Machine Learning
Differential Privacy of Gradient Descent on Perturbed Objectives
Austin Watkins and Raman Arora
Objective perturbation adds a random linear term to a regularized empirical risk and releases the exact perturbed minimizer. We study the finite computation obtained by releasing the $N$-th iterate of deterministic gradient descent on $w\mapsto F(w;S)+\langle z,w\rangle$, where $z\sim\mathcal N(0,\sigma^2I_d)$ is drawn once before optimization. For strongly convex and smooth objectives with Lipschitz Hessian, we prove an explicit condition under which the map $z\mapsto w_N$ is a $C^1$-diffeomorphism on the bounded domains used in the
privacy argument, with a quantitative lower bound on the smallest singular value of its Jacobian. This permits a direct change-of-variables analysis of the finite iterate. For generalized linear models, the resulting
privacy-profile bound has no explicit ambient-dimension factor once the iteration condition holds, and its finite-iteration correction decreases geometrically. By letting the free truncation parameter grow slowly with $N$, we recover the corresponding exact-minimizer certificate in the limit. We also bound the expected excess empirical risk by $d\sigma^2/(2\mu)$ plus a geometrically decreasing optimization term, and transfer the result to population risk without an additional multiplicative condition-number factor in the leading statistical terms.
Read the full abstract ▾
Artificial Intelligence
Ego2World: Compiling Egocentric Cooking Videos into Executable Worlds for Belief-State Planning
Qinchuan Cheng, Zhantao Gong, Pengzhan Sun et al. (+2 more)
Egocentric videos capture how people carry out everyday activities, yet testing an
agent requires evaluating the consequences of actions it chooses itself. We introduce Ego2World, a
benchmark that turns annotated cooking activities into executable planning environments under partial observation. Its compiler links source steps and objects to symbolic action rules, persistent world states, and explicit task conditions, so researchers can execute an
agent's proposed actions and check their outcomes. World state and
agent belief are maintained separately, enabling controlled studies of planning and information reuse across continuing tasks. Evaluating six planners on 105 tasks shows that accepted operations often leave task goals unmet. Execution traces and condition checks distinguish interrupted runs, partial attainment, and completed execution without goal attainment. In a separate paired Qwen-Plus study, persistent belief improves action validity by 4.15 percentage points and reduces visual-query attempts by 90.27%, with higher
token use and no detected completion gain. Ego2World provides a reusable testbed for tracing how planning and
memory choices affect execution, observation demand, and task attainment, connecting recorded human activity to the development and evaluation of interactive
agents.
Read the full abstract ▾
All authors Qinchuan Cheng, Zhantao Gong, Pengzhan Sun, Angela Yao, Shijie Li
Computation and Language
WakeKV: Reactive, Reversible KV Residency for Heads That Change Their Minds
Utkarsh Ranjan
Most KV-cache compression methods classify
attention heads once, either offline or during prefill, and keep this classification fixed throughout generation. Across three models (1.5B-8B) and three regimes (needle
retrieval, long chain-of-thought, and multi-turn recall), we measure head behavior on four model-regime combinations and find that most heads change their reading behavior at least once during generation. We introduce WakeKV, a reactive residency policy that moves cooling heads to a recoverable CPU reservoir rather than freezing or permanently evicting their state. At matched
memory or budget, WakeKV consistently improves miss rate over frozen classification and destructive eviction, evaluated across five model-regime combinations and over three cited baselines (SnapKV, uniform R-KV, and ReasonAlloc) across four eligible combinations. A FlexiCache/vLLM implementation on Mistral-7B confirms the benefit on real hardware, improving throughput while retaining LongBench quality.
Read the full abstract ▾
Human-Computer Interaction
Characterizing the Performance Gap in Human Activity Recognition for Older Adults
Hossein Khayami, Sungjin Hwang, Eshed Ohn-Bar et al. (+4 more)
Human activity recognition (HAR) from wrist-worn accelerometers is increasingly used for health and behavioral tracking. Yet, most wearable HAR models are developed and evaluated on
datasets dominated by younger adults, leaving it unclear whether
benchmark progress generalizes across age groups. In this work, we leverage MyMove, our carefully annotated, free-living older-adult HAR
dataset (mean age 71), to evaluate deep-learning architectures and training regimes under both leave-one-subject-out and cross-
dataset transfer. We find that improvements on younger-adult
benchmarks fail to transfer equally to data collected from older adults, resulting in a persistent and often widening performance gap. However, richer representations, particularly frozen self-supervised features pretrained on the age-diverse UK Biobank
dataset, substantially improve performance on data from older adults and consistently narrow the performance gap, at modest cost to younger-adult performance, though disparities remain. These findings suggest that
benchmark gains and architectural scaling alone provide an incomplete picture of progress in wearable HAR, and broader advances may require representations that better capture population diversity, alongside personalized adaptation to individual movement patterns and routines.
Read the full abstract ▾
All authors Hossein Khayami, Sungjin Hwang, Eshed Ohn-Bar, David E. Conroy, Amanda Lazar, Eun Kyoung Choe, Hernisa Kacorri
Software Engineering
Self-Supervised Scaling of Terminal Environments for Scientific Domains
Zhongzhi Li, Yucheng Shi, Zongxia Li et al. (+8 more)
Terminal
agents are increasingly deployed beyond software engineering in science and other specialized domains. Constructing training environments requires executable reference behavior and a domain-specific verifier that distinguishes semantic correctness from superficially plausible artifacts. Authoring these components for each task requires repeated engineering and limits reuse. We introduce software-in-the-loop reconstruction, a self-supervised framework that obtains reference outputs and verification targets from existing software workflows, executable programs mapping structured inputs to outputs. For each workflow, we execute multiple input configurations and partition cases into public observations and hidden evaluations. Given the instruction, input schema, and public input–output observations, an
agent constructs an editable program without access to the source workflow. The candidate is evaluated on hidden configurations against workflow outputs. A hierarchical verifier combines domain-specific semantic comparison, structural validity, and anti-shortcut checks, while public feedback supports iterative revision. The construction admits additional workflows and configurations without authoring a reference solution for each task. We instantiate SWR with 500 workflows and 46 software families across six domains. Across three attempts per task, Qwen3.8-Max solves 838 tasks and produces 1,422 verified trajectories, which we oversample to 3,000 reconstruction-only training examples. Supervised fine-tuning of Qwen3.8-27B improves mean Terminal-Bench 2 performance from 47.94% to 53.56% across three seeds and achieves the highest mean among four matched-
token corpus controls on all four reported evaluations. These results indicate that existing scientific software can provide scalable, behaviorally verified supervision for terminal
agents.
Read the full abstract ▾
All authors Zhongzhi Li, Yucheng Shi, Zongxia Li, Junyao Yang, Ruhan Wang, Yu Wang, Jingyuan Huang, Jichao Yu, Ninghao Liu, Haitao Mi, Leowei Liang
Robotics
RoboChemGym: A Protocol-Driven Generative Simulation Framework for Long-Horizon Chemical Manipulation
Chenxi Li, Haiyuan Wan, Rui Li et al. (+10 more)
Wet-lab experimentation serves as the gold standard for hypothesis verification in scientific discovery; yet it is inherently labor-intensive, costly, and safety-critical.
Embodied agents hold the promise of automating these tedious workflows, but their development is hindered by the scarcity of real-world training data. While simulation offers a scalable alternative for producing demonstrations, current methods primarily target relatively short-horizon tasks with loosely structured interactions, failing to meet the strict procedural constraints and fine-grained manipulation demands of chemical experiments. To bridge this gap, we introduce RoboChemGym, a framework that autonomously generates high-fidelity manipulation demonstrations aligned with real-world experiment protocols, featuring a self-improving task synthesis mechanism to iteratively refine task execution and scene configurations, enabling the reliable generation of expert trajectories for complex, multi-object protocols exceeding 10 interaction steps. Furthermore, we introduce a hierarchical
benchmark that systematically assesses performance across varying granularities, spanning from atomic operations to full-cycle experimental workflows. RoboChemGym sets a scalable paradigm for the automated data synthesis and capability evaluation of
embodied agents in intricate chemical tasks, serving as a critical stepping stone toward fully intelligent laboratories.
Read the full abstract ▾
All authors Chenxi Li, Haiyuan Wan, Rui Li, Jingyuan Li, Sha Zhang, Bohan Feng, Jianbao Cao, Zhangrui Zhao, Di Hu, Wangmeng Zuo, Shixiang Tang, Minting Pan, Dongzhan Zhou
Discrete Mathematics · Cross-listed from math.CO
Typical growth of the Füredi-Hajnal and Stanley-Wilf limits
Jesse Geneson
We prove that the Füredi-Hajnal limit and the Stanley-Wilf limit of a uniformly random permutation
matrix of order $k$ are at most $\exp\bigl(O(\sqrt{k}(\log k)^{5/2})\bigr)$ with probability tending to one as $k\to\infty$. This improves the bound $\exp\bigl(O(k^{2/3}(\log k)^{7/3}/(\log\log k)^{1/3})\bigr)$ of Cibulka and Kynčl. Together with the lower bound due to Fox, these bounds show that the logarithms of both limits are $k^{1/2+o(1)}$ for almost all permutations.
Read the full abstract ▾
Robotics
AdaTempo: Learning Shared Relative Tempo from Demonstrations for Faster Robot Manipulation
Jiale Cao, Yike Niu, Zhengrong Xue et al. (+1 more)
Visuomotor policies trained via imitation learning often inherit the unnecessarily slow timing of teleoperated demonstrations. Yet uniform speedup is unreliable because different phases of a manipulation task tolerate acceleration differently. In this work, we introduce AdaTempo, a self-supervised method that accelerates visuomotor policies by exploiting shared relative-tempo structure in demonstrations. AdaTempo establishes phase correspondence, aggregates the aligned relative tempo into a consensus, and maps it to a continuous speedup profile used to resample demonstrations into accelerated training trajectories. Training standard policies such as ACT or
Diffusion Policy on these resampled trajectories directly embeds the desired tempo in the learned behavior, without runtime tempo selection or online retiming. Extensive evaluations show that AdaTempo achieves up to a $3.57\times$ speedup and yields a stronger success–speed trade-off than the original policies and representative acceleration baselines.
Read the full abstract ▾
All authors Jiale Cao, Yike Niu, Zhengrong Xue, Huazhe Xu
Machine Learning
MuonIO: Principled Norm-Aware Descent for Embedding Tables and Language Model Heads
Linkai Ma, Xinyu Luo, Mengbo Wang et al. (+3 more)
The
Muon optimizer derives its update rule for hidden linear layers by solving a local linearization of the loss penalized by the spectral norm, motivated by an RMS-stability argument for dense linear layers. Standard
Muon implementations, however, exclude the input (
embedding table) and output (
language model head) layers from this principled treatment, for which they use AdamW instead. We present MuonIO, a single
Muon-style update for both of these layers. For the
language model head $\mathbf{L} \in \mathbb{R}^{V \times d}$, we motivate the use of the $2\to\infty$ operator norm, due to the Lipschitz continuity of the softmax output geometry, while for the
embedding table $\mathbf{E} \in \mathbb{R}^{d \times V}$, we draw on the $1 \to 2$ operator norm, based on the one-hot input geometry identified by Bernstein & Newhouse (2025). The identity $\lVert\mathbf{L}\rVert_{2\to\infty}=\lVert\mathbf{L}^\top\rVert_{1\to2}$ then puts both
matrices in the same vocabulary-oriented geometry: MuonIO applies a single normalized-vector rule, which appears as column normalization for $\mathbf{E}$ and row normalization for $\mathbf{L}$. Empirical evaluations demonstrate the effectiveness of our approach, with MuonIO reducing I/O optimizer state
memory by 50% and I/O update FLOPs by $\sim$46% compared to
Muon for 1B LLaMA pretraining on C4, while also improving validation perplexity.
Read the full abstract ▾
All authors Linkai Ma, Xinyu Luo, Mengbo Wang, Ananth Grama, Petros Drineas, Brian Bullins
Artificial Intelligence
Label-Efficient Time Series Classification at Scale: A Dual-Stream OSSE-LSTM with Counterfactual Attribution
Nguyen Ho, Bach Tung Tran, Trung Ky Nguyen et al. (+3 more)
Time series are produced continuously at enormous scale by industrial equipment, wearables, power grids, and clinical monitors, yet annotation remains manual, expensive, and expert-dependent. The binding constraint in large-scale time series analytics is therefore not data volume but label volume, and the question facing a practitioner is concrete: how many examples per class must be labeled before a classifier becomes usable? We study this question directly, in a regime where the label space is fixed and known in advance and the decision rule must be constructed from only K labeled examples per class. We propose Dual-Stream OSSE-LSTM, an episodic metric-learning framework that pairs an Omni-Scale CNN with Squeeze-and-Excitation recalibration, for multi-scale motif extraction without per-
dataset kernel tuning, with a Bidirectional LSTM for global temporal context. The two streams are independently normalized and fused into a prototype-oriented
embedding. Because decisions taken from a few labels must also be explainable, we introduce Counterfactual Integrated Gradients (C-IG), which attributes the prototype margin between target and opposing classes rather than an isolated classifier logit, and reuses the resulting maps as soft masks for test-time prototype refinement without updating the encoder. On 19 univariate UCR
datasets, OSSE-LSTM attains the highest average accuracy and per-
dataset win count at every support size, and its accuracy remains within a 0.36-point band (96.36-96.72%) across that range. Its weakest configuration still exceeding the best result any compared baseline achieves at any K (93.99%).
Read the full abstract ▾
All authors Nguyen Ho, Bach Tung Tran, Trung Ky Nguyen, Zhenchang Xia, Bolong Zheng, Long Van Ho
Artificial Intelligence
Learning to Revise Reasoning with Segment-wise On-Policy Distillation
Yuxiang Zhang, Ding Cao, Shuting Cui et al. (+3 more)
On-policy
distillation (OPD) improves large
language model
reasoning by training students on their own rollouts with dense
token-wise supervision from the teacher. However,
token-wise OPD does not explicitly provide a coherent alternative
reasoning step showing how the student's step could be revised to improve subsequent
reasoning. Furthermore, this paradigm can become less effective when the student produces a degenerate
reasoning prefix, as subsequent teacher supervision remains conditioned on that prefix and may reinforce poor
reasoning patterns. In this work, we focus on learning
reasoning revision with segment-wise OPD to rework intermediate
reasoning steps and better support subsequent
reasoning. Through controlled
reasoning interventions, we find that replacing student segments with teacher redrafts improves subsequent
reasoning accuracy. Therefore, we address the problem of turning teacher redrafts into explicit supervision for learning to revise
reasoning. We propose Segment-wise On-Policy
Distillation (Seg-OPD), which selects student segments based on an uncertainty metric and obtains corresponding teacher redrafts. Seg-OPD trains the student to prefer teacher redrafts over their paired student segments while retaining dense
token-wise OPD supervision. Extensive experiments on mathematical
reasoning and competitive programming tasks show that Seg-OPD-trained students achieve higher revision success rates than baselines. Seg-OPD consistently outperforms the compared state-of-the-art baselines in
reasoning accuracy with an average relative improvement of 5.22% across diverse models and tasks. Code is available at https://anonymous.4open.science/r/Seg-OPD.
Read the full abstract ▾
All authors Yuxiang Zhang, Ding Cao, Shuting Cui, Lei Wang, Weijieying Ren, Tianxiang Zhao
Computation and Language
Silent Dissent: LLM Agents That Yield to the Majority Still Represent Their Original Premise
Ziang Ni and Peng Zou
Multi-
agent debate is increasingly used to reach consensus among LLM
agents, yet
agents often yield to a unanimous majority. When an
agent changes its answer, has it changed its mind or only its statement? We study this with two-hop factual questions whose intermediate entity (the bridge, e.g. the country in "the capital of the country where the Sagrada Familia is located") is never stated by anyone. Scripted peers, in the role of Asch's confederates, unanimously assert a wrong answer taken from another fact with a different bridge. At the moment the
agent answers, we read the bridge from its residual stream with the Jacobian lens (J-lens) and, for comparison, the logit lens. In pre-registered tests on held-out facts with four open-weight models,
agents of Qwen3.5-4B, Qwen3.6-27B and Gemma-4-E4B-it that gave in still represented their original bridge in the pre-registered layers below the output (hit@100 above a control entity: 0.85, 0.22 and 0.24), where the logit lens rarely ranked it among the top 100
tokens (0.00-0.06). These
agents also represented the bridge behind the peers' answer, beyond a mention baseline. A pre-registered addendum hid the
agent's earlier answer or removed it:
agents that gave in still represented their original bridge in all four models (0.43, 0.29, 0.37 and 0.25 with the answer hidden), including Llama-3.1-8B-Instruct, which barely did so with its answer in view (0.03). The premise can thus be computed from the question alone while the
agent states the majority's answer. Hiding the earlier answer also changed conformity: Qwen3.5-4B gave in on 89% of questions instead of 8%. In exploratory interventions, injecting the bridge's J-lens direction brought
agents back to their original answer only in the two Qwen models. Stated consensus in multi-
agent debate can thus overstate agreement. We also report the negative results of our pre-registered program.
Read the full abstract ▾
Machine Learning
Conditional Capacity and Routing in Mixture-of-Experts Particle Transformers
Kaushik Pendiyala, Haris Zia, Trevin Lee et al. (+8 more)
Mixture-of-Experts (MoE) models can increase parameter capacity without proportionally increasing active computation, but it is unclear how this trade-off behaves in particle-physics
transformers. We study dense and MoE Particle
Transformers on 188-class JetClass-II, varying expert count, routing capacity, top-K, and auxiliary loss. We find that, when
token dropping is avoided, top-1 MoE models improve over the dense baseline at nearly unchanged nominal forward compute, while further increasing the number of stored experts produces little additional accuracy gain. Activating multiple experts per
token yields additional predictive improvements at higher computational cost. Routing analyses show that expert assignments become more strongly associated with particle identity and kinematics in some configurations, but this structure does not increase monotonically with classification performance. These results highlight the need to distinguish stored parameter capacity, active computation, routing capacity, and routing organization when evaluating sparse expert models for jet classification. Code and experiment configurations are available at https://github.com/kpendiyala/MPT.
Read the full abstract ▾
All authors Kaushik Pendiyala, Haris Zia, Trevin Lee, Timothy Legge, Alejandro J. De Leon, Zihan Zhao, Aaron Wang, Abhijith Gandrakota, Jennifer Ngadiuba, Richard Cavanaugh, Javier Duarte
Machine Learning
Learning from Evolving Errors: Adaptive Iterative Repair for On-Policy Distillation
Rui Li, Liyang He, Zheng Zhang et al. (+3 more)
On-policy self-
distillation (OPSD) supplies dense
token-level feedback on trajectories sampled from the student's own policy, a richer training signal than the outcome-level rewards of reinforcement learning. This feedback comes from a teacher conditioned on a full reference solution unavailable to the student. The reference solution specifies the target but not how to move from the student's current error toward it, creating a solution-conditioned shortcut risk. We introduce AIR-OPD, an adaptive iterative repair framework for on-policy
distillation that provides error-to-repair supervision. Given a failed response, a guidance generator synthesizes repair guidance for the current error. The student samples an on-policy retry with this guidance. If the retry remains incorrect, the generator produces new repair guidance for the newly observed error. At each round, a fixed teacher receives the guidance as privileged context and supervises the student on an error-aligned region of its latest failed response. Outcome-aware stage weighting favors early repair stages and credits stages whose immediate retry passes verification. We train AIR-OPD on the DAPO-Math-17K
dataset and evaluate on AIME24, AIME25, and HMMT25, alongside out-of-distribution tests on MMLU-Pro and GPQA. We examine two guidance sources, self-guidance from the current student policy and external guidance from a larger model. For both Qwen3-4B and Qwen3-8B, AIR-OPD attains the best mathematical-
reasoning averages, improving over the strongest baseline by up to 3.6 points, while preserving base-model performance on the out-of-distribution
benchmarks.
Read the full abstract ▾
All authors Rui Li, Liyang He, Zheng Zhang, Zhenya Huang, Linbo Zhu, Qi Liu
Computers and Society
LearnAdapt Praxis: Controlled AI Assistance and Evidence Traces for Adult Workplace Learning
Nizam Kadir
AI can help adults produce plausible workplace artefacts while leaving their independent
reasoning difficult to inspect. LearnAdapt Praxis addresses this design problem through a five-stage learning workspace: Frame, Learn, Build, Validate and Transfer. The application stores an initial response, versioned specifications, coaching records, validation observations, a separate transfer response and facilitator feedback. Project-level server controls restrict coaching, access to earlier work and learner export during an active transfer attempt; they do not establish that a learner avoided assistance outside the application. This technical report describes the implemented architecture and evaluates selected workflow, authority, failure-recovery and provenance properties. A reproducible synthetic rehearsal exercised 120 serial project episodes across three fictional workplace contexts and four injected provider conditions. All 3,990 recorded checks met their specified expectations. The resulting records contained 240 specification versions, 1,200 activity events and 60 stored synthetic hints; 60 injected provider failures produced no fabricated hints. Separate authentication regressions exposed and resolved a session-expiry defect, and limited staging and production checks verified account access and live model connectivity. The evidence supports the tested engineering properties of the recorded release. It does not establish learning gains, model-output quality, unaided assessment validity, population usability or production capacity. The contribution is an implemented arrangement for separating assisted work, project-level assistance withdrawal and inspectable evidence, accompanied by executable tests and an explicit account of what remains to be validated with adult learners.
Read the full abstract ▾
Robotics
GeoScaffold: Learning Compact Geometric Latents via Reconstruction for Efficient Vision-Language Navigation
Yixuan Jiang, Wentong Li, An Liu et al. (+5 more)
Recent
vision-and-
language navigation (VLN) systems increasingly adopt streaming
Video-LLM policies that map
egocentric RGB observations and instructions directly to low-level actions. Yet these policies inherit weak 3D
geometric priors from 2D pretraining. Existing geometry-aware extensions charge a persistent inference-time price: depth sensors, 3D encoders, or per-step perception tool calls. We propose GeoScaffold, a
geometric supervision framework that pays this price once, at training time, by internalizing geometry into the policy itself. It first learns a compact depth tokenizer on depth maps from the training trajectories and freezes it. It then fine-tunes the policy with a handful of learnable geometry query
tokens, training their hidden states to reconstruct
navigation-critical geometry such as depth, connectivity, and traversability. This supervision turns the query states into compact
geometric latents for action decoding, and through the shared weights also internalizes geometry into the backbone's own representations. Like a scaffold, the tokenizer, target generators, and reconstruction heads are discarded after training, leaving the backbone and action interface unchanged. Extensive experiments show that GeoScaffold consistently outperforms leading
vision-only navigators on continuous VLN
benchmarks, offering a practical paradigm for lightweight edge deployment of spatially aware
embodied navigation models.
Read the full abstract ▾
All authors Yixuan Jiang, Wentong Li, An Liu, Zihao Xin, Fulin Tang, Cong Leng, Yang Gao, Jian Cheng
Machine Learning
Test-time Calibration Learning for Large Language Model Reasoning
Zizhuo Zhang, Xiong Peng, Jingwei Sun et al. (+4 more)
Reliable large
language models (LLMs) must not only produce accurate answers but also express confidence that faithfully reflects their probability of being correct. Such calibration is essential for identifying uncertain predictions and supporting reliable decision-making in real-world deployment. Recent studies incorporate calibration learning into reinforcement learning (RL), jointly optimizing answer correctness and verbalized confidence using ground-truth correctness supervision. However, their reliance on labeled data limits their applicability in practical test-time settings, where ground-truth labels are unavailable and calibration may need to adapt to newly encountered target tasks. To address this challenge, we propose Test-Time Calibration Learning (TTCL), a label-free framework that jointly adapts
reasoning accuracy and verbalized confidence directly on unlabeled target-task data. Specifically, TTCL derives self-supervision signals for both correctness and calibration from multiple model-generated responses, enabling calibration learning at test time without ground-truth labels. Theoretical analysis further establishes TTCL as a bounded surrogate for the ideal calibration objective. Extensive experiments on mathematical
reasoning and factual question answering demonstrate that TTCL consistently improves both accuracy and calibration across diverse models and tasks. On base models, TTCL achieves an average relative accuracy improvement of +40.13% and an ECE reduction of +70.80% across eight
benchmarks. Moreover, TTCL can further improve both accuracy and calibration for already calibrated models under domain shift, particularly when source-domain calibration transfers poorly to target tasks. In the math-to-factQA setting, TTCL achieves an average relative accuracy gain of +20.35% and reduces ECE by +53.83%. The source code is released at https://github.com/tmlr-group/TTCL.
Read the full abstract ▾
All authors Zizhuo Zhang, Xiong Peng, Jingwei Sun, Rong Yao, Shixiong Kai, Mingxuan Yuan, Bo Han
Robotics
Who Went Where When on the Lunar Surface: Forensic Trajectory Analysis to Identify Byzantine Rovers
Lachlan Holden, Feras Dayoub, Melissa de Zwart et al. (+2 more)
Future planetary surface missions are likely to involve multiple independently operated rovers sharing the same deployment region, raising the need to verify compliance with operational constraints such as Lunar Safety Zones. Because continuous in-situ observability is rarely available, such verification requires post-hoc reconstruction of rover trajectories from sparse telemetry, including odometry, pose priors, and relative inter-rover detections. We introduce the problem of forensic trajectory analysis for non-cooperative planetary rovers in the presence of Byzantine
agents: rovers that provide miscalibrated or deliberately falsified measurements to support an incorrect trajectory. We show that standard outlier-robust pose graph optimisation methods are vulnerable in this setting, because Byzantine rovers can generate measurements that are internally consistent and numerous enough to make truthful incriminating measurements appear as outliers. To address this, we propose an attribution-aware trajectory estimation method that reasons over rover credibility rather than individual measurement validity. The method evaluates candidate credible rover subsets by comparing the statistical consistency of their internal and boundary relative detections against provided priors, and then estimates trajectories using only measurements attributed to credible
agents. Across synthetic simulations and real planetary-analogue trajectory data, the proposed method identifies Byzantine rovers and produces significantly more accurate trajectory estimates than existing robust pose graph optimisation baselines.
Read the full abstract ▾
All authors Lachlan Holden, Feras Dayoub, Melissa de Zwart, David Harvey, Tat-Jun Chin
Robotics
DeltaWorld: Physically Consistent Interactive World Simulators via Action-Conditioned Latent Increment Learning
Boyuan Hou, Xiaoge Cao, Chaofan Zhang et al. (+2 more)
Interactive world simulators can provide scalable environments for
robot planning, policy training, and evaluation by predicting action consequences while reducing reliance on repeated physical rollouts. To serve these applications, they must generate future image sequences that respond faithfully to
robot actions and preserve the dynamics of
robot-object interactions over long horizons. However, existing world models typically predict the entire next latent state and often fail to capture subtle changes induced by
robot actions. Such omissions can produce physically implausible outcomes, including object interpenetration and excessive deformation. To address this limitation, we propose DeltaWorld, a physically consistent interactive world simulator for robotic manipulation. Our method introduces the Delta Latent Transition Model (Delta-LTM), which predicts action-induced latent feature changes and adds them to the current latent state to obtain the next state, rather than predicting the next latent state directly. To mitigate object interpenetration and excessive deformation in predicted future frames, Interaction-aware Latent
Alignment is introduced to construct counterfactual interaction regions and supervise interaction-related latent changes. DeltaWorld is evaluated on the IWS manipulation
benchmark and a self-collected cross-
robot dataset covering multiple
robot embodiments and manipulation tasks. On the cross-
robot dataset, DeltaWorld reduces FVD by 46.6% and LPIPS by 31.1% relative to the IWS baseline. These results highlight the potential of DeltaWorld for long-horizon action-conditioned
video prediction in robotic manipulation.
Read the full abstract ▾
All authors Boyuan Hou, Xiaoge Cao, Chaofan Zhang, Shuo Wang, Shaowei Cui
Computers and Society
Lessons from Trauma-Informed Training on Technology-Facilitated Abuse for Gender-Based Violence Advocates
Naman Gupta, Connie W. Chau, Sophie Stephenson et al. (+2 more)
Technology-facilitated abuse (TFA) is an emerging gendered public health crisis affecting millions of people across the globe. TFA coincides with other forms of gender-based violence (GBV), such as emotional, psychological, and physical abuse by an intimate partner. Survivors often seek support from GBV advocates who specialize in helping survivors navigate abusive situations and potential pathways for healing and remediation. With the rise in TFA, however, survivors and GBV advocates experience barriers and gaps in knowledge in identifying and mitigating this newer, ever-evolving form of abuse. To address this, we developed trauma-informed training as a critical capacity-building intervention to improve GBV advocates' knowledge and skills for responding to survivors and to encourage multi-stakeholder collaboration toward a structural response. We facilitated 8 training workshops at local, state, and national US-based GBV organizations. Our study demonstrates that the trainings increased advocates' perceived understanding of TFA abuse vectors and their impacts on survivors, along with advocates' confidence in providing support, safety planning, and referrals through collaboration with community stakeholders. We then conducted retrospective reflections through autoethnography to surface key lessons, contestations, and tensions that emerged from our experiences in designing and coordinating trainings with host GBV organizations. Our analysis of autoethnographic notes revealed three key design decisions: coordinating logistics flexibly, reducing reflexive distance from host organizations and attendees, and using our field experience to tailor content for accessibility. We contribute a concrete checklist to guide future HCI scholars in conducting training interventions for stakeholders in high-stakes contexts.
Read the full abstract ▾
All authors Naman Gupta, Connie W. Chau, Sophie Stephenson, Kate Walsh, Rahul Chatterjee
Artificial Intelligence
Decoupling Memory from Context: Structured Memory for Token-Efficient Test-Time Continual Learning
Yehya Farhat, Michael Desmond and Anastasios Kyrillidis
Large
language models (LLMs) are increasingly deployed in enterprise, scientific, and medical applications, where
agents must incorporate domain-specific knowledge and adapt from experience. Context engineering offers a practical alternative to weight updates by improving model behavior through instructions, strategies, and evidence supplied at inference time. However, adapting context online typically requires a costly trial-and-error process, while queries are often processed independently, preventing useful experience from carrying forward.
Memory systems address this limitation by retaining information across interactions, but approaches that continually append information to a shared context face increasing
token costs, context-window limits, and performance degradation as the context expands. We introduce a unified formulation of context optimization and show that an
agent memory system update can be interpreted as an optimization update procedure over the model's context. This perspective attempts to provide a principled framework for studying
memory design and its efficiency. We then propose GraphMemory, a lightweight graph-based
memory that accumulates, refines, organizes, and connects reusable strategies. For each query, GraphMemory retrieves only the relevant subgraph, enabling online context adaptation without exposing the model to the entire
memory. Under bounded
retrieval, the amount of retrieved
memory remains constant as the number of processed examples grows. Experiments show that GraphMemory achieves competitive downstream performance while using approximately 81-85% fewer
memory-construction
tokens than our baselines.
Read the full abstract ▾
Artificial Intelligence
Large language models exhibit unreliable updating of clinical judgment as patient evidence evolves
Min Zeng and Rui Zhang
Large
language models (LLMs) are increasingly explored for clinical
reasoning, but whether they appropriately revise judgments as patient evidence evolves remains unclear. We evaluated longitudinal belief updating using matched intensive-care trajectories from electronic health records. Across diverse LLMs, conditioning on a preceding judgment more often increased than reduced prediction error when estimates changed, replicated for a second endpoint. Controlled interventions revealed two failure modes. First, with preceding assessment fixed, models responded more strongly to worsening than matched improving respiratory evidence; this asymmetry persisted after headroom normalization at moderate and strong evidence levels. Second, with current evidence fixed, increasing prior risk from 10% to 90% shifted estimates by 26.2 percentage points, demonstrating causal influence of prior model beliefs. Prompting did not restore reliable updating. Evidence-Validated Longitudinal Update (EVLU) identified fewer, more reliable revisions, revealing a reliability-coverage trade-off. These findings establish longitudinal belief updating as a distinct dimension of LLM reliability.
Read the full abstract ▾
Machine Learning
RAOA: Alternating-Operator Neural Computation with Programmable Radio Propagation
Toshiaki Koike-Akino
Can programmable
radio propagation serve as computational depth rather than only as a communication channel or one-shot analog transform? We introduce the
Radio Alternating Operator Ansatz (RAOA), a recurrent computing architecture that alternates an energy-derived problem update with a mixing update over a persistent latent state. Recomputing the problem field after each mix makes repeated passes compositional even when the same learned controls are reused across depth. We evaluate this idea through exact discrete optimization, constrained programmable-propagation simulation, and pretrained-model adaptation. On discrete objectives, repeated execution can improve solution quality without increasing the learned-control count, and the same formulation handles higher-order interactions directly. A passive phase-only free-space model further shows that the required operators can be approximated by programmable propagation while retaining useful downstream behavior despite realization error. When inserted as a zero-initialized residual adapter, RAOA adapts pretrained
language models with WikiText performance close to a matched shallow MLP across three model families, while
reasoning-task transfer remains model-dependent. Together, these results connect alternating-operator computation, programmable
radio propagation, and neural adaptation within one recurrent framework. The RF realization evidence is simulation-based rather than a hardware demonstration.
Read the full abstract ▾
Systems and Control · Cross-listed from math.OC
Advances in Continuous-Time Multiparametric Optimal Control: The Role of Time-Varying Active Constraints
Lida Lamakani and Efstratios N. Pistikopoulos
Multiparametric optimal control in continuous time partitions the space of initial states into critical regions, each with its own control law involving a set of time-varying active constraints. The boundaries between two neighbouring regions are either hyperplanes, which are given in closed form by one linear equation, or curved boundaries, which must be computed. The sequence of time-varying active constraints plays a key role in defining the linear or nonlinear shape of a critical-region boundary. In this paper we show how to determine that shape prior to any computation. In particular, we show that the boundary is a hyperplane under two conditions. First, the new constraint becomes active at the same instant at every point of the boundary. Second, the durations for which the other constraints stay active are the same at every point of the boundary. Otherwise, the boundary is curved. Both conditions can be read from the sequences of active constraints of the two neighbouring regions, which gives five rules, each yielding a hyperplane or a curved boundary. We illustrate the rules on the Newell-Lee evaporator, where they classify the eight boundaries of a seven-region partition into four hyperplanes, given in closed form, and four curved boundaries, computed exactly.
Read the full abstract ▾
Artificial Intelligence
DataWeave: Deploying Human-LLM Analytics for Exploratory Structured Data Analysis
Raquib Bin Yousuf, Harith Laxman, Vitaliy Shkremetko et al. (+10 more)
Data journalism, the practice of using data analysis to surface newsworthy stories, depends increasingly on the ability of reporters and investigative journalists to uncover trends, disparities, and accountability narratives. In practice, exploring large structured
datasets remains slow and brittle: journalists must navigate hundreds of variables across many
datasets over years, understand data coding conventions, and write non-trivial analysis code while hypotheses evolve. Although LLMs are often touted as "ask in English, get SQL/answers," real newsroom workflows expose recurring failures, e.g., schema mismatches and drift, misread domain semantics and units, and silent assumptions. We present DataWeave, a system that addresses these needs by combining conversational interaction, schema grounding, analytical planning, and executable query generation to support exploratory analysis over structured data. Rather than treating LLMs as autonomous answer engines, DataWeave frames them as interactive partners whose outputs can be inspected, corrected, and steered as hypotheses shift. We present a case study with professional journalists using our system to analyze the U.S. Department of Education's Integrated Postsecondary Education Data System (IPEDS), a high-stakes public
dataset with substantial domain semantics and frequent schema updates. We also report how deployment experience and iterative refinement shaped the current DataWeave architecture and its analytical workflow. Our findings distill design principles and deployment lessons for trustworthy human-LLM collaboration in structured data analysis.
Read the full abstract ▾
All authors Raquib Bin Yousuf, Harith Laxman, Vitaliy Shkremetko, Eunice Son, Shambhavi Verma, Brian O'Leary, Venketesh Subramony, Sylvain Nazef, Jacquelyn Elias, Ron Coddington, Chris Contakes, Michael Riley, Naren Ramakrishnan
Artificial Intelligence
Spend Teacher Tokens Where They Matter: Success-Referenced On-Policy Distillation
Xiang Chen, Futao Su, Kong Wang et al. (+2 more)
On-policy
distillation (OPD) combines student-generated rollouts with dense
token-level supervision from a teacher, but providing such supervision for every rollout requires substantial teacher computation. We introduce Success-Referenced On-Policy
Distillation (SR-OPD), which reduces this cost by selecting which
prompts and rollouts receive teacher supervision. When the student produces both successful and failed rollouts for the same
prompt, a successful rollout can serve as a natural reference for selecting failed rollouts. SR-OPD therefore focuses on such
prompts and prioritizes failed rollouts whose hidden-state trajectories show sustained divergence from a successful reference, while accounting for estimated teacher-input cost. Across three teacher-student pairs and six mathematical
reasoning benchmarks, SR-OPD uses only 3.46-5.02% of the teacher-input
tokens required by Vanilla OPD in the one-pass setting while maintaining comparable
reasoning performance. Under a controlled setting matched to 5% of Vanilla OPD's teacher-input budget, further experiments support both key design choices: focusing supervision on
prompts with both successful and failed rollouts, and using successful rollouts to guide failure selection. These results indicate that a student's own successful behavior can serve as a useful reference for allocating teacher supervision under a fixed teacher-input budget.
Read the full abstract ▾
All authors Xiang Chen, Futao Su, Kong Wang, Jiayi Chen, TanLin Li
Operating Systems
FDP: The Data Placement Promise of Modern NVMe SSDs
Sijie Lan, Hui Qi, Xing He et al. (+3 more)
NVMe SSDs are now widely deployed as the storage tier in data centers. As SSDs have evolved over the past decade, the commu- nity has continued to debate the interfaces they expose and how operating systems and storage systems should exploit them. The NVMe Flexible Data Placement (FDP) proposal is the latest point in this design space. FDP introduces an interface based on Reclaim Units that enables explicit data placement to reduce device write amplification without the software engineering costs of sequential- write constraints and host garbage collection. FDP-enabled SSDs are emerging in commercial products and early data center de- ployments. Their compatibility with conventional block I/O allows existing applications to run unchanged, allowing a frictionless adop- tion in industry. This paper presents an experimental evaluation of FDP SSDs to characterize their data placement guarantees over the raw device interface. We then revisit two widely deployed and distinct open- source storage systems, MySQL and RocksDB, and examine whether lifetime-based data separation and distinct write patterns built into their architectures can be mapped onto FDP SSDs without inva- sive changes. Our evaluation shows end-to-end WAF reductions at higher device utilization, along with QoS and throughput improve- ments under synthetic and real-world workloads. These results demonstrate that FDP provides a practical and deployable cross- layer mechanism for data placement with open-source ecosystem support on Linux. They also highlight why FDP SSDs are gaining traction in industry.
Read the full abstract ▾
All authors Sijie Lan, Hui Qi, Xing He, Mahmut Kandemir, Javier González, Vivek Shah
Computer Vision · Cross-listed from eess.IV
One Photon, Many Worlds: Posteriors and Predictions with Single-Photon Cameras
Haejoon Lee, Mohit Gupta, Vijayakumar Bhagavatula et al. (+1 more)
Single-
photon avalanche diode (SPAD) cameras operate fundamentally differently from conventional cameras due to their
photon-counting nature. Each frame produces a binary image: pixels report zero if no
photons arrived during exposure, and one if one or more
photons arrived. Reconstructing a scene or inferring its properties from a single binary frame is difficult because many different images could produce the same measurement; thus, the inverse problem is fundamentally one-to-many. As we gather more binary measurements, the inherent uncertainty associated with the inverse problem and any associated inference diminishes. With sufficient
photon counts,
photon noise becomes negligible relative to the signal mean, enabling near-deterministic scene recovery and inference. This work characterizes the transition from
stochastic to near-deterministic scene understanding as
photon budget increases, analyzing how the stochasticity in
photon arrival affects downstream inference tasks. Technically, we develop a conditional generative framework based on a Hypergeometric frame-thinning process for accumulated binary SPAD measurements. Generative models capture the one-to-many nature of
photon-starved inverse problems, enabling empirical characterization of how this ambiguity diminishes with increasing measurements and its impact on downstream tasks like character recognition, QR code decoding, and facial analysis.
Read the full abstract ▾
All authors Haejoon Lee, Mohit Gupta, Vijayakumar Bhagavatula, Aswin C. Sankaranarayanan
Systems and Control
Generation and Transmission Expansion Planning with BESS-Based Virtual Transmission Lines
Qiushi Wang and Xingpeng Li
This paper proposes a mathematical model for long-term Generation and Transmission Expansion Planning (GTEP) that integrates a relaxed Virtual Transmission Line (VTL) as a Storage in Place of Transmission Asset (SIPTA) strategy to address challenges posed by transmission capacity shortages and system congestion in deregulated power
markets, particularly under the rapid growth of renewable energy resources and integrated data centers. The proposed VTL formulation coordinates the operation of the two battery energy storage systems (BESSs) forming a VTL pair by preventing them from charging or discharging simultaneously, thereby providing additional congestion relief without introducing an explicit congestion cost into the objective function. Base case studies on a revised IEEE 24-bus system demonstrate that VTL reduces system congestion compared with the standalone BESS case, achieving a 12.3% reduction in weighted total congestion and up to approximately 67% reduction in congestion on individual transmission branches, with only a 0.3% increase in total planning cost. Furthermore, improvements across multiple congestion metrics indicate that the benefits of VTL extend beyond reducing congested line-hours to reducing congestion rent and N-1 transmission violations in the base case. These results demonstrate the potential of VTL to provide congestion mitigation that complements standalone BESS applications.
Read the full abstract ▾
Human-Computer Interaction
Asterism: Exploring and Synthesizing Scattered Observations into Literature-Grounded Hypotheses and Theories
Joseph Chee Chang, Michael D'Arcy, Amy X. Zhang et al. (+15 more)
A theory draws many independent observations into one framework with novel hypotheses. A researcher building such a theory must synthesize observations scattered across many papers, each describing related concepts but often in different terms. Which concepts matter most also depends on their preferences and research questions. Recent approaches scale theory synthesis with LLMs, but automate away choices and intuitions from researchers. We present Asterism, which extracts observations from hundreds of papers as concept-relation triples, with concepts unified in a hierarchical ontology. Researchers curate an evidence graph using the ontology and aggregate observations at different levels of granularity to focus theory formation on specific phenomena of interest. In a field deployment (n=10), researchers worked from observations to theories, and kept concepts and hypotheses fitting their preferences. In two case studies, teams of immunology and agriculture researchers discovered mechanisms outside their standard analyses and constructed hypotheses worth follow-up experiments.
Read the full abstract ▾
All authors Joseph Chee Chang, Michael D'Arcy, Amy X. Zhang, Pao Siangliulue, Sangho Suh, Aakanksha Naik, Jena D. Hwang, Javier Ramos Benitez, Stella Wroblewski, Matt Latzke, Michael Cuoco, Ruben Lozano-Aguilera, Kris Ganjam, Joel Chan, Doug Downey, Peter Jansen, Kyle J. Travaglini, Daniel S. Weld