Artificial Intelligence
EPOCH: Coverage-Aware Evolution with Experiential Preference Optimization for LLM-based Automated Heuristic Design
Oguzhan Gungordu, Ayse Tursucular, Siheng Xiong et al. (+1 more)
LLM-based automated heuristic design (AHD) discovers heuristics for combinatorial optimization problems (COPs), where an LLM generates candidates in an evolutionary search. Existing frameworks freeze the generator or fine-tune it on a scalar fitness signal hiding which instances each heuristic covers. Reflection-based frameworks improve heuristics with natural-
language feedback, but it stays in the
prompt and never reaches the generator's weights. We propose EPOCH, which makes instance coverage the objective of the evolutionary search and fine-tunes the generator to internalize reflection. Parent selection, operator allocation, and stagnation recovery all optimize how well the heuristics jointly cover the training instances, so the search returns a complementary heuristic ensemble. The generator learns from its own search by experiential preference optimization. A teacher LLM returns a natural-
language insight on the generated heuristics, and the generator produces new heuristics with this insight. These improvements join the preference pairs for direct preference optimization (DPO). Since DPO only teaches the generator to rank these improvements, a reflective self-
distillation (RSD) term makes it more likely to generate them on its own, and the gains accumulate over the long horizon of the search. Across COPs and open-source LLM backbones, EPOCH's heuristic ensembles outperform inference-only and fine-tuned baselines and generalize across problem scales.
Read the full abstract ▾
All authors Oguzhan Gungordu, Ayse Tursucular, Siheng Xiong, Faramarz Fekri
Artificial Intelligence
Get In, Decide, Prove: A Merchant-Side Readiness Benchmark for Agentic Commerce
Adrian de Valois-Franklin, Alex Bogdan, Anas Ibrahim et al. (+2 more)
AI
agents now browse and buy on people's behalf, and
benchmarks measure how well the
agents perform. Far less is known about the other side of the transaction: whether a merchant's website lets an
agent in, publishes terms precise enough to decide a purchase, and leaves evidence of what was agreed. This paper presents a merchant-side
benchmark built on those three questions and reports a pilot of it. The central measurement, decision sufficiency, rates each criterion of a concrete buyer mandate (total cost, cancellation or return terms, service date, variant identity) as determinate, indeterminate, or unknown from the merchant's own published evidence. Readiness scores carry their evidence coverage and missingness bounds; access is reported separately for a declared bot, a declared headless browser, and a user-present browser; and each observed term is mapped to the RAILS admissibility class of the evidence that could support it in a dispute. Four large merchants received the full assessment: three refused the declared profiles at their offer pages, and no mandate could be confirmed as met, because each merchant left a total or a refund term undetermined. An access census of 555 sites of merchants that two payment processors publicly name as clients found the home page unreadable to both declared profiles at 105 sites (18.9%). A declared assessment of 330 merchants, scored by deterministic rules without a rater, found that evidence coverage rather than the score decides who can be ranked: 115 merchants (35%) reached the ranking threshold, rankable profiles scored a median of 89 to 90, and material terms was the one pillar well below the others, because the all-in total was decidable at 18 merchants. The pilot shows that the measurements can be taken; it does not validate them or rank merchants, and the weights and the projected clearing band await validation against outcomes.
Read the full abstract ▾
All authors Adrian de Valois-Franklin, Alex Bogdan, Anas Ibrahim, Ibrahim Shaer, Tamaz Andguladze
Artificial Intelligence
What Makes a Latent Space Shared? Direct and Recoverable Compatibility in Motion VAEs
Iago Brito, Walcy Rios, Lucas Fernandes et al. (+2 more)
A shared latent space is often assumed to make representations from different schemas directly interchangeable, yet sharing parameters, dimensionality, or a prior does not determine how corresponding instances are expressed in latent coordinates. We show that this assumption conflates recoverable correspondence, direct compatibility, and decoder reuse. In a controlled multi-schema motion VAE on HumanML3D, even identical inputs yield only $5.9$–$17.7\%$ raw Recall@1 and $0.221$–$0.484$ paired-
token cosine, despite correspondence being almost perfectly recoverable after linear calibration. Cycle consistency strengthens recoverability but still leaves direct
retrieval and
token agreement near zero. In contrast, only $64$ paired clips raise raw Recall@1 to $88.4$–$90.3\%$ and
token cosine to approximately $0.82$, making most post-hoc
alignment unnecessary, although crossed decoding remains substantially worse than native reconstruction. We further find that reducing measured marginal discrepancy does not imply schema invariance. These results show that a shared backbone or prior does not ensure directly compatible latent coordinates, while limited paired correspondence can substantially improve direct compatibility in the tested setting.
Read the full abstract ▾
All authors Iago Brito, Walcy Rios, Lucas Fernandes, Kaiki de Oliveira, Arlindo Galvão Filho
Computation and Language
PIG: Parallel Inconsistency Guidance for Accelerating Diffusion Language Models
Quentin Fruytier, Anton Xue, Sanjay Shakkottai et al. (+1 more)
Diffusion language models accelerate generation by decoding multiple masked positions per forward pass. However, accuracy is known to drop when parallel decoding trajectories deviate from their sequential counterparts, which are slow and expensive "oracles" that adhere to the joint distribution of
language. In this paper, we propose Parallel Inconsistency Guidance (PIG), a new paradigm that uses a trained auxiliary model to directly estimate the inconsistency between parallel and sequential generation from a single model forward pass. During inference, masked positions are traversed by decreasing confidence, and
tokens are added to the parallel decode set one-at-a-time until the total estimated inconsistency between the parallel and sequential generation exceeds a threshold. Surprisingly, it suffices to train a lightweight ~2M parameter auxiliary model on a small mixture drawn from OpenCoder, GSM8K-train, MATH-train, and MBPP-train. For LLaDA-8B Instruct and NemotronDiffusion-3B Instruct, PIG extends the accuracy-TPF frontier on GSM8K, MATH500, MBPP, HumanEval, and MMLU, when compared to the industry standard Fast-dLLM and measures favorably on LLaDA-8B Instruct against DAPD, KLASS, EB-sampler, and other learned unmasking policies.
Read the full abstract ▾
All authors Quentin Fruytier, Anton Xue, Sanjay Shakkottai, Sujay Sanghavi
Software Engineering
VulnBump: A Benchmark for Fixing Vulnerable Dependencies in Real Projects While Keeping the Build and Tests Green
Gabija Pasiunaite, Ryan McMorrow, Brian Clark et al. (+2 more)
Software composition analysis (SCA) tools report far more vulnerable dependencies than teams fix: in Snyk Open Source production data, 94% of vulnerability findings have a known fixed version, yet only about 10% are resolved. Agentic coding tools could close this gap, but no
benchmark evaluates them on vulnerability-driven upgrades in real, runnable projects across ecosystems, verified independently of the
agent. We present VulnBump: 307 upgrade tasks covering 2,066 fixable vulnerabilities in 43 repositories across six package managers, matched to Snyk Open Source production vulnerability distributions. An upgrade passes only if, in a fresh container, dependencies resolve, a rescan shows the targeted vulnerabilities fixed, the project builds, and every previously passing test still passes. A non-agentic baseline that only applies Snyk's recommended version passes 46.9% of upgrades; with the same model (Claude Sonnet 5.5), Snyk's Evo Remediation
Agent passes 90.2%, Claude Code + Snyk scan 77.5% and Claude Code unaided 59.6%. The
agents fail in opposite ways: Claude Code mostly leaves the vulnerability in place, whereas most of Evo Remediation
Agent's failures break the build or tests. An SCA scanner is a key tool for
agents: Snyk's guidance raises Claude Code's PASS rate by 17.9 percentage points; without it, Claude Code often settles on a still-vulnerable version. Yet knowing the target is not enough: given the same Snyk findings, Evo Remediation
Agent's purpose-built harness passes 12.7 points more than Claude Code + Snyk scan. Major framework migrations remain hard for all harnesses. Because the
agents keep projects working at similar rates, evaluating remediation quality in dependency upgrades requires verifying the fix, the build and the tests together.
Read the full abstract ▾
All authors Gabija Pasiunaite, Ryan McMorrow, Brian Clark, Liran Tal, Luke Tu
Networking
Computing All-Pairs Shortest Communication Time Paths for Periodically Varying Satellite Networks
Koushik Sinha, Dibakar Saha, Sai Puppala et al. (+1 more)
We address the problem of designing an efficient
algorithm for computing the all-pairs shortest-time paths in time-varying networks, specifically targeting the dynamic topological characteristics of low earth orbit (LEO) satellite constellations. We model such temporal graphs as $G = (V, E_t)$, where $V=\{1, 2,\ldots , n\}$ is the set of $n$ vertices in the graph, and $E_t$ is the set of $M$ time-varying edges considered over a total time window of size $T = M\tau$, $\tau$ being the duration of each interval in that time window. For such a network, our
algorithm finds the all-pair shortest paths in $O(M^2n^3)$-time. A key advantage of our approach is its computational structure, which mirrors two
matrix multiplication steps, first in the forward direction and then in the backward direction. This structure of the
algorithm makes it exceptionally suitable for parallelization on SIMD architectures like GPUs, thereby offering a significant speedup over traditional shortest-path
algorithms and enabling efficient, network-wide message routing in rapidly changing LEO satellite constellations.
Read the full abstract ▾
All authors Koushik Sinha, Dibakar Saha, Sai Puppala, Bhabani P. Sinha
Machine Learning
HarnessTTT: Learn to Optimize Harness at Test-Time for Scientific Discovery
Yingzi Ma, Yulong Cao, Nanxi Li et al. (+5 more)
Scientific discovery with
language models requires finding the best valid solution within a finite computational budget. We study how feedback from this search can improve the procedure used to conduct it. We introduce HarnessTTT, a test-time learning framework that trains a harness proposer while keeping the executor frozen. The proposer generates executable harnesses comprising system
prompts, reusable skills, tools, middleware, and execution controls. Each harness guides a budgeted discovery rollout, whose outcome provides feedback for updating the proposer. A discovery-oriented policy-gradient objective combines gap-normalized rewards, leave-one-out advantages (RLOO), and max-sharpening to favor high-performing proposals. Generated components are validated before execution, and the search retains the best valid solution and selected harnesses across rounds. Across fourteen discovery tasks in mathematics, systems, GPU kernels, heuristic programming, astrodynamics, and biology, HarnessTTT with a frozen 9B executor improves on OpenEvolve with the same executor on all eleven
benchmark tasks (e.g., from 1.17 to 2.64 on circle packing), improves on the discovery-fine-tuned Finch-9B by up to 92%, holds the best open-weight sub-10B result on nine, and reaches 0.380919 on Erdős minimum overlap, better than the best human reference of 0.380927. Scaling the proposer and frozen executor to 27B improves on eleven of fourteen tasks, and transferring the learned harnesses to GPT-5.5 matches or exceeds the strongest reported system of any backbone on nine of fourteen tasks. Together, these results show that harness search can itself be learned at test time: a trained proposer lets a small frozen executor search effectively, and the harnesses it finds carry over to stronger executors.
Read the full abstract ▾
All authors Yingzi Ma, Yulong Cao, Nanxi Li, Fang Wu, Yizhe Zhang, James Zou, Yejin Choi, Chaowei Xiao
Information Retrieval
HASTE: Hierarchical and Attribute-aware Supervision for Generative Recommendation
Tripti Shukla, Shwetha Somasundaram, Akshat Gupta et al. (+3 more)
Generative recommendation models have shown promising results by representing items as semantic IDs and generating these IDs autoregressively. We introduce an approach showing that explicitly incorporating hierarchical and attribute-level supervision into generative recommendation can simultaneously improve training efficiency and long-tail recommendation performance. Existing approaches typically optimize semantic ID prediction with a standard causal cross-
entropy objective, which does not explicitly exploit the hierarchical structure of semantic IDs and can require substantial training to learn effective item representations. Moreover, data-sparse tail items often suffer from poor representations due to limited supervision, resulting in weaker long-tail recommendation performance. We address these challenges with HASTE (Hierarchical and Attribute-aware Supervision for generaTive rEcommendation), a unified training framework that introduces hierarchical and attribute-specific supervision. HASTE's Hierarchical Loss explicitly exploits the multi-level structure of semantic IDs, providing supervision at each level of the item hierarchy and substantially accelerating training convergence. Its Attribute-Specific Losses encourage the model to preserve fine-grained item attributes, leveraging the
language model's inherent semantic knowledge to improve representations and recommendations for tail items. We extensively evaluate HASTE on a fashion recommendation
benchmark and across multiple domains of the Amazon
dataset. HASTE improves recommendation performance across
datasets and item-frequency regimes. Notably, the Hierarchical Loss achieves approximately 2x faster convergence than the standard causal cross-
entropy objective, substantially improving training efficiency while maintaining strong recommendation quality.
Read the full abstract ▾
All authors Tripti Shukla, Shwetha Somasundaram, Akshat Gupta, Rohit Garg, Paul Duff, Ian Anderson
Artificial Intelligence
When Goals Leak Across Relationships: How Cached Goal Representations Shape Cross-Client Decisions
Saloni Gupta, Sébastien Krier and Glenn Matlin
As LLM
agents take on more autonomous roles, they may interact with multiple clients and counterparties whose goals and incentives conflict. If an
agent maintains shared inference state across these interactions, information associated with one relationship may influence decisions made for another. We test OLMo-3-7B-Instruct in a controlled two-client environment with 20
market scenarios, where each client is assigned an opposing objective. With shared conversational
memory, the model deviates from the current client's objective in 22% of eligible decisions. We then investigate how these goals are represented in the KV cache. Linear probes show that client-goal ownership becomes highly recoverable in middle layers and is concentrated in particular
attention heads. We use these results to identify where to intervene in the cache and test whether these representations affect the model's decisions. Ablating the competitor's cached goal representations at these locations shifts the model toward the current client. The effect is larger for heads identified by probing than for randomly selected heads, and larger when ablating goal
tokens than matched non-goal
tokens from the same client. Our results show that client-specific goal representations persist in the KV cache and can causally influence decisions made for other clients, highlighting the importance of relationship-specific state isolation in persistent LLM
agents.
Read the full abstract ▾
Computation and Language
UMCR: Universal Medical Concept Recognition through Guideline Integration and Agentic Linking
Fabrice Lamarche and Amal Zouaq
Medical Concept Recognition is the task of extracting and grounding spans in medical text to entries in a standard ontology. Current methods are generally developed towards a single ontology and source text type (clinical notes, drug labels, etc.) The central challenge is therefore to build methods that adapt to any target ontology without requiring ontology-specific retraining. More recent approaches like REAL and AutoPCR make direct use of Large
Language Models and can theoretically adapt to any ontology choice but suffer from a lack of generalization. We propose UMCR, a pipeline that allows extraction and linking to any target ontology using any source text variety, utilizing direct guideline integration and an agentic linking module. We evaluate our method on the recent MedPath
benchmark, covering a wide variety of medical text types and vocabularies, and show that our method achieves strong performance across these tasks. This ability unlocks interoperability in the healthcare domain, allowing for extraction and
alignment between different medical standards. Our method also reduces dependence on parametric LLM
memory, thanks to improved interaction with the target ontology compared to other proposed approaches.
Read the full abstract ▾
Computation and Language
claimcheck: Measuring and Improving Specification Faithfulness
Martin Amster, One An, Holly Baker et al. (+3 more)
Formal verification proves that a program satisfies its specification, but says nothing about whether the specification captures what the author meant. As LLMs increasingly write both code and specifications, a gap between the author's natural-
language requirement and the specification becomes a live risk. A machine-checked proof of a property narrower than the one requested is worthless but passes every check. Closing this gap is solving the spec formalization problem: given a natural-
language requirement, produce a formal artifact whose meaning matches it. To measure the gap, we curate an end-to-end
benchmark for spec formalization spanning four formal
languages: Dafny contracts and Lean 4, Isabelle and Rocq
theorem statements. Each of its 3,234 rows pairs a natural-
language requirement with a formal artifact and a label established by execution, by proof, or by the
benchmark it is drawn from. A third of the rows are meaning-preserving rewrites of the artifact that keep the faithful label, so a judge cannot score by detecting that a row was edited. We introduce claimcheck, a tool that detects incorrect formalizations: the formal artifact is translated back into plain English by a model that never sees the requirement, and a separate model, the judge, decides whether the informalization and the requirement express the same guarantee. On all four
languages it gains 8.2 to 9.8 points of macro recall over a single call shown the requirement and the artifact, and 4.2 to 6.0 over that call handed the same list of meaning-preserving rewrites. Showing the judge the artifact as well costs 1.4 to 4.5 points. Across four judges that also see the artifact, the gain shrinks as the judge gets stronger, to within a point of the informed single call for the strongest.
Read the full abstract ▾
All authors Martin Amster, One An, Holly Baker, Fernanda Graciolli, Simon Henniger, Nada Amin
Computer Vision
Brain2Face: A Study on the Relation of EEG Signals and Spatio-temporal Head Avatars
Camilo Andrés Martínez Martínez, Olaf Dünkel, Kartik Teotia et al. (+3 more)
Driving digital head avatars is classically done by hand-crafted artist design or by image-based facial performance capture. In this work, we ask whether spatio-temporal tracking of the humans's head geometry and appearance can be performed solely from
brain signals, i.e., Electroencephalography (
EEG). Since prior work mostly focused on activity and emotion recognition, this task is relatively unexplored without even having publicly available high-quality
datasets and
benchmarks. Thus, we contribute a
dataset featuring paired
EEG and human head geometry as well as appearance annotations. We synchronize 64-channel
EEG with per-frame expression latent codes of a personalized Gaussian head avatar. Second, we introduce a baseline to the task of expression recovery of a head avatar from
EEG signals. To this end, we propose a dedicated
EEG-to-expression model that takes a temporal sequence of
EEG signals as input and regresses the latent expression parameters of the 3D Gaussian head avatar. Lastly, we validate our capture and algorithmic design choices through a
benchmark protocol that we introduce to this task. We believe this work paves the way towards better understanding of the relation between
EEG signals and facial surface as well as appearance changes.
Read the full abstract ▾
All authors Camilo Andrés Martínez Martínez, Olaf Dünkel, Kartik Teotia, Maurice Rekrut, Christian Theobalt, Marc Habermann
Computer Vision
WIRE: Weight Space Implicit Representation Encoding of Frozen Video LLMs
Ameen Ali, Tamim Zoabi, Lior Wolf et al. (+1 more)
Video language models represent a
video as a long sequence of visual
embeddings in a decoder's input. Every visual
embedding is processed by every decoder layer during prefill, stored in the key value cache, and attended by every generated
token, so a long
video raises prefill,
memory, and generation cost at once. We present WIRE (Weight Space Implicit Representation Encoding), which reduces this recurring cost by moving part of the
video conditioned computation of a frozen
video language model from its input activations into a temporary low rank update of its weights. WIRE keeps a short explicit visual context, so the update acts as a correction rather than a replacement of the
video. WIRE first compresses the full resolution
embeddings of each frame into a small set of carrier
tokens using a question conditioned bidirectional selective scan, and physically contracts the decoder input so every decoder layer, cache entry, and decoding step operates on the shorter sequence. Hypernetworks at selected decoder layers read the compressed forward pass together with a readout of the full resolution features removed by contraction and generate LoRA updates to the
attention and feedforward projections. The updates are merged after prefill, so autoregressive decoding runs the unmodified frozen backbone. On Qwen3-VL-8B, WIRE with 16 carrier
tokens per frame contracts the visual stream by $3.5\times$, reduces decoder prefill time by $3.35\times$ at 256 frames and $4.14\times$ at 1024 frames, shrinks the key value cache proportionally, and keeps per
token decoding latency approximately constant. Across nine
benchmark settings at 256 frames, it obtains the highest average accuracy among efficient
video language models we evaluate under a common 256 frame budget.
Read the full abstract ▾
All authors Ameen Ali, Tamim Zoabi, Lior Wolf, Chaim Baskin
Computer Vision
MID: Mask-Image Distributional Divergence for Evaluating Medical Image Segmentation
Vincenzo Marcianò, Xiaoming Zhang, Gianluca Guglielmo et al. (+3 more)
Current evaluation protocols for medical image segmentation remain largely anchored in sample-wise comparisons, e.g., Dice and Hausdorff distance, which require each prediction to be paired with a ground-truth mask. Yet two limitations arise in practice: they are inapplicable when predictions are made on unlabeled data; and even when annotations are available, they cannot assess whether a collection of predictions matches the distributional structure of the ground-truth population. We introduce MID (Mask-Image Distributional Divergence), a distribution-level evaluation metric for medical image segmentation. MID builds upon the observation that segmentation quality is a property of the joint image-mask distribution: a mask may be anatomically plausible in isolation yet incorrect for the image it accompanies. MID compares the joint distribution of images and masks between a reference set and a set of predictions, without requiring sample-wise correspondence. This captures both mask realism and image-mask consistency. We evaluate MID across 13 publicly available
datasets spanning CT, MRI, and MRA. Under anatomically realistic corruptions across 56 organ groups, MID tracks mean Dice and Hausdorff distance without per-sample ground-truth pairing. MID also detects distributional shifts across modalities and anatomies, identifies image-mask misalignment through controlled shuffling experiments, and produces reliable model rankings across real segmentation models. Official implementation available at github.com/erc-caravel/pytorch-mid
Read the full abstract ▾
All authors Vincenzo Marcianò, Xiaoming Zhang, Gianluca Guglielmo, Michela Antonelli, Sebastien Ourselin, Maria A. Zuluaga
Robotics
Can a Frontier VLM Serve as a Robot Policy for Memory-Dependent Manipulation?
Jack B. Jedlicki, Amish Sethi and Heng Yang
We use a frozen frontier
vision-
language model, GPT-6-Astra, directly as the
robot policy on RoboMME, a
benchmark of 16
memory-dependent manipulation tasks spanning temporal, spatial, object, and procedural
memory. The model keeps the whole episode in context and outputs every end-effector waypoint and gripper command, with no RoboMME-specific training. On the 800 test episodes it succeeds in 92.1%, above the previously reported human score of 90.5%, which was obtained with an oracle skill interface, and far ahead of the best leaderboard entry (60.8%) and of a hierarchical system that pairs the same model with a RoboMME-trained policy (79.1%). It matches or exceeds the human score on 13 of the 16 tasks. Its 63 failures concentrate in two tasks and are mostly premature completions and mistimed or unintended button presses. These results blur the usual division between long-horizon planning,
memory and end-effector control, and raise the question of how much of this stack a single general-purpose model can take over in embodied systems. Project website: https://embodied-astra.github.io. Code,
prompts and all episode logs: https://github.com/jackbjed/embodied-astra-robomme.
Read the full abstract ▾
Computer Vision
HairFlow: Modeling 3D Hair Strands with Multi-Modal Conditioned Diffusion
Yating Wang, Kui Wu, Ran Yi et al. (+5 more)
Modeling 3D hair strands is challenging due to complex hairstyle geometry, scarce high-quality training data, and incomplete or noisy input observations. Foundation models offer broader hairstyle priors, but their outputs are not directly usable for strand-based rendering and simulation. Existing approaches require costly per-instance optimization to fit hair priors to meshes from foundation models and 2D orientations from specialized predictors trained on limited hair data, restricting efficiency and generalization. We present HairFlow, a
multimodal conditioned
diffusion framework for efficient and controllable hair strands modeling. HairFlow conditions strand generation on two complementary representations: a coarse mesh that constrains global shape and multi-view sketches that specify local strand flow. HairFlow combines an Orientation VAE with a conditioned
diffusion transformer to generate volumetric fields that are traced into explicit strands. To overcome the lack of paired sketch-strand training data, we introduce an automatic synthesis pipeline that generates geometrically aligned multi-view sketches with diverse styles representative of inference-time inputs. Experiments show that HairFlow generates plausible 3D strands that faithfully follow the input conditions across diverse hairstyles, substantially reduces inference time, and supports flexible
multimodal control.
Read the full abstract ▾
All authors Yating Wang, Kui Wu, Ran Yi, Zixuan Lu, Tongtong Wang, Zhongtian Zheng, Lizhuang Ma, Yuefan Shen
Machine Learning
On the Statistical Mechanics of Attention
Jerry Yao-Chieh Hu, Yu-An Chen, Maojiang Su et al. (+1 more)
We revisit the statistical mechanics of
Transformer attention via modern Hopfield models. We present a free-energy formalism to characterize parameter regimes and critical thresholds for robust
attention inference. The resulting free-energy landscape incorporates randomness in query states and
attention weights.
Attention then emerges as the equation of motion of the corresponding statistical-mechanical system (i.e., modern Hopfield model) through the standard free-energy minimization principle. This allows us to identify first-order phase transitions in
attention between glassy and robust-inference phases. We further extend to attentions with
stochastic queries and keys. Together, our results provide a rigorous statistical-mechanics framework for characterizing phase structure and inference reliability across a family of
Transformer attention mechanisms.
Read the full abstract ▾
All authors Jerry Yao-Chieh Hu, Yu-An Chen, Maojiang Su, Han Liu
Machine Learning · Cross-listed from stat.ML
Monitoring for Shifts at Unknown Times: Parameter-Free Conditional Conformal Martingales
Tuo Liu, Drew Prinster and Francesco Orabona
Conditional conformal test martingales provide sequential tests for detecting distribution shifts, using a fixed reference
dataset to avoid contamination from test-time samples. Prior work used a penalized betting function via online optimization with smoothing, clipping, and other hyperparameters, which can adapt slowly when a shift occurs after a long stationary period. In this work, we introduce an approach that requires no hyperparameters and provably adapts quickly to shifts occurring at unknown times. Our key idea is to frame the penalized betting problem as portfolio selection in a three-asset
market. Then, we use a restarting universal portfolio, with a heavy-tailed wealth allocation over time. We establish anytime false-alarm control and derive optimal finite-sample bounds on detection delay under detectable alternatives. We also develop an FFT-based implementation that computes the portfolio sequence over $T$ rounds in $\mathcal{O}(T^2\ln T)$ time, instead of $\mathcal{O}(T^3)$ of the naive implementation. Synthetic and real-world experiments suggest that the proposed approach adapts rapidly after long periods of null samples, with detection delays depending substantially less on shift time than prior baselines.
Read the full abstract ▾
Human-Computer Interaction
Human Situational Awareness and Workload during Heterogeneous Autonomous Vehicle Hazard Monitoring: A Cross-Platform Study
Ziyue Wang, Yang Xing, Argyrios Zolotas et al. (+3 more)
As autonomous ground and aerial vehicles become increasingly capable, human operators are transitioning from direct control to supervisory monitoring roles. Maintaining Situational Awareness (SA) during rare but safety critical hazard events remains a fundamental challenge, particularly when operators must monitor heterogeneous autonomous platforms with different spatial and cognitive demands. This study develops a unified experimental framework for investigating human SA and workload during supervisory monitoring of autonomous ground and aerial vehicles under hazard conditions. Eighteen participants completed six within-subject conditions combining three interface modalities, namely, visual-only, haptic-only, and visual-haptic, with two platform types, ground vehicle and aerial drone. SA was measured using Situation Awareness Rating Technique (SART), while workload was assessed using the NASA Task Load Index (NASA-TLX). The key findings are: 1) Aerial monitoring produced significantly lower overall SA, higher situational demand, and greater workload than ground monitoring, driven by elevated Demand and reduced Understanding rather than diminished Supply. 2) Workload was consistently coupled with situational demand across all conditions, suggesting a stable SA-workload mechanism. 3) Both haptic-only and visual-haptic significantly improved overall SA relative to visual-only without increasing workload, demonstrating that interface design can enhance awareness within the existing workload envelope. These findings establish a cross-platform behavioural baseline for designing
multimodal interfaces that enhance operator SA without elevating workload in heterogeneous autonomous vehicle systems.
Read the full abstract ▾
All authors Ziyue Wang, Yang Xing, Argyrios Zolotas, Adolfo Perrusquia, Weisi Guo, Antonios Tsourdos
Artificial Intelligence
Budgeted KV-Cache Repair for Evolving Contexts
Han Yu, Wenhui Zhu, Jincheng Cao et al. (+15 more)
Language-model
agents revise their working context as information becomes obsolete, but deleting text does not erase its influence on cached computation. Later key-value (KV) states remain conditioned on the deleted content, while recomputing the entire retained suffix can be costly. We introduce budgeted KV-cache repair: recovering task performance by recomputing a user-chosen fraction of the retained suffix. Comparing repair allocations under identical relevance scores and
token budgets, we find that refreshing coherent regions can substantially outperform refreshing isolated
tokens. This finding motivates Semantic-Unit Refresh (SUR), which allocates the budget to query-relevant text regions using inexpensive
embedding scores, without training or an auxiliary
transformer forward. To execute these repairs efficiently, a layer-packed executor processes selected states together at each layer while preserving full causal cache access. Across five models, SUR achieves strong recovery in controlled deletion tasks while recomputing only 2-5% of the suffix. On four natural multi-hop QA
datasets, it achieves near-full-recompute exact match at a 5% budget with lower post-edit latency. The executor accelerates fragmented refresh by up to 16.1x over interval-wise execution.
Read the full abstract ▾
All authors Han Yu, Wenhui Zhu, Jincheng Cao, Rui Cai, Yuanda Xu, Zhengze Zhou, Xiwen Chen, Hao Wang, Xuanzhao Dong, Han Shi, Menglin Zhou, Shayan Mohajer Hamidi, Lin Su, Mina Razghandi, Sayan Ghosh, Qing Lan, Rohit Jain, Alborz Geramifard
Systems and Control
Filtering for Liveness: Recurrence via Backup Reachability Control Barrier Functions
David E. J. van Wijk, Pio Ong, Aaron D. Ames et al. (+1 more)
Liveness requires a dynamical system to repeatedly accomplish a desired objective over time. In this work, we consider a particular form of liveness known as recurrence, which requires the closed-loop trajectory to regularly revisit a prescribed set, with no more than a specified amount of time between visits. Inspired by the control barrier function (CBF) safety-filter paradigm, we develop a controller-filtering framework that makes adjustments to a nominal controller only when necessary to guarantee recurrence. Unlike conventional CBF methods, which enforce set forward invariance, our framework allows the trajectory to leave the set while guaranteeing its timely return. To achieve this, our framework combines two components: a backup reachability CBF that preserves the ability to return to the prescribed set within the allowable time, and a timing-based mechanism that invokes a reaching controller only when the nominal behavior would otherwise fail to meet the return-time requirement. The resulting framework guarantees recurrence while preserving the nominal behavior when possible, enabling control objectives that require temporary excursions from the set, such as traversal between disjoint regions. Our method is successfully utilized in a drone racing example with a recurrence constraint on beacon visibility.
Read the full abstract ▾
All authors David E. J. van Wijk, Pio Ong, Aaron D. Ames, Joel W. Burdick
Game Theory
An Introduction to Contract Theory for Computer Scientists
Paul Duetting, Michal Feldman and Inbal Talgam-Cohen
This survey introduces contract design to computer scientists: using outcome-based payments to incentivize effort. We discuss applications that motivate a computational approach to contract design, ranging from online labor
markets, to incentive-aware algorithmic classification, to emerging ecosystems of AI
agents. We present the classic principal-
agent model and introduce basic concepts. We show how optimal contracts are computable via linear programming, and why they can be opaque and brittle. Motivated by this we turn to simpler contract formats, specifically linear contracts. We discuss approximation guarantees, and robust (max-min) optimality of such contracts. We then move beyond the single-
agent setting to combinatorial contract settings with multiple
agents, mapping the algorithmic landscape of tractability and approximation. Finally, we discuss partial information settings through the lens of learning
algorithms, and outline open directions. The goal is a concise, accessible entry point that connects economic foundations with algorithmic tools and highlights opportunities for new theory and applications.
Read the full abstract ▾
Machine Learning · Cross-listed from stat.ML
Accounting for model error in ensemble variational data assimilation through learned generative dynamics
Marc Bocquet, Tobias S. Finn and Sibo Cheng
Many approaches have recently been proposed to combine data assimilation with machine learning for improved forecasts with geophysical models. Here, we focus on combining advanced sequential data assimilation schemes with a generative forecasting model which accounts for complex model errors. This generative model provides a
stochastic approximation of the conditional distribution of the successor state given the current state. The proposed variational formulation is a novel one-step weak-constraint 4D-Var scheme in which a learned conditional
stochastic forecast replaces the prescribed additive Gaussian model error representation. We derive and implement this formulation as an ensemble variational
algorithm, the generative iterative ensemble Kalman filter (IEnKF-G), which generalises the iterative ensemble Kalman filter with additive Gaussian model error (IEnKF-Q). We extend the method to a smoother with an assimilation window spanning multiple time steps and propose a simplified variant. The IEnKF-G is evaluated on a
stochastic variant of the Lorenz 1963 model to assess its robustness. It is then tested on a multi-scale variant of the one-dimensional Lorenz 1996 model, in which the resolved variables are affected by model error originating from the hidden small-scale variables. The
algorithm is then compared to an ensemble Kalman filter that adaptively mitigates model and sampling errors, and to the IEnKF-Q. The IEnKF-G is generally more accurate in the tested configurations, with substantial gains under partial observations and significant model error. This demonstrates the potential of generative data-driven models when paired with classical data assimilation methods, particularly when model error is substantial.
Read the full abstract ▾
Machine Learning
COMPASS: Membership Inference Attack Against Vision Large Language Models via Adaptive Noise Calibration
Damien Lo, Hong Kyu Lee, Ruixuan Liu et al. (+1 more)
Vision large
language models (VLLMs) are deployed in
privacy-sensitive domains, raising training-data exposure concerns. Existing gray-box membership inference attacks (MIAs) commonly rely on
entropy statistics or generated descriptions, requiring costly generation with limited membership separation. Perturbation-based methods instead measure response changes but focus on large perturbations, leaving VLLM membership behavior under smaller perturbations poorly understood. We systematically characterize VLLM membership behavior under controlled Gaussian perturbations across noise levels at fine resolution. We find that optimal perturbation magnitude and membership-signal direction vary across model-
dataset pairs. In many settings, a previously unstudied low-noise regime yields stronger separation than large perturbations, with members exhibiting lower divergence than non-members, reversing the conventional score direction. Other settings retain the conventional direction, demonstrating that neither a fixed perturbation magnitude nor a predetermined score orientation is universally reliable. We propose COMPASS, an adaptive gray-box MIA that calibrates both the perturbation magnitude and membership-score direction using a loosely distribution-matched, known non-member reference set. We instantiate COMPASS using Renyi-normalized KL divergence and Renyi divergence, with max-k aggregation over the most informative image-logit positions. Across LLaVA v1.5-7B, MiniGPT-4, and HuluMed-32B, spanning pretraining, instruction-tuning, and medical-image
datasets, COMPASS outperforms baselines. On general-domain data, COMPASS achieves AUCs up to 0.88. On the distribution-matched medical evaluation, it reaches 0.64 AUC, while the strongest baseline remains at chance level. These results establish full-range adaptive perturbation analysis as an effective approach to VLLM membership inference.
Read the full abstract ▾
All authors Damien Lo, Hong Kyu Lee, Ruixuan Liu, Li Xiong
Artificial Intelligence
Do Theorem Provers Need Theorem-Proving Agents? mini-Lean-agent: A Coding-Agent Baseline for Lean
Tomas Ortega, Simon Park, Ayush Khaitan et al. (+3 more)
General-purpose coding
agents use standard shell and file interactions, yet formal
theorem-proving
agents often rely on specialized, ad-hoc tooling. This makes it difficult to determine which components of
theorem-proving
agents provide
benchmark gains: an improved base model, a specialized harness, a specific tool, or a combination of any of them. We introduce mini-Lean-
agent, a deliberately minimal
agent for Lean tasks whose only model-visible tool is bash. The model must use bash to inspect and edit the repository, search local libraries, invoke Lean, and manage its own intermediate work, while a separate trusted evaluator verifies the final artifact. We compare mini-Lean-
agent against AxProverBase and Numina-Lean-
Agent on the Putnam 2025
benchmark. Experiments with Gemini 3.8 Flash as the base model show that mini-Lean-
agent solves 7/12 problems at \$2 per problem limit, compared with AxProverBase's 4/12. With Astra as the base model, mini-Lean-agent solves 12/12 problems at an average cost of \$1.28 per problem. This suggests that a generic coding
agent with a minimal harness can already achieve strong performance on Lean
benchmarks. Our results motivate using mini-Lean-
agent as a standard baseline when evaluating
theorem-proving infrastructure.
Read the full abstract ▾
All authors Tomas Ortega, Simon Park, Ayush Khaitan, Liam Fowl, Alex Kontorovich, Sanjeev Arora
Systems and Control
STATCOM-Based Flicker Mitigation in Electric Arc Furnace Systems Using DQ-PI and Lyapunov-Based Nonlinear Control
Vikram Chekuri, Narapareddy Ramarao and Prashanth N A
Electric arc furnaces inject
stochastic reactive-power swings that cause voltage flicker at the point of common coupling. This paper compares two STATCOM inner controllers for an 11~kV, 50~Hz furnace feeder: a split-frequency DQ-PI design and a Lyapunov-based nonlinear design whose integral state is retained in the storage function, giving global asymptotic stability of the nominal unsaturated current-error subsystem. Gains for both controllers were tuned by a frozen metaheuristic campaign and then evaluated over 600~s with an IEC~61000-4-15 digital flickermeter. A post-campaign audit showed that the
stochastic arc realization used for the original comparison was periodic, so the two selected gain sets were frozen without retuning or reselection and evaluated on ten independent
stochastic realizations that had been specified and archived before the STO-ENS validation campaign, together with a paired uncompensated case for each realization. Both controllers reduce the mean short-term flicker severity by about 62% relative to the STO-ENS uncompensated baseline, and no statistically detectable difference in mean flicker severity is found between them. They separate instead in realization sensitivity: the Lyapunov standard deviation across arcs is roughly one third that of DQ-PI. Controller ordering inferred from a single
stochastic trajectory is therefore not a reliable measure of
stochastic robustness, and ensemble validation is necessary.
Read the full abstract ▾
Performance
DynaSPLIT: Strong tail-optimal scheduling for the M/G/n with heavy-tailed job sizes
Zhouzi Li, Mor Harchol-Balter and Alan Scheller-Wolf
We study the asymptotic response time tail in the M/G/n queue with heavy-tailed (regularly varying) job sizes. For this setting, strongly tail optimal policies are known only at lower load, where n-1 servers suffice for stability. At higher load, the tail optimal scheduling has been open. This paper presents DynaSPLIT, the first strongly tail optimal policy at high load. Together with prior work, this result shows that strong tail optimality is achievable across the entire stability region of the M/G/n with heavy-tailed job sizes.
Read the full abstract ▾
Computation and Language
The Curse of Knowledge in Role-Playing Language Models
Xiao Zhang
Role-playing
language models speak as characters in games and
agent simulations, where the system records what each character can hear, see and understand. We test whether characters respect these boundaries in 480 scenes, each with a counterfactual twin that changes only the hidden fact, so mentions of the twin's fact measure guessing. Across 11 open-weight models, characters use content from
speech they cannot understand or hear at 67 and 72 percentage points (pp) above this baseline, although most models correctly state what the character perceives. This is a curse of knowledge. The leak extends to hidden actions and private messages and changes where characters search. Five of six proprietary models rarely leak, but compliance in strong models depends on input format. Changing only the scene layout or character description raises the rate in two otherwise compliant open-weight models from under 10 to over 60 pp, and combined changes raise two proprietary models from near zero to 13 and 21~pp. Writing the line as the scene's author leaks nearly as much as role-play, and thinking rarely helps. Giving models only what the character observes stops the leak without hiding what it may report.
Read the full abstract ▾
Robotics
Evaluating Long-Horizon Robot Planning under Uncertainty
Harsh Muriki, Gayathri Aravindan, Yuchen Zheng et al. (+1 more)
Household
robots must successfully navigate im-perfect circumstances, both in their internal models and the external world. We introduce a
benchmark of seven long-horizon household tasks in Habitat that vary initial
robot memory and environment configurations. We evaluate adaptations of ReAct, VLM-TAMP, and Tru-POMDP within a shared execution framework across 90 tasks-environment-
memory combinations, totaling 1,350 episodes. Our evaluation measures task success, partial completion, and action efficiency, along with rule-based analysis of execution traces. ReAct achieves the highest overall task success (45.3%) and completion (71.7%), while having accurate initial
memory does not consistently yield the highest performance for every planner. We identify recurring placement errors, precondition errors, and redundant actions through trace analysis. These findings highlight differences in how the evaluated planners use initial knowledge and respond to uncertainty.
Read the full abstract ▾
All authors Harsh Muriki, Gayathri Aravindan, Yuchen Zheng, Sonia Chernova
Computation and Language
Thinking Outside the Bots: Human Ideas in AI's Semantic Blind Spots Are Not Inferior
Kibum Moon, Dan R. Johnson, Kostadin Kushlev et al. (+6 more)
AI-generated outputs are frequently perceived as highly creative, but also tend to be more similar to each other (homogenized) than human ideas. Does the human heterogeneity that extends beyond AI reflect valuable thinking that AI misses? Alternatively, is greater human heterogeneity driven by lower-quality ideas and less effective thinking that AI avoids? We developed Expansion of Divergent Generative Expression (EDGE) to map AI's semantic "blind spots" by assessing how strongly/weakly individual human ideas were represented in a task-matched AI semantic comparison set. Specifically, we compared human-generated vs. AI-generated ideas across three open-ended tasks: college admissions essays, alternative uses for everyday objects, and interpersonal advice. Across all three tasks, human responses extended into semantic regions sparsely covered by AI outputs. These distinctively human responses showed no meaningful deficits in creativity, quality, or effectiveness, were associated with equal-or-better academic performance, and with credibly superior ratings and achievement for some outcomes. These ideas were thus not merely poor-performing variation; they performed as well as or better than ideas that overlapped more strongly with AI ideas. More distinctive human ideas tended to receive higher creativity ratings, but this relationship was weak or reversed for AI ideas. Taken together, these results suggest that differentiation among human-generated ideas does not reflect poor thinking that AI can safely omit, and instead may afford both individual and population-level advantages.
Read the full abstract ▾
All authors Kibum Moon, Dan R. Johnson, Kostadin Kushlev, Benjamin Lira, Indre Viskontas, James C. Kaufman, Roger E. Beaty, Angela L. Duckworth, Adam E. Green