authors Agnibh Karmakar, Mayur Parvatikar, Shreyash Dhoot, Amit Dhanda, Aman Chadha, Kapil Wanaskar, Vinija Jain, Amitava Das
Graphics
Cascaded Non-Line-of-Sight Imaging
Diego Royo, María Peña, Forrest B. Peterson et al. (+3 more)
Time-of-flight non-line-of-sight (NLOS) imaging recovers information from hidden objects by analyzing the time of flight of indirect
photons scattered on a visible (relay) wall. Most methods make the simplifying assumption that
photons travel exclusively three-bounce paths, thus ignoring other useful information encoded in higher-order
photons (with, e.g., four- or five-bounce paths). We present a novel cascaded NLOS imaging approach that leverages higher-order information and allows imaging a broader range of single- and multi-corner scenarios. We combine ultra-fast
laser scanning with recent time-gated 2D sensor arrays to capture the scene's impulse response on a visible relay wall. From the captured impulse response, our method computes an analogous virtual impulse response at any other hidden wall. This effectively allows us to concatenate a second, virtual NLOS imaging system that leverages higher-order illumination. We validate our cascaded imaging method both in simulation and with a real prototype, demonstrating NLOS imaging with fourth- and fifth-bounce illumination of objects in challenging orientations and hidden around two corners. We also analyze how wave-based NLOS imaging interacts with rough hidden walls, which explains and helps overcome existing visibility limitations. We further illustrate how to image hidden objects from different perspectives, thus observing previously unseen features, by relying on multiple hidden walls.
Read the full abstract ▾
All authors Diego Royo, María Peña, Forrest B. Peterson, Andreas Velten, Julio Marco, Diego Gutierrez
Robotics
GzDRL: Reproducible and Scalable Deep Reinforcement Learning with Gazebo
Amal Dev Haridevan, Junjie Kang and Jinjun Shan
We present GzDRL, a novel single-process reinforcement learning (RL) framework for Gazebo that overcomes longstanding bottlenecks in scalable, reproducible robotics experimentation. Unlike conventional middleware-based RL-Gazebo integrations that suffer from nondeterminism and irreproducibility, GzDRL introduces a systematic, middleware-free environment-stepping mechanism that directly synchronizes
agent actions and physics updates. This design enables deterministic, high-throughput data collection, efficient vectorization, and reproducible RL training and evaluation. Comprehensive
benchmarks demonstrate that GzDRL achieves the highest workstation throughput among the evaluated frameworks while remaining competitive with GPU-accelerated simulators on laptop hardware, and maintains precise
agent-environment synchronization, multi-
agent scalability, and experiment-level reproducibility. We further validate sim-to-real transfer by deploying learned policies directly onto a physical quadrotor, without fine-tuning. Our results establish GzDRL as an accessible and reproducible platform for advancing RL in robotics and automation.
Read the full abstract ▾
Machine Learning · Cross-listed from physics.ao-ph
Calibrating subgrid parametrizations of single-column ocean models via simulation-based inference
Luben M. C. Cabezas, Sacha Wendling, Aurèle Gallard et al. (+3 more)
Subgrid parametrizations of vertical mixing in ocean models depend on free coefficients that cannot be measured directly and must be calibrated against high-fidelity references such as large-eddy simulations (LES). Existing approaches return point estimates and leave the associated uncertainty unquantified, a limitation when the inverse problem is ill-posed or when distinct parameter configurations fit the data comparably well. Simulation-based inference (SBI) addresses exactly this: given a prior and access to the simulator, it approximates the full posterior over parameters without requiring a tractable likelihood, at a cost set by the number of simulator evaluations. We apply it to tunax, a JAX-based single-column ocean model, to calibrate the coefficients of its $k$–$\varepsilon$ closure. A blockwise PCA summary statistic compresses the simulator output along the depth axis while preserving its forcing–horizon–variable structure, making inference tractable at modest budgets. We compare neural posterior estimation and its sequential variants against a recent training-free approach built on a tabular foundation model. The latter recovers informative posteriors from a few hundred simulator calls, outperforming the trained
estimators at every budget considered.
Read the full abstract ▾
All authors Luben M. C. Cabezas, Sacha Wendling, Aurèle Gallard, Gabriel Mouttapa, Julien Le Sommer, Pedro L. C. Rodrigues
Digital Libraries
LLM Signals in Funded Grants: Evidence from International Funding Agencies
M. Z. Naser
The release of ChatGPT in November 2022 introduced a writing tool of unprecedented fluency into the daily routines of researchers across the sciences. Prior work has measured what follows in journal abstracts and in peer reviews by documenting an upward shift in the frequency of words and short phrases that large
language models (LLMs) tend to overproduce. However, a much less-examined question concerns whether the same shift extends to grant proposals, the documents through which researchers compete for public funding, and, in particular, to the subset of proposals that succeed. Such a distinction is important to note because funded grants represent decisions to allocate public research resources, and because the proposing population spans every scientific discipline in which a country supports research. This brief report draws on an analysis of 221,425 funded grant abstracts from three major science-funding agencies in two countries: the U.S. National Science Foundation (NSF), the U.S. National Institutes of Health (NIH), and UK Research and Innovation (UKRI). The window covers late 2017 through mid-2026, providing roughly 5 years of pre-ChatGPT baseline and 3.5 years of post-release observation in each corpus.
Read the full abstract ▾
Computer Vision
ArtSociety: Multi-Agent Multimodal Collaboration for Art Emotion Understanding
Jian Li, Fanfan Ji, Jinxiang Lai et al. (+5 more)
The AffectiveArt Multidimensional Art
Emotion Understanding task asks to jointly predict an artwork's fine-grained
emotion (12 classes, 1549:1 head-to-tail ratio), binary valence/arousal, and five attribute-grounded descriptions – sub-tasks that exhibit strong empirical trade-offs, so the single-model solutions we tried do not jointly optimize all of them well. We present ArtSociety, a multi-
agent framework that assembles heterogeneous
multimodal experts – a DINOv2-
Giant vision agent (A1), a scene-grounded CoT fine-tuned MLLM (A2), and three closed-source
reasoning agents (A3-A5) – and coordinates them with two training-free controllers: (i) a rare-class-aware voting arbiter that lowers the agreement threshold for tail
emotions, exploiting decorrelated error patterns across
agent families; and (ii) a description-first
reasoning agent whose DESCRIBE-then-CLASSIFY chain of thought forces visual evidence before label commitment, yielding near-perfect grounded descriptions. A task-routing policy directs the hard
emotion task to the full five-
agent ensemble while assigning the near-saturated valence/arousal and generative description tasks to the single strongest
reasoning agent. On the official test set (1,000 artworks), ArtSociety achieves an Overall Score of 0.8870 (Classification 0.7789, Description 0.9952). An eleven-variant ablation study reveals that, once method and scale saturate at around 0.76, the decisive gains come from
agent collaboration and data-side supervision – a 30B MoE model trained on older data does not outperform an 8B model trained on better data. Code is available at https://github.com/swordlidev/ArtSociety
Read the full abstract ▾
All authors Jian Li, Fanfan Ji, Jinxiang Lai, Ying Tai, Jian Yang, Xiao-Tong Yuan, Chengjie Wang, Yabiao Wang
Computer Vision
Abstract-LoRA: Unlocking Single-Image Style Transfer through Targeted U-Net Block Training
Xinglin Hu
Diffusion models represent one of the most advanced paradigms in generative modeling. Leveraging their development, a growing number of style transfer methods based on
diffusion models have been proposed. However, among these methods, multi-image style transfer approaches that require at least five to ten style examples tend to achieve more satisfactory results. Single-image methods, by contrast, often struggle with either insufficient content preservation or inadequate style fidelity. This greatly limits style extraction from scarce artworks and undermines their artistic value. To address this, we propose Abstract-LoRA, a method that pushes the boundaries of single-image style transfer through lightweight LoRA training on specific U-Net blocks in
diffusion models. Specifically, our work is inspired by B-LoRA, a style transfer method that achieves basic style-content disentanglement by training specific U-Net blocks. However, it suffers from a critical limitation: the inability to capture complex backgrounds. Building upon B-LoRA, our method conducts a more refined analysis of U-Net blocks, employing additional U-Net blocks and clustering-based abstraction of style images to better disentangle and balance style and content. Extensive experiments demonstrate that our proposed method not only generates visually more harmonious and satisfying artistic images but also quantitatively improves the preservation of both style and content in the final outputs.
Read the full abstract ▾
Neural and Evolutionary Computing
CompEvo: Competition-Induced Evolution for Multi-Agent in News-Driven Time Series Forecasting
Yuxuan Zhang, Yangyang Feng, Yong Guan et al. (+6 more)
News-driven time series
forecasting uses evolving textual events together with historical observations to predict future values, supporting applications such as
market risk monitoring and resource scheduling. In multi-
agent settings, two challenges still remain. The first is degeneration of thought, where
agents converge to similar evidence-seeking behaviors. The second is insufficient theoretical grounding, where strategy updates are often heuristic and lack a principled formulation. To address the above challenges, we propose CompEvo, a competition-induced
evolution framework for multi-
agent news-driven time series
forecasting. For theoretical grounding, we introduce an evolutionary game formulation to guarantee
equilibrium existence and optimization convergence. Building on this formulation, we construct a trainable multi-
agent evolution framework that integrates strategy execution, fitness-based differentiable selection, and competition-induced strategy
evolution. CompEvo enables heterogeneous
agents to explore diverse news evidence, converts
forecasting feedback into differentiable influence weights, and evolves
agent strategies under competitive pressure to preserve effective logic while maintaining diversity. Experiments on four real-world
datasets show that CompEvo reduces RMSE by 27.3% and MAPE by 26.2% on average over strong baselines. Further analysis indicates that CompEvo successfully maintains diverse and specialized
agent behaviors.
Read the full abstract ▾
All authors Yuxuan Zhang, Yangyang Feng, Yong Guan, Daifeng Li, Kexin Zhang, Junlan Chen, Bowen Deng, Jun Liu, Zehua Zeng
Numerical Analysis
Geometry Parameterisation via a Structural Modal Basis for Aerodynamic Shape Optimisation
Alwin Wang, Robert Carrese, Luca Brown et al. (+2 more)
Aircraft outer mould lines are often heavily constrained early by payload requirements, manufacturability limits, and low-observability considerations. The remaining aerodynamic design space is typically small, highly constrained, and difficult to represent using a concise and physically meaningful set of design variables. A structural modal parameterisation method (MPM) is introduced for such problems. The method constructs a tunable pseudo-structure and solves its
eigenvalue problem to obtain a modal basis, from which a selected subset of modes parameterises the geometry. Boundary conditions, stiffness distribution, density, thickness, and added masses are treated as intentional basis-design variables that shape the admissible deformation space prior to optimisation. The resulting design coordinates are independent of any specific flow solver, making the approach broadly applicable. For tightly constrained aerodynamic shape optimisation problems, it provides a practical balance of parameter conciseness, robust constraint awareness, and
geometric flexibility.
Read the full abstract ▾
All authors Alwin Wang, Robert Carrese, Luca Brown, Joel Collins, Pier Marzocca
Distributed Computing
Toward Sustainable Distributed LLM Inference: A Systems Synthesis and Research Agenda for an Energy-, Carbon-, and Cache-Aware llm-d Control Plane
Twinkll Sisodia
Large
language model (LLM) sustainability is increasingly a serving-systems problem, not only a training problem. In production, energy and carbon impact depend on more than model size: workload shape, batching, key-value (KV) cache reuse, prefill/decode placement, model and accelerator choice, power state, geographic carbon intensity, and service-level objectives (SLOs) all matter. Recent systems papers study many of these factors separately. This paper connects those results and asks a practical engineering question: what do they imply when the decision point is a distributed inference control plane such as llm-d? The contribution here is synthesis, not a new set of
benchmark results. Reported performance, energy, carbon, and cost improvements remain the results of the cited papers and systems. I group the literature into recurring design patterns and use those patterns to sketch a Sustainable Inference Control Plane (SICP) for llm-d. The proposed control plane would consider latency, energy, carbon, cache reuse, serving cost, and quality when routing and scaling, while keeping TTFT/TPOT SLOs as hard constraints. I also outline an evaluation framework based on SLO-satisfied goodput per joule and per gram CO2e, together with a reproducible experimental plan. The main observation from connecting the literature is that sustainable LLM inference is unlikely to come from one "green" model or one accelerator; it is more naturally treated as a control problem across model, phase, cache, hardware, replica, region, and time.
Read the full abstract ▾
Cryptography and Security
Constructions of complete permutations over $\mathbb{F}_q^n$
Sartaj Ul Hasan, Ramandeep Kaur, Hridesh Kumar et al. (+2 more)
Complete permutation
polynomials play an important role in cryptography, particularly in the design of cryptographic primitives such as the Lai–Massey scheme and S-boxes. We generalize a result of Sun, Li, Guo, and Qu (2021) by characterizing the complete permutation behavior of the mapping $\Psi(X)=M(X+\psi(AX))$ over $\mathbb{F}_q^n$, where $\mathbb{F}_q$ is a finite field of $q$ elements with $q$ being a
prime power, $M\in GL(n, \mathbb{F}_q)$, $GL(n, \mathbb{F}_q)$ is the general linear group of order $n$ over $\mathbb{F}_q$, $A_{m \times n}$ is a full-rank
matrix over $\mathbb{F}_q$, and $\psi=(\psi_1,\psi_2,\ldots,\psi_n)$ with each component function $\psi_i:\mathbb{F}_q^m\to\mathbb{F}_q$. Furthermore, we establish criteria for the permutation and complete permutation properties of the mapping $F(X)=T(X+B^tf(AX))$ over $\mathbb{F}_{q}^n$, $f: \mathbb{F}_{q}^{m} \rightarrow \mathbb{F}_{q}^{n-m}$, $T \in GL(n, \mathbb{F}_q)$, $A_{m \times n}$ and $B_{(n-m)\times n}$ are full-rank
matrices over $\mathbb{F}_q$, $B^t$ represents the transpose of the
matrix $B$, and $0<m<n$ are integers. These results also generalize an earlier result of Gravel and Panario (2023), who showed that any arbitrary function $f$ from $\mathbb{F}_q^m$ to $\mathbb{F}_q^{\,n-m}$ can be extended to a bijection over $\mathbb{F}_{q}^n$ through the mapping $F(X)=T(X+B^tf(AX))$, under the condition $AB^t=0$. Here we do not impose the restriction that $AB^t=0$.
Read the full abstract ▾
All authors Sartaj Ul Hasan, Ramandeep Kaur, Hridesh Kumar, Daniel Panario, Qiang Wang
Software Engineering
Look Before You Prompt, and After: Scaffolding Human-AI Collaboration in Software Tutorial Creation
Avinash Bhat, Vy Bui and Jin L.C. Guo
With LLMs, creating software tutorials now involves steering the model's output and shaping it into a coherent, accurate learning resource, yet existing LLM tools offer writers little support for this work. By analyzing interviews with technical writers ($N=17$), we identify three requirements for how they assemble and structure multiple LLM responses, curate the context the model uses, and verify the generated content. We designed a tool called dBlocks with the following features: blocks to scope content, a context manager to edit context, and inline execution to verify code. Following a human-centered design method, we iteratively refined the design through a user study ($N=5$). In a within-subjects lab study ($N=16$) comparing dBlocks with participants' preferred workflows for LLM-assisted authoring, participants reported significantly higher confidence in the tutorials they produced with dBlocks. In addition, the tool reduced friction in verification, with writers verifying code as they drafted rather than deferring or skipping it, and helped them avoid searching long chat histories by scoping their work into blocks that kept each tutorial section and its LLM conversation together. More broadly, our work offers implications for tools that scaffold human-AI collaboration in SE workflows and shows how human-centered design can guide the development of LLM-integrated tools.
Read the full abstract ▾
Machine Learning · Cross-listed from stat.ML
Rollcast: Proper-Score Gated Rolling Anchors for Adaptive Probabilistic Time-Series Forecasting
Giancarlo Vercellino
Rollcast is a probabilistic
forecasting method for univariate time series that combines a compact set of rolling statistical anchors rather than relying on a single global model. Rolling means, medians, extrema, regression endpoints, and
quantiles define candidate forecast locations and a representation of the current state. A state-dependent softmax gate learns anchor probabilities by minimizing negative log predictive density, while residual distributions retrieved from similar historical states provide local uncertainty. Recursive simulation propagates the resulting mixture over multiple forecast horizons. The method is evaluated in a Monte Carlo study covering eight data-generating processes, including autoregressive, random-walk, local-trend, threshold, regime-switching,
stochastic-
volatility, heavy-tailed, and variance-break dynamics. Across 2,000 independent fitted series, Rollcast is compared with the true conditional predictive distribution generated by an oracle simulator. Overall empirical coverage is 86.2% for nominal 90% intervals and 91.5% for nominal 95% intervals. Predictive intervals are on average 13.6% wider than the oracle at the 90% level, while CRPS is 14.4% higher than oracle CRPS. Performance is closest to the oracle under autoregressive, threshold,
stochastic-
volatility, heavy-tailed, and variance-break dynamics, while local trends and regime switching are more challenging. The results indicate that Rollcast can construct competitive probabilistic forecasts from simple, interpretable local summaries, while also identifying limitations in calibration and recursive uncertainty propagation.
Read the full abstract ▾
Computational Engineering
LLM-Aided Design for Manufacturing: A Multi-Agent System for Intent-Preserving Redesign of CAD for Improved Manufacturability
Kojo Welbeck, Xiangyu Shi, Zahra Sadeghi et al. (+2 more)
We introduce autonomous, intent-preserving Design for Manufacturing (DFM) redesign of CAD parts: given an engineer's CAD model, the method returns a variant that is easier to manufacture without losing its design intent. Generating such a redesign in a single shot is unreliable, since CAD fidelity degrades as parts grow complex; we instead produce it as a sequence of individually verified design transitions. Our DFM-Redesign pipeline realizes this with two coupled
agent subsystems driven by a pretrained
multimodal LLM: a DFM Reviewer that inspects the current design and proposes one intent-preserving manufacturability improvement at a time, and a CAD Modifier that executes each proposal as an edit to the part's CadQuery program. The CAD Modifier closes a verification loop, compiling every candidate edit and visually checking it against the intended change from multi-view renderings, then re-generating or re-instructing until the edit is accepted or abandoned. Iterating review and verified modification compounds edits into parts more complex than one-shot generators reliably produce, preserves the original intent at each step, and requires no fine-tuning. On a 46-part
benchmark scored by chamfer distance to reference geometries, the CAD Modifier reproduces target parts more accurately on average than chain-of-thought single
agents given the same tools, and ablations isolate the contributions of the visual review loop and of captioning the design state before each edit. A centrifugal pump casing built from 32 chained transitions illustrates the complexity reachable by compounding verified edits. This is a preliminary report: evaluation of the full review-and-redesign loop, including manufacturability gain and an operational measure of intent preservation, is ongoing.
Read the full abstract ▾
All authors Kojo Welbeck, Xiangyu Shi, Zahra Sadeghi, Qi Zhu, Ping Guo
Artificial Intelligence
EdgeMem: LLM-Free Agent Memory Construction and Retrieval via Evidence-Preserving Multi-Anchor Hypergraph
Zeyang Cui, Jiannong Cao, Zhiyuan Wen et al. (+3 more)
Agent memory allows LLM
agents to use earlier interactions when answering new queries. Existing methods often compress interaction histories into summaries or other LLM-generated representations. Repeated generation adds cost and can discard answer-bearing details before the system knows what a future query will require. We propose EdgeMem, an
agent-
memory method built around a simple principle: preserve original interaction turns and organize them through complementary content, temporal, and episodic cues. EdgeMem realizes this principle with a multi-anchor hypergraph constructed by lightweight local processing.
Retrieval directly returns source evidence and reserves LLM use for final answer generation, combining structured access to multi-session histories with faithful retention of the original conversation. Experiments on LoCoMo and LongMemEval-S show strong
retrieval and
memory-grounded question answering; on LoCoMo, EdgeMem achieves the highest strict-judge score among seven reproduced systems under a shared
prompt (61.01 versus 58.70), while construction and
retrieval require no generative-LLM calls. Overall, EdgeMem shows that preserving and organizing source evidence provides an effective and efficient foundation for
agent memory without generative
memory management.
Read the full abstract ▾
All authors Zeyang Cui, Jiannong Cao, Zhiyuan Wen, Bo Yuan, Junlan Feng, Shengyuan Chen
Human-Computer Interaction
An Agent Model Abstraction for Human-AI Teaming Cognitive Coupling
Kolitha Kottagaha W.M, Jos A.C. Bokhorst, Ben Gaffinet et al. (+1 more)
Industrial environments increasingly rely on collaboration between humans and AI-enabled
agents. Effective teamwork requires aligning how
agents perceive situations, plan actions to pursue goals, and adapt to changing conditions, yet existing systems lack mechanisms for cross-
agent cognitive processes coupling. This paper presents a conceptual cognitive
agent model that formalises cognitive coupling through eight components: Input, Process, Output, State, Value,
Memory, World Model, and Goal. The model abstracts how
agents coordinate and co-regulate their cognitive cycles, providing a basis for analysing distributed cognition and designing cognitively interoperable human-AI systems.
Read the full abstract ▾
All authors Kolitha Kottagaha W.M, Jos A.C. Bokhorst, Ben Gaffinet, Christos Emmanouilidis
Computer Vision
Subject-Relative Micro-Motion and Sleep Dynamics for Near-Infrared Video Sleep Staging
Kunmin Jang, You Rim Choi, Hun Heo et al. (+5 more)
Near-infrared (NIR)
video is a promising modality for contactless sleep monitoring, but recent
video-based sleep staging methods often use it as a route to reconstructed respiratory/cardiac proxies or cross-modal physiological representations. We study
video-only sleep staging under labels defined by polysomnography (PSG), where the model infers sleep stages from NIR
video alone without explicit physiological proxy reconstruction or auxiliary physiological signal supervision. This tests whether NIR
video itself can provide informative sleep-stage evidence, rather than only serving as an input for recovering physiological proxies. We propose ViNUSS (
Video-Native Unmediated Sleep Staging), a framework that combines subject-relative micro-motion learning with full-night sleep dynamics modeling. Spatially anchored pre-spatial micro-motion encoding preserves localized temporal variation together with its spatial context. Within-subject stage contrast learns stage cues with respect to each subject's night-specific baseline. Two-scale sleep dynamics modeling captures within-epoch motion
evolution and organizes epoch-level evidence into a coherent full-night sleep-stage trajectory. On 475 overnight NIR recordings (~3,250 hours), ViNUSS achieves 0.80 accuracy and 0.78 macro-F1 for four-class sleep staging. Interpretability analysis suggests
attention to thoraco-abdominal periodic motion and gross body movements associated with arousals and position changes. These results support NIR
video as an independently informative and complementary modality for PSG-defined sleep-stage estimation
Read the full abstract ▾
All authors Kunmin Jang, You Rim Choi, Hun Heo, Heonjun Lee, Suahn Bae, Dongik Park, Hyun-Woo Shin, Hyung-Sin Kim
Graphics
LayoutShop: Content-Constrained Exploratory Design of Creative Article Layout
Jialuo Li and Pengfei Xu
We present LayoutShop, a novel computational framework for designing creative layouts that frame a given article. Inspired by the actual article layout design process, we enable users to create or select layout templates for conceptualization. These templates help construct a layout design space to extract eligible layout structures. Our
algorithm then determines the geometry of the extracted layout structures to frame the given article via an optimization approach. We then employ two neural networks for layout assessment, and the high-quality outputs are returned to users for selection. We conducted a user study to evaluate the framework's usability and the quality of the article layouts it produces. The results of the user study confirmed that our framework can effectively help users create high-quality article layouts.
Read the full abstract ▾
Software Engineering
Dynamic Adaptation of the LLM Context for Generating Routines with Coupled Semantics
Gnaneswar Villuri, Hashmath Shaik and Alex Doboli
LLM-based code generation fails when correctness depends on execution-dependent coupling: the meaning of one routine is defined by the runtime behavior of another, a relationship that cannot be resolved from textual descriptions alone. This limitation, which we call static binding, is not confined to explicitly coupled problems; it appears to varying degrees whenever correctness depends on joint execution behavior across components, from explicit cross-coupled optimizers to subtler joint constraints in packing, routing, and symbolic search. This paper proposes dynamic context adaptation, a sample-efficient validation-generation loop designed for this setting. A validation
agent extracts structured diagnostic information from execution traces, providing gradient-like guidance to a generation
agent that proposes multiple candidates per iteration. A knowledge graph derived from the problem description supplies semantic constraints to the generation
agent. Simulated annealing selects among candidates to avoid greedy collapse. Our method outperforms zero-shot, Reflexion, and OpenEvolve on seven of eight problems at both 300 and 600 evaluations (p < 0.01), a regime where population-based search has not yet accumulated sufficient diversity to compete. Notably, on the primary motivating problem (cross-coupled optimization), our method also achieves the best score at 1000 evaluations, consistent with the hypothesis that structured execution feedback is most beneficial when correctness depends on runtime coupling. Ablation results confirm that structured execution feedback is the primary driver.
Read the full abstract ▾
Cryptography and Security
Optimizing Credential Blast Radius Through Trust Boundaries and Delegation Under Post-Quantum Authentication Costs
Pauli Taipale and Harri Lainio
Partitioning interacting services into independently rooted trust domains limits issuer-compromise reach while increasing calls across trust boundaries. Post-
quantum replacements for public-key authentication and key-establishment mechanisms can increase crossing latency on constrained or lossy paths. We formulate the joint selection of trust domains and credential-derivation structures under policy and latency constraints, linking separate service-interaction and credential-derivation graphs through domain assignment. Credential blast radius measures weighted service impact after compromise. A linear upper bound supports optimization, while a joint event model gives exact expected impact. We identify when risk from issuers trusted across domains can be incorporated into this linear score, avoiding separate issuer-propagation calculations for each candidate. Although the general problem is NP-hard, we identify restricted cases that can be solved efficiently and exactly. Joint optimization yields lower blast radius than choosing boundaries first in 195 of 230 exhaustive synthetic comparisons, especially under chained delegation. A trace-derived replay used measured post-
quantum costs, synthetic risk inputs, a fixed derivation family, and one to six trust domains. Under independent compromise events, mean expected impact was up to 36% lower than with one domain within the latency budget. The framework turns risk assumptions and measured crossing costs into candidate trust-domain and credential-derivation designs.
Read the full abstract ▾
Artificial Intelligence
Extremely Sparse Supervision Incentivizes Reasoning Ability
Zhishuai Liu, Xingzi Xu, Mehmet Saygin Seyfioglu et al. (+2 more)
Large
language models demonstrate increasingly strong
reasoning capabilities through effective post-training. Yet, prevailing post-training methods optimize over massive numbers of
tokens, implicitly assuming that effective learning must be
token-intensive. We revisit this assumption in the on-policy
distillation (OPD) setting, which naturally admits dense teacher supervision at every generated
token. Using the Qwen3 family, we discover a counter-intuitive phenomenon:
reasoning can be effectively incentivized by an extremely small fraction of generated
tokens–as few as one or two
tokens per
reasoning trajectory, corresponding to only 0.05% of all
tokens. Surprisingly, this sparse supervision in most cases matches or surpasses full-
token training in improving
reasoning ability, despite excluding the vast majority of generated
tokens from the training objective. This phenomenon is consistently observed across nine teacher–student configurations spanning different model scales on mathematical
reasoning tasks, and is further validated on coding
reasoning, Llama models and Proximal Policy Optimization (PPO)-based reinforcement learning with verifiable reward (RLVR). Interestingly, such extremely sparse supervision may be closer to the natural learning process: rather than correcting every step word by word, one reflects on a few critical
reasoning steps, updates prior understanding, and continues the trial-and-error, avoiding micro-level corrections while remaining remarkably effective. Overall, our results challenge the assumption that effective post-training must be
token-intensive and point to a new direction for understanding and designing more efficient post-training
algorithms.
Read the full abstract ▾
All authors Zhishuai Liu, Xingzi Xu, Mehmet Saygin Seyfioglu, Pan Xu, Karim Bouyarmane
Artificial Intelligence
La Agente Óptima: Towards Agentic Self-Driving Laboratories
Marcel Müller, Jiaru Bai, Willi Gottstein et al. (+14 more)
Self-driving laboratories (SDLs) combine automated experimentation with adaptive decision-making to accelerate scientific discovery. Their operation nevertheless often depends on human specialists who translate scientific objectives into executable closed-loop campaigns. Specialists adjust them as data and operating conditions change. Here, we present La Agente Óptima, an agentic framework that constructs and supervises
Bayesian optimization campaigns across computational and experimental systems while maintaining a persistent optimization state. By separating large
language model (LLM)
reasoning from executed campaigns, Óptima runs repetitive optimization loops consistently, returns control to the
agent only when progress requires interpretation or campaign revision, and keeps every decision auditable. We evaluate Óptima across ablation studies, five digital discovery tasks, and two physical platforms. Throughout, Óptima maintained executable campaigns as both the scientific problem and execution environment evolved. In a closed-loop contact angle optimization campaign, Óptima identified and corrected a mid-run measurement failure, bringing the contact angle from 71.4 to 67.8 degrees, just above the 64-66 degree range. From this result, Óptima correctly inferred that the target was likely unattainable with the available reagents and recommended changing the formulation. In a five-day multi-objective flow-chemistry campaign, Óptima increased the yield from 30% to 59% over 23 experiments. Despite substantial inference costs, it cost less and used substantially less starting material than a human-directed campaign, while selecting a more mass-efficient operating point. These results show that LLM-based
agents can make rigorous, long-running optimization campaigns accessible to domain scientists without specialist setup, expanding the scope of SDLs.
Read the full abstract ▾
All authors Marcel Müller, Jiaru Bai, Willi Gottstein, Abhijoy Mandal, Mohammad Nazeri, Elia Savino, Yanlin Fang, Sujoy Das, Sergio Pablo García Carrillo, Yeonghun Kang, Juan B. Pérez-Sánchez, Simone Pilon, Martin Fitzner, Timothy Noël, Frank Gu, Varinia Bernales, Alán Aspuru-Guzik
Artificial Intelligence
Reducing Hallucinated Transcripts in Whisper via Hallucination Space Projection
Maryam Abbasihafshejani and Murtuza Jadliwala
Whisper is a widely used foundation model for automatic
speech recognition (ASR), but its generative decoder can produce fluent hallucinated transcripts for inputs containing little or no
speech. We propose a training-free, inference-time method to reduce these
hallucinations using low-rank projection of decoder activations. A compact
hallucination-associated subspace is estimated from non-
speech calibration data, and decoder hidden states are projected away from this subspace during inference. We evaluate two variants: always-on, which applies projection to all inputs, and gated, which applies it only when Whisper predicts that an input is likely non-
speech. Across non-
speech benchmarks, always-on projection reduces average
hallucination rate (HR) from 31.31% to 2.44%, a 92.21% relative reduction, while gated projection reduces HR to 3.74%, an 88.05% relative reduction, with lower false rejection of genuine
speech. On LibriSpeech, gated projection increases absolute word error rate (WER) by 0.33-4.39 percentage points and yields false-rejection rates (FRR) of 0.41–9.97% across model and split settings. These results show that low-rank activation projection can substantially suppress Whisper
hallucinations without retraining, while providing a controllable trade-off between
hallucination suppression and
speech recognition performance.
Read the full abstract ▾
Artificial Intelligence
IPGeoAI: Transformer-Based Geolocation with LLM Semantic Fusion
Avinash Kadimisetty, Andy Jinqing Yu, Philip Favaloro et al. (+2 more)
Accurate city-level IP Geolocation is an important enabler for the modern digital ecosystem, underpinning services ranging from local content delivery and targeting to digital rights enforcement. However, traditional heuristic and database-driven methods often struggle to resolve the complex, non-linear allocation patterns of modern network infrastructures, particularly within the exploding IPv6 address space and transient mobile networks. In this paper, we introduce IPGeoAI, a novel deep learning model architecture that reframes geolocation from a static lookup problem to a sequential modeling task. Our approach utilizes the
Transformer Encoder to capture hierarchical dependencies inherent in IP subnet structures. We propose a method to resolve geographic ambiguity by integrating unstructured semantic context via a Zero-Shot LLM Feature Extraction pipeline. We utilize Large
Language Models to transform raw, noisy Autonomous Systems (AS) descriptions into structured, domain-specific metadata (such as 'University' vs. 'ISP' or 'Global' vs. 'Local') via an offline pre-computation process. By fusing these semantic signals into the network via a Multi-Head Cross-
Attention module, we bridge the gap between numerical network
topology and real-world semantic identity. Extensive offline evaluation on a proprietary
dataset spanning 200,000 cities demonstrates that IPGeoAI significantly outperforms a leading external vendor in city-level granularity. By adopting a hierarchical inference strategy that refines coarse-grained country signals, our model achieves a 6% improvement in city-level accuracy while extending coverage to 100% of the traffic. Furthermore, in large-scale online production tests, the model drove a statistically significant +0.35% improvement in our 1st-tier downstream use cases metric.
Read the full abstract ▾
All authors Avinash Kadimisetty, Andy Jinqing Yu, Philip Favaloro, Wenlong Liu, Xiaolu Xiong
Machine Learning · Cross-listed from quant-ph
A Sim-to-Real Study of Surface-Code Decoder Benchmarking
Shay J. Manor, Leila S. Erhili and Yassine Jebbouri
Quantum error-correction decoders are typically benchmarked against synthetic
circuit-level noise, under the assumption that a decoder's ranking under such noise transfers to hardware and improves as the noise model becomes more realistic. The Willow processor, the first to operate below the surface-code threshold, allows us to test this assumption. We rank a panel of six decoders using a four-rung ladder of noise models with increasing fidelity, evaluated against real data across three code distances, two bases, and fifteen round counts. Rank agreement with hardware appears once the noise model gives each operation type its own error rate. Calibrating the model to the device improves absolute error rates but not rank agreement. We additionally provide the first independent evaluation of NVIDIA's Ising pre-decoder on hardware, at code distances below its training receptive field and via a mapping onto the
lattice on which it was trained. Under these conditions, it holds no accuracy-latency advantage: another panel decoder matches or improves on it in both per-cycle error rate and decode latency in 278 of the 280 evaluations. We release the full pipeline and the per-shot outcome of every evaluation, so future decoders and devices can be compared.
Read the full abstract ▾