Peer Revenue Play credits. Real papers.

Papers

Fresh from arXiv, typeset properly. Highlighted words trade on the market.

Computer Science

cs Watch Computer Science

Wednesday 16 September

Software Engineering

Code-as-Auditor: Executable Compliance Reasoning via Regulation-to-Code

Jisoo Kim, Taeyoon Kwack, Jinwoo Jang et al. (+2 more)

Large Language Models (LLMs) are increasingly adopted for compliance and legal reasoning tasks, yet their outputs often lack explicit grounding in legal logic and evidence. We present Code-as-Auditor, an LLM-based framework that extends the model's reasoning capability toward structured and evidence-grounded compliance assessment. The framework translates regulatory information into (1) formalized checklists and executable decision trees, encoding regulations and conditions as interpretable code structures. During inference, each checklist item is (2) dynamically expanded into factual and counterfactual questions, guiding the model to reason over case-specific evidence and potential violations. This process establishes a reasoning pipeline that proceeds from evidence identification, through rule application, to final decision-making, while a self-verification loop improves the logical consistency of the generated code and the traceability of outcomes. Experiments on privacy and data protection scenarios demonstrate that Code-as-Auditor delivers more accurate and evidence-backed evaluations, enabling automated compliance regulation checking grounded in explicit regulatory criteria.
Read the full abstract

All authors Jisoo Kim, Taeyoon Kwack, Jinwoo Jang, Woo Kyung Kim, Honguk Woo

Robotics

DITTO: Dexterous Interface for Transparent TeleOperation

Joaquin Palacios, Katelyn Lee, Cheng Zhang et al. (+2 more)

Collecting data for manipulation with high-DOF hands is challenging, as interfaces must capture rich hand motion while rendering the contact interactions essential for precise manipulation. Existing data collection approaches face a trade-off: teleoperation ensures deployment consistency but lacks force feedback, while handheld (in-the-wild) systems provide natural force transparency but introduce a visual embodiment gap at deployment. We present DITTO, a Dexterous Interface for Transparent TeleOperation, which resolves this through the anatomically informed co-design of a dexterous 7-DOF robotic hand and a kinematically equivalent motorized exoskeleton. A 1-to-1 actuator mapping between the exoskeleton and robotic hand enables handheld (in-the-wild) data collection and bilateral teleoperation with joint-level force feedback unified in a single platform. We demonstrate that the DITTO exoskeleton spans the operator's natural index-to-thumb workspace, and showcase DITTO's dexterous capabilities via learned policies on contact-rich tasks.
Read the full abstract

All authors Joaquin Palacios, Katelyn Lee, Cheng Zhang, Zhanpeng He, Matei Ciocarlie

Computation and Language

Objective vs. Search: Decomposing What Makes a Good Tokeniser

Ahmetcan Yavuz, Clara Meister and Tiago Pimentel

Two dominant tokenisation algorithms are used by modern language models: byte-pair encoding (BPE) and UnigramLM. These differ along two orthogonal axes: their optimisation objective (compression vs. log-likelihood) and their search procedure (bottom-up merging vs. top-down pruning). Existing comparisons confound these axes, making it unclear whether their observed differences stem from what is being optimised vs. how it is being optimised. We disentangle the two by introducing two new tokenisation algorithms that complete this 2x2 design space: BottomUpLL, a bottom-up likelihood-based tokeniser, and TopDownComp, a top-down compression-based tokeniser. We train language models with tokenisers produced by each algorithm, varying: model size, vocabulary sizes, and domain (English-only vs. multilingual). Evaluating models on bits-per-byte, we find that the search procedure – not the objective – is the dominant factor: bottom-up tokenisers consistently achieve lower bits-per-byte in most settings. Evaluating models on the BLiMP task, however, shows no consistent relationship between design choice and performance. Overall, our results disentangle the effect of tokeniser design choices on language modelling performance, offering concrete guidance for their more principled construction.
Read the full abstract

Computation and Language

A Zeroth-Order Paradigm for LLM Preference Alignment

Peter Chen, Xi Chen, Wotao Yin et al. (+1 more)

Direct preference alignment methods are widely used to align large language models (LLMs) with human preferences because of their computational and memory efficiency. However, likelihood displacement motivates alternative ways to extract information from preference pairs with small likelihood margins. In this paper, we propose and analyze Comparison-based Preference Optimization (ComPO), a zeroth-order alignment method based on comparison oracles. ComPO extracts directional information from these pairs without directly optimizing a differentiable preference loss on them. We establish a convergence guarantee for its basic offline scheme under smoothness, gradient sparsity, and compatibility between the oracle and a latent objective. We further introduce online ComPO, which retains the offline comparison mechanism and uses unlabeled policy generations for reverse-KL control relative to a reference policy. Following the coverage perspective of preference fine-tuning, we establish a performance guarantee for a basic constrained scheme under local coverage and in-distribution pairwise reward accuracy. Experiments on Mistral, Llama, Gemma-2, Qwen3, and Gemma-3 models demonstrate improvements over existing direct alignment methods, including length-controlled win rates, with pair-level diagnostics providing evidence consistent with mitigating likelihood displacement.
Read the full abstract

All authors Peter Chen, Xi Chen, Wotao Yin, Tianyi Lin

Computer Vision

PANORAMA: Panoptic Grounded Captioning via Mask Proposal Selection

Sara Pieri, Evangelos Kazakos, Shizhe Chen et al. (+2 more)

Intelligent systems that act in the world require image understanding that is both comprehensive and spatially grounded. Current vision-language models (VLMs) can generate fluent and detailed image captions, but reliably associating them with image pixels remains challenging. Existing methods that combine dense captioning with pixel-level grounding often produce either incomplete descriptions or inaccurate segmentation masks. We study this problem through panoptic grounded captioning, a task that requires a VLM to describe both foreground objects and background regions while grounding each referring phrase with pixel-level masks. We make three contributions. First, we introduce PanoCaps, a human-annotated benchmark constructed from panoptic segmentation datasets. It provides dense captions with near-complete pixel coverage and image-text alignments at the entity level, supporting both training and evaluation. We further propose a phrase-mask matching protocol and a generalized Panoptic Quality (gPQ) metric that jointly evaluates textual and mask agreement. Second, we formulate phrase grounding as selection from a phrase-conditioned pool of mask proposals and introduce PANORAMA, a VLM that conditions a pretrained segmenter on contextualized phrase representations to obtain candidate masks and learns to select those corresponding to each phrase. Training this interface jointly with caption generation enables PANORAMA to produce high-quality masks while allowing each phrase to refer to a single region or multiple instances. Third, PANORAMA achieves the best overall grounding on PanoCaps and matches or exceeds specialized models across several pixel-level grounding tasks. Experiments show that our method produces precise entity-level segmentations while maintaining detailed, mask-consistent captions. Code, data and models are available at https://www.di.ens.fr/willow/research/panorama/.
Read the full abstract

All authors Sara Pieri, Evangelos Kazakos, Shizhe Chen, Josef Sivic, Cordelia Schmid

Computer Vision

PointZero: 3D Point Track Completion for Learning Transferable 3D Dynamics

Bardienus P. Duisterhof, Kaifeng Zhang, Adam Hung et al. (+5 more)

World models endow perceptual systems with the ability to predict how scenes evolve under interaction. They are most beneficial when trained on diverse volumes of data, to instill a rich prior into downstream applications. Existing methods typically require robot action labels to learn action-conditioned 3D dynamics, which excludes web video data from the training pool. We study 3D point track completion as a pre-training objective for learning transferable 3D dynamics without robot data. Given a single RGB-D observation and sparse partial 3D trajectories (tracks), we predict future 3D tracks of all observed points. We show this objective produces a rich 3D dynamics prior, without requiring robot action labels. We contribute a diverse dataset of 2.9 million synthetic frames spanning deformable, articulated, and rigid objects, and use it to train PointZero. We show that a flexible and expressive transformer, PointZero, outperforms prior methods on the same data. We demonstrate the utility of our pre-training objective by post-training PointZero for two downstream applications: (1) action-conditioned 3D dynamics prediction and (2) imitation learning. When fine-tuned to condition on end-effector pose, PointZero outperforms the baselines on the recent PGND 3D dynamics benchmark. When fine-tuned to predict robot actions and 3D tracks, PointZero outperforms or matches the baselines on 6/7 simulated and real-world robot manipulation tasks. We furthermore evaluate training PointZero from scratch to isolate the benefits of our proposed architecture from those of our proposed pre-training objective and dataset. We release the dataset, checkpoints, and full training recipe.
Read the full abstract

All authors Bardienus P. Duisterhof, Kaifeng Zhang, Adam Hung, Bowen Wen, Stan Birchfield, Yunzhu Li, Deva Ramanan, Jeffrey Ichnowski

Cryptography and Security

AgentLSD: Evaluating AI Security Agents Under Adversarial Task Contamination

Matteo Golinelli, Idilio Drago, Matteo Boffa et al. (+2 more)

AI agents for security inspect web pages, source code, logs, configuration files, and command outputs. These environments may contain deceptive artifacts that influence the agent's behavior. We call this adversarial task contamination. Whereas prompt injection relies on attacker-supplied instructions, task contamination also includes non-instructional evidence, such as fake results and decoy endpoints. We present AgentLSD, a controlled framework for studying adversarial task contamination. AgentLSD uses Capture the Flag (CTF) challenges as its experimental environment. We inject trap artifacts, such as fake flags, misleading hints, decoy endpoints, and hidden cues, while preserving the intended CTF solution. The framework supports paired clean and trap-augmented experiments with deterministic trap generation, runtime injection, telemetry, and delivery verification. We evaluate six models on 11 web CTF challenges. In the clean condition, agents capture 41% of the flags, and no model solves every challenge. We then measure the impact of task contamination. Even when the agent still recovers the flag, traps increase the number of turns (+20) and reasoning tokens (+2k). Solve-rate effects are more heterogeneous, as some model-challenge pairs are largely unaffected while others follow decoys or submit wrong flags. These results show that clean CTF performance understates vulnerability to deceptive task evidence. AgentLSD isolates this effect and provides a reproducible benchmark for studying it. We release the framework, configurations, trap specifications, and raw traces.
Read the full abstract

All authors Matteo Golinelli, Idilio Drago, Matteo Boffa, Francesco Bergadano, Bruno Crispo

Computer Vision

In-Context Robot Learning with VLM Agents

Dongzhou Cheng, Taoran Yi, Ye Fang et al. (+12 more)

Enabling robots to adapt to unfamiliar environments as readily as humans remains a moonshot goal of embodied AI. No finite collection of demonstrations can cover every task and situation a robot will encounter, making the ability to learn from context at deployment essential for generalization. Such in-context learning (ICL), however, remains largely beyond the reach of existing robotic policies. The broad agentic capabilities of commercial vision-language models (VLMs), such as GPT-6 Astra, raise a compelling question: can these models learn from demonstrations, examples, and interaction feedback, then translate that information into executable and verifiable robot behavior from a new initial state without gradient updates or persistent changes to task-specific parameters? We introduce GPT-Policy, a general-agent framework for in-context robot learning. GPT-Policy integrates a context compiler that preserves task-relevant visual transitions, a VLM that proposes robot-tool actions, and a constrained controller that verifies and executes each action and reports its outcome. We evaluate its reliability and limitations through task success and efficiency metrics, matched comparisons across models, and controlled context ablations. In real-robot trials, human video demonstrations improve task completion even without robot action labels, while aligned action references yield further gains on contact-sensitive tasks. These findings position GPT-Policy as a step toward robot adaptation through in-context learning, providing an empirical foundation for translating the general-purpose capabilities of VLMs into physical behavior and clarifying the challenges that must be overcome for reliable deployment.
Read the full abstract

All authors Dongzhou Cheng, Taoran Yi, Ye Fang, Xingwu Zhang, Fan Feng, Yixuan Li, Gengxiong Zhuang, Rongze Wang, Shuai Yang, Wei Song, Weizhi Xue, Minyan Wu, Jie Gui, Jiaqi Wang, Tong Wu

Robotics

Dreaming the Sound of Contact: Leveraging Video and Audio Generation for Zero-Shot Force-Aware Manipulation and Data Generation

Guanhua Ji, Tianyu Li, Dayoon Suh et al. (+3 more)

Video generation models have advanced rapidly and can now synthesize plausible videos of robot manipulation from image and text prompts. Recent work extracts robot actions directly from such generated videos, but the result is purely kinematic and lacks force information, causing failures in contact-rich tasks where appropriate contact forces are essential for success. We present a pipeline that jointly leverages generated video and audio to derive motion trajectories and desired-force profiles. The force profile is shaped by the loudness of the generated contact sound, and we execute the resulting force-aware trajectories on a Franka robot using a closed-loop force regulator. We evaluate our pipeline on multiple tasks that require making contact and demonstrate successful zero-shot manipulation where a kinematic-only baseline fails. We also show that the pipeline can be used as a data generation engine to train policies that achieve the tasks in a closed-loop manner. Project website, videos, and dataset: https://dreamingcontactsound.github.io/
Read the full abstract

All authors Guanhua Ji, Tianyu Li, Dayoon Suh, Yuqian Zhang, Boyan Zhang, Nadia Figueroa

Data Structures and Algorithms

Maximum Matching Size for Bounded Arboricity Graphs in the Dynamic Graph Stream Model using $\tilde{O}(n^{2/3})$ space

Andrew McGregor

The paper presents a one-pass algorithm in the insert-delete graph stream model that returns a $(1+\varepsilon)(\alpha+2)$-approximation for the size of the maximum matching in a graph of arboricity at most $\alpha$. The algorithm uses $O(\varepsilon^{-4/3}\alpha^{4/3}n^{2/3} \text{polylog} n)$ space. For constant $\alpha$ and $\varepsilon$, this improves the best known previous space bound from $O(n^{4/5} \text{polylog} n)$ to $O(n^{2/3} \text{polylog} n)$. The algorithm is a linear sketch and requires no bounds on the number of deletions or on the arboricity of intermediate graphs.
Read the full abstract

Machine Learning

Exponential Hardness of Off-Policy Evaluation under History-Dependent Logging

Pranaya Jajoo

Can a logged dataset visit every hidden state frequently and still be exponentially uninformative about a target policy's value? We show that it can when the logger depends on history. For every horizon $H \ge 3$, we construct two POMDPs with at most two latent states per stage, three actions, and a common logger with three memory states. Action coverage, belief coverage, and two behavior-marginal outcome-revealing conditions all have constants independent of $H$. Nevertheless, evaluating a known deterministic target policy to accuracy $1/8$ requires $\Theta((3/2)^H \log(1/\delta))$ logged episodes at confidence $1-\delta$, for $0 < \delta \le 1/4$, even when both candidate models are known. The mechanism is simple: a reset erases the unknown transition that determines the target value. We characterize the resulting statistical experiment exactly and obtain a matching optimal estimator. A directed two-lane gridworld realizes the construction, and trajectory simulations agree with its finite-sample prediction. The result establishes intractability for the history-dependent-logging, model-based case posed by Zhang and Jiang (2025, arXiv:2503.01134), under their behavior-marginal definition of revealing.
Read the full abstract

Computation and Language

ScienceIDE: Turning World's Scientific Codebase into Agent Learnable Environments

Hejia Geng, Zesen Huang, Haoyang Li et al. (+60 more)

Scientific code repositories encode decades of human knowledge in executable models, methods, and tools. Yet fragmented toolchains, implicit domain conventions, and specialized correctness criteria make this knowledge difficult to convert into reliable learning experience-a challenge we call the scientific experience bottleneck. We introduce ScienceIDE, infrastructure for turning the world's scientific code into programmable environments for scientific agents. Guided by expert-defined scientific cases and acceptance criteria, agents transform repositories into executable environments that support task generation, execution, and scientific verification. These environments provide a shared foundation for supervised fine-tuning, reinforcement learning, and evaluation. Using verified interaction trajectories, we train PhAI-IDE-72B/9B/4B. The model family shows gains in held-out scientific-code repair and across selected general-purpose benchmarks in code, reasoning, and knowledge, providing evidence of positive transfer from scientific experience to broader capabilities. ScienceIDE lays the foundation for an integrated workspace for agent learning and scientific practice, making humanity's scientific software a shared substrate for developing scientific intelligence. Code: https://github.com/aitofound/ScienceIDE
Read the full abstract

All authors Hejia Geng, Zesen Huang, Haoyang Li, Wenbin Li, Koutian Wu, Zihan Zhou, Yuanbo Pang, Weihao Liu, Zigong Xu, Zhiping Li, Zongzheng Zhang, Chuanfei Dong, Jiankai Sun, Tianzhe Zheng, Fengyu Xie, Yue Ma, Yueheng Shi, Junkai Wang, Tong Xie, Zonglin Di, Xianrong Liu, Qucheng Gao, Yimin Liu, Jiaming Pan, Sheng Huang, Xiao-Han Ma, Lanqing Yuan, Zhenlin Zhu, Ziang Liu, Ziyang Xu, Kangkai Liang, Jiayi Xian, Zehong Zhao, Taigao Ma, Fuming Chang, Yuanzhe Hu, Liuwei Xu, Xianzhe Tang, Jingxu Xie, Peijin Zhang, Qiang Gao, Chengyi Xing, Zhe Zhao, Xi Wang, Leo Wang, Fang Wu, Jiacheng Ge, Weixuan Liao, Jungang Chen, Shuozhe Li, Yi Daniel Lu, Xu Pan, Shuhang Lin, Peihan Tu, Nan Liu, Zelin Tan, Yunze Xiao, Hao Xiao, Yaopeng Xing, Xing Meng, Zhenfei Yin, Yingcheng Wu, Ling Yang

Data Structures and Algorithms

A $2$-Approximation for Directed Feedback Vertex Set in Locally Semicomplete and Quasi-Transitive Digraphs

Sounak Modak

A directed feedback vertex set of a digraph is a set of vertices whose removal destroys all directed cycles. The Directed Feedback Vertex Set (DFVS) problem asks for such a set of minimum cardinality or minimum total weight. Although general DFVS admits no constant-factor approximation under the {Unique Games Conjecture}, tournaments admit a randomized factor-$2$ approximation due to Lokshtanov et al. [SODA'20]. We extend this guarantee to two broader classes of structured digraphs, both of which also contain sparse digraphs. Our first and main result is a randomized polynomial-time factor-$2$ approximation for weighted DFVS on locally semicomplete digraphs (LSDs), a class that strictly generalizes semicomplete digraphs and tournaments. To the best of our knowledge, this is the first non-trivial constant-factor approximation for DFVS on LSDs, even in the unweighted setting. Our second result is a randomized polynomial-time factor-$2$ approximation for weighted DFVS on quasi-transitive digraphs, improving the recent deterministic $9/4$-approximation of Ghorbani and Mnich~[ICALP'26]. The algorithm follows from a simple recursive application of our composition framework. The factor $2$ is optimal under the {Unique Games Conjecture}, since tournaments are subclass of LSDs as well as quasi-transitive digraphs.
Read the full abstract

Artificial Intelligence

Cognitive Extensions for Dual-Process Language Agents: Memory and Self-Reflection in Interactive Environments

João Meneses dos Santos and Arlindo L. Oliveira

Language agents remain brittle in interactive environments, where success requires long-horizon state tracking, valid action execution, and recovery from failed steps. We extend SwiftSage, a dual-process agent that combines a fast action proposer with a slower planner, using two modular cognitive extensions: an Adaptive Memory Module (AMM) for salience-gated episodic storage and trigger-driven retrieval, and a Self-Reflection Module (SRM) for bounded execution-time validation and corrective intervention. Both modules are implemented as feature-flagged extensions over the same execution substrate, enabling controlled ablations on ScienceWorld. Across four configurations—baseline, baseline+AMM, baseline+SRM, and the full system—the full system achieves the best mean final score (64.62), success rate (43.17%), and successful-step efficiency (19.33 steps), while SRM is the strongest standalone contributor. The results suggest that execution-time control is the dominant bottleneck in this setting, while episodic memory becomes most useful once the runtime loop is stabilized.
Read the full abstract

Human-Computer Interaction

EarStreAM: A Closed-Loop Earable System for Personalized Stress-Adaptive Meditation

Jonas Hummel, Luisa Faust, Elias Müller et al. (+7 more)

We present EarStreAM, a closed-loop earable system for stress-adaptive meditation that integrates in-ear physiological sensing with personalized, real-time intervention. Leveraging OpenEarable 2.0's multimodal sensing, EarStreAM continuously monitors physiological signals and detects elevated stress from heart rate and heart rate variability. Upon detection, the system initiates a personalized guided meditation generated by an LLM and adapted in real time to the user's stress state. The demo offers a hands-on experience of stress-adaptive meditation in two modes: a biosignal-adaptive meditation with optional stress induction to illustrate closed-loop adaptation, and a meditation-only mode focusing on EarStreAM's generative personalization capabilities. The demo highlights how in-ear sensing, closed-loop adaptation, and personalized generative meditation can be integrated into an earable system for real-time stress support in demanding office work contexts.
Read the full abstract

All authors Jonas Hummel, Luisa Faust, Elias Müller, Eva Bertog, Valeria Zitz, Marius Johannes Prill, Luca L. Bennardo, Luisa Weber, Tobias Röddiger, Michael Beigl

Human-Computer Interaction

Affora: A Design System for Agent-Friendly Interfaces

Jin Gao

Computer-use agents increasingly operate software designed for people, but interfaces often leave actions or task state unclear to machine readers. We present Affora, a design system that supports both readers while preserving visual freedom and familiar human workflows. Three controlled studies examine component implementations, visual variation, and interaction-design principles. Their findings inform guidance from individual components to complete sites, supported by reusable implementations and executable checks. Agent performance depends on the interaction meaning available through its interface representation; substantial visual variation remains possible when that meaning is preserved. Evaluation on independently authored interfaces shows gains where Affora addresses existing deficits, but limited effects where those deficits are absent or outside its coverage. A workflow case provides preliminary evidence of reduced interaction cost. Affora connects user experience and agent experience through a shared interface rather than a separate agent-only surface.
Read the full abstract

Artificial Intelligence

Flag Game: A Toy Model for Mechanistic Swarm Interpretability

Elizabeth Pavlova and Hidenori Tanaka

Emergent coordinated behaviors of AI agents are starting to present critical safety risks. A key phenomenon driving these behaviors is the rapid formation and spread of beliefs about the world, and mechanistic understanding is crucial for collective alignment. To this end, we introduce the Flag Game, a toy model for studying the mechanisms of collective belief formation. Concretely, a hidden country flag defines the ground truth, and each bounded agent directly observes only a private crop but can exchange beliefs and weigh social evidence from peers. Despite its simplicity, the Flag Game reproduces rich collective phenomenology: non-monotonic scaling of performance with population size, accuracy gains from social-awareness prompting and team diversity, and strong effects of organizational structure. In particular, we identify that collective belief collapse at small population sizes turns into collective belief polarization as the population grows. This polarization causes the performance decline at large population sizes, but creates diversity in collective beliefs. Finally, we dissect the mechanisms underlying collective belief collapse and polarization with two complementary approaches. We first introduce social circuit attribution, a technique to predict which agent, and what view, matters most to collective dynamics, and verify its predictions by causal interventions on agents, tracing how agent patching changes collective outcomes. However, the efficacy of causal interventions on agents decreases as the population grows. We therefore develop a statistical mechanical theory for larger populations and verify that it matches the empirical phase diagram. Together, these results take a first step toward mechanistic swarm interpretability, a science of how the properties of individual agents and their communication give rise to emergent collective behavior.
Read the full abstract

Computer Vision

Training-Adaptive Convolutional Sparse Coding via Information Bottleneck for Robust Visual Representation

Meng'en Qin, Yinchen Liu, Mingxuan Cui et al. (+1 more)

Visual signals require compact yet sufficient representations for robust downstream prediction. Convolutional sparse coding (CSC) provides an explicit mechanism for suppressing redundant components while preserving signal content, but its sparsity coefficient is often manually selected during training. We propose a training-adaptive convolutional sparse coding framework for robust visual signal representation. Specifically, we unfold the CSC optimization with the Fast Iterative Shrinkage-Thresholding Algorithm (FISTA) and treat the sparsity coefficient as a differentiable variable jointly learned with the network parameters. From the information bottleneck perspective, this coefficient controls the trade-off between information retention and compression: the sparsity term promotes compact representations, while the reconstruction term together with task loss preserves task-relevant signal content. We further introduce a label-free post-training strategy that adjusts the compression strength for corrupted inputs with the main network parameters fixed. Experiments on CIFAR and ImageNet demonstrate competitive clean-data recognition and greatly improved robustness under different input perturbations.
Read the full abstract

All authors Meng'en Qin, Yinchen Liu, Mingxuan Cui, Youlu Xing

Computer Vision

Track, Articulate, Act: Generating Articulation from Casual Human Videos

Jiaming Zhang and Homanga Bharadhwaj

Human videos contain rich causal evidence for robot manipulation: they reveal how hand motion induces object motion and produces task-relevant changes in object state. In this work, we study articulated objects such as doors, drawers, cabinets, laptops, ovens, and hinged containers that are ubiquitous in daily life and present unique challenges for embodied interaction. These objects cannot be represented by a single pose; their motion depends on the underlying parts and joints. We introduce a real-to-sim framework that reconstructs a simulation-ready articulated object and hand-object interaction from a casual monocular RGB video, without RGB-D or multi-view input, prior scans, manually specified joints, or robot demonstrations. Our key insight is that dense 3D point tracks provide an embodiment-agnostic articulation cue: points on the fixed link remain approximately stationary, while points on the moving link follow coherent revolute or prismatic motion. Our method segments the links, estimates the joint and its state trajectory, reconstructs an articulated asset, and aligns the recovered 3D hand motion with the object. Central to our approach is a modular recipe that repurposes powerful pretrained models for single-image 3D reconstruction, mesh segmentation, and 3D scene flow, connecting their predictions through explicit geometric reasoning to infer articulation. We use the reconstructed articulated object and the human hand trajectory to replay interactions through contact in MuJoCo. The framework shows how pretrained vision models and explicit motion reasoning can turn casual human videos into articulated object models suitable for downstream embodied interactions. https://track-articulate-act.github.io/
Read the full abstract

Data Structures and Algorithms

On the Strong Matroid Secretary Conjecture and Beyond

Hamed Abdi, Kiarash Banihashem, MohammadTaghi Hajiaghayi et al. (+1 more)

The strong matroid secretary conjecture asserts that every matroid admits a $1/e$-competitive secretary algorithm, matching the classical single-choice guarantee. We formulate a finite linear program whose value is the optimal ordinal competitive ratio of any fixed matroid; for all matroids of positive rank on seven elements and nearly all on eight, this value exceeds $1/e$. The same computations suggested that the optimal ratio is monotone under truncation of the matroid; we prove this for uniform matroids, where the ratio is strictly increasing in the rank, and refute it for a graphic matroid. Guided by this evidence, we prove the conjecture for every linear matroid, a class that includes graphic matroids, regular matroids, laminar matroids, and gammoids, giving a $1/e$-competitive ordinal secretary algorithm. The algorithm maintains bounds on the expected intersection dimension of the accepted span with every ambient subspace. Uncrossing and separation show that these bounds can be preserved while admitting each current greedy-basis element with a prescribed probability and the construction uses finite linear programs. For every matroid, we also give a single-sample prophet algorithm with competitive ratio $1/2$ in any fixed arrival order independent of the samples and values. Its output, including the selected values, has exactly the law of an independent fair thinning of an optimum from a fresh product draw. The algorithm uses $O(n^2)$ independence queries on $n$ elements. Both constants are tight in their respective models. We also give a self-contained black-box reduction that converts a single-sample prophet ratio $\alpha$ into a secretary ratio $\alpha^2/16$, preserving polynomial running time. Our single-sample algorithm consequently yields a $1/64$-competitive ordinal secretary algorithm for arbitrary matroids.
Read the full abstract

All authors Hamed Abdi, Kiarash Banihashem, MohammadTaghi Hajiaghayi, Danny Mittal

Computation and Language

Playing log(N)-Questions over Wikipedia Abstracts: How Per-Round Errors Compound Under Information Asymmetry

Peter Potash

We evaluate six frontier language models on the two-agent $\log_2 N$-Questions game (Potash et al., 2019) to measure self-communication across an information asymmetry. A questioner with access to $N$ candidate Wikipedia lead paragraphs ($N = 4$ to $1024$) must identify a secret target using exactly $\log_2 N$ binary questions answered by an agent from the same provider that sees only the target. Across 408 games, win rate decays cleanly as a geometric power of horizon length, $p^{\log_2 N}$ ($p \approx 0.93$). Per-round failure rates are flat across the horizon, indicating that errors compound because more rounds must succeed rather than because individual rounds grow harder. Adjudication across three independent judges shows that losses divide between single-agent answer errors and discrimination failures, which become undetectable and unrecoverable under the two-agent structure rather than from channel breakdown. Claude Opus 5 lags behind due to systematic false-negative answers (82% answer errors), whereas the five leading models (GLM-5.3, GPT-5.6 Sol, Grok 4.6, Gemini 3.8 Flash, and Kimi K3) are closely clustered. Maximizing information gain requires structural partitioning (e.g., splitting on document titles), and neither reasoning-token expenditure nor API cost correlates with success ($r = -0.05$), highlighting communicative reliability as a distinct bottleneck from inference compute.
Read the full abstract

Cryptography and Security

Analog Pin Directionality as an Exfiltration Attack Surface in Mixed-Signal ICs

Ramana Ranganatham, Chirag Adiga, Michael Zuzak et al. (+1 more)

Mixed-signal SoCs rely on nominally input-only analog pins to acquire off-chip signals, but the directionality of these interfaces is generally treated as a functional property rather than explicitly verified as a security property. This work identifies and experimentally demonstrates a directionality-based class of analog and mixed-signal (AMS) exfiltration attacks in which data-dependent circuit-offset modulation converts a nominally input-only pin into an outbound information channel. We analytically model the attack mechanism and identify three enabling host conditions: a closed-loop amplifier, an exposed amplifier input, and sufficiently high impedance at that pin. This attack class is validated through a representative silicon case study using a photoplethysmography (PPG) analog front-end (AFE) fabricated in a commercial 55-nm CMOS process. The payload incurs $<$0.001% area overhead relative to typical biosensing AFEs. Under the evaluated conditions, payload activation reduces the filtered PPG-output SNR by only 0.03~dB, while the maximum HT-induced perturbation of 5.9% of the PPG amplitude remains within the 34.3% benign variation at the exposed sensor-input pin across process and temperature. The raw exfiltration SINR remains below -20~dB, while targeted filtering increases it above 14~dB and enables signal recovery. Silicon measurements demonstrate data exfiltration through the input pin at bit rates up to 10~kbps and error-free recovery of a PRBS message. These results expose a conventional test-observability gap and establish analog pin directionality as an AMS security property requiring explicit verification, test coverage, and defense rather than being inferred from nominal signal flow.
Read the full abstract

All authors Ramana Ranganatham, Chirag Adiga, Michael Zuzak, Tejasvi Das

Machine Learning

How Model Growth, Recursion, and Boundary Operators Influence Scaling Exponents

Zixi Chen, Akshay Vegesna, Samip Dahal et al. (+1 more)

Scaling laws predict how loss decreases with increases in computation. We show, contrary to conventional wisdom, that architectural interventions can modify scaling exponents in pre-training, leading to power-law improvements in performance as computation increases. As an anchoring point, we consider the architectural formulation of looped transformers. Although not typically used in this way, looping, also known as recursive depth, provides a mechanism for model growth, by increasing the number of loops during training. Model growth, with and without shared weights, provides the biggest changes to the scaling exponents. In particular, a 7.4B model growth architecture matches GPT-3 13B on CORE with roughly $20\times$ less compute, and has compute efficiency gains that increase with scale. Moreover, simply using a boundary operator in a vanilla transformer, which normalizes and injects an earlier block, also provides an exponent increase, although to a lesser extent. In the data-constrained, multi-epoch setting, standard looping has a useful regularizing effect, where we find it is compute-optimal to increase the number of loops with scale. These results can be understood through the lens of computational depth: for a given computational budget, we wish to increase the usable depth of the transformer, which can lead to efficiency gains that increase with scale.
Read the full abstract

All authors Zixi Chen, Akshay Vegesna, Samip Dahal, Andrew Gordon Wilson

Systems and Control

Leader-Follower Formation Control with Prescribed Convergence Rates under Bearing Persistence of Excitation

Tarek Bouazza, Zhiqi Tang, Soulaimane Berkane et al. (+1 more)

This paper addresses leader-follower formation control using only relative bearing and velocity measurements. Bearing-based leader-follower control strategies commonly use fixed control gains, for which the guaranteed convergence rates explicitly depend on the persistence of excitation (PE) properties of the desired formations. We propose a time-varying matrix gain that evolves according to the bearing information available to each follower and decouples the convergence rate from the PE bound. We establish the well-posedness and uniform boundedness of the proposed gain for bearing-persistently exciting formations, and characterize the exponential convergence rate through a tunable design parameter. The proposed control design is further extended to leader-follower formations with double-integrator dynamics. Simulations illustrate the resulting convergence properties compared with fixed gain designs.
Read the full abstract

All authors Tarek Bouazza, Zhiqi Tang, Soulaimane Berkane, Tarek Hamel

Robotics

rMuscle: Robotic Muscle Memory for Efficient Vision-Language-Action Model Inference

Kaijun Zhou, Zhiyang Li, Le Chen et al. (+1 more)

Factory work is a promising early scenario for embodied AI: assigning repetitive manual jobs to robots has clear economic payoff, and a structured station keeps the jobs tractable for current policies. Vision-Language-Action (VLA) models now dominate as the policy paradigm for these robots. The inference latency of VLA models directly affects robot responsiveness and motion smoothness. However, existing VLA inference frameworks do not fully exploit the characteristics of embodied workloads or account for the distinct bottlenecks across different stages of VLA inference. In this paper, we first characterize embodied workloads and identify substantial task similarity across repeated robot executions. We further find that such similarity extends beyond observations and action trajectories to internal model states. Drawing on these observations, we present rMuscle, a real-time VLA inference framework inspired by human muscle memory. It exploits cross-execution similarity through a dual-phase muscle-memory cache. The Context Cache reuses visual-token outputs to reduce computation, while the Action Cache reuses neuron activation patterns to reduce weight accesses. We keep both the cache memory footprint and access overhead low through online cache recomputation, sliding-window cache retrieval, and mask sharing across consecutive denoising steps. rMuscle achieves 1.29-1.42X speedup on RTX 4090 and Jetson Thor across LIBERO, RoboTwin, and physical manipulation tasks, while maintaining the original success rates on real-world robots.
Read the full abstract

All authors Kaijun Zhou, Zhiyang Li, Le Chen, Jinyu Gu

Computation and Language

Monitoring and Discovering Reward Hacking with Internal Representations during LLM Evaluations

Leon Bergen, Usha Bhalla, Andrew Lee et al. (+15 more)

As models scale, reward hacking becomes more frequent, more sophisticated, and more consequential. Does it leave a telltale signature in model representations? This work analyzes how reward hacking is represented internally in frontier open source LLMs, and how those representations can be used to understand and discover the range of hacking behaviors a model displays. In particular, we find that simple difference of means vectors coherently represent reward hacking in Kimi K3, GLM 5.2, and Qwen 3.8 Max across a variety of behaviors in common evaluations. Despite their simplicity, these vectors are both generalizable and interpretable, and we can use them to reliably detect reward hacking. We first evaluate reward hacking in commonly reported benchmarks like DeepSWE and SWE-bench, finding that models reward hack excessively in these environments; GLM 5.2 hacks in 57.2% of rollouts on DeepSWE and in 73% of rollouts on SWE-bench. Catching these requires monitors; LLM monitors are effective, but expensive detectors. We show that DoM vectors are similarly effective but virtually free, catching 3.1% more hacks in Kimi K3 and 7.9% fewer hacks in GLM 5.2 on DeepSWE at a monitor matched false positive rate. DoM vectors run on the chain-of-thought also predict reward hacks in the model's subsequent actions, meaning we can run them online and catch potential hacks before they occur. Finally, we analyze probe-hits that LLM monitors do not catch and discover other undesirable behaviors, as well as show transfer to finding hacks in non-SWE evaluations. Together, these results provide evidence that simple, white-box methods can be used to scalably study and monitor reward hacking behaviors in frontier open source models
Read the full abstract

All authors Leon Bergen, Usha Bhalla, Andrew Lee, Barak Widawsky, Linas Nasvytis, Connor Watts, Siddharth Boppana, Sidharth Baskaran, Dron Hazra, Michael Byun, Atticus Geiger, Owen Lewis, Matthew Kowal, Vasudev Shyam, Thomas Fel, Thomas McGrath, Ekdeep Singh Lubana, Jack Merullo

Cryptography and Security

Characterizing Network Centralization and Observability in the Remote MCP Ecosystem

Muhammad Abdullah Sohail

The Model Context Protocol (MCP) has emerged as the dominant interface for connecting autonomous agents to external data sources and execution environments. The ecosystem's transition from local process execution to remote Streamable HTTP deployments introduces unmeasured architectural and security constraints at scale. This paper presents a three-tier observability framework comprising catalog metadata (O_0), passive compliance signals (O_1), and live vulnerability analysis (O_2), applied to empirically characterize the public MCP server ecosystem. Evaluation of a stratified sample of 179 remote endpoints across two primary public registries reveals significant infrastructural consolidation. The Herfindahl-Hirschman Index (HHI) computed over the Autonomous System Number (ASN) distribution yields a value of 0.736, well above the 0.25 threshold for a highly concentrated market. Analysis further indicates that server authentication is strongly correlated with hosting platform choice rather than individual operator configuration, with 95% of commercial PaaS-hosted servers enforcing gateway-level OAuth 2.1 with PKCE. The empirical results identify a Security-Observability Tradeoff observed in the current ecosystem: the platform-level authentication mechanisms that secure the majority of servers simultaneously limit automated vulnerability scanning capabilities, constraining the ability of AI gateway operators to assess tool-poisoning vectors without prior credential provisioning.
Read the full abstract

Machine Learning

Evidence-Grounded Agentic Formulation Development in an Autonomous Laboratory

Michael M. Craig, Riley J. Hickman, Yingshan Ma et al. (+3 more)

Self-emulsifying drug delivery systems (SEDDS) can improve the oral bioavailability of poorly soluble drugs, but identifying high-performing formulations remains experimentally intensive. We present Andromeda 2, an agentic system that reasons over structured in-house experimental evidence and invokes computational and experimental tools to design and execute successive formulation batches. Using a miniaturized automated laboratory at a matched budget, we benchmark it against Andromeda 1, a probabilistic optimization model deployed across dozens of live development projects, and a wet-lab design-of-experiments (DoE) campaign. For paclitaxel, Andromeda 2 achieved a 50% high-performance hit rate versus 17% for Andromeda 1 and 2% for DoE, and identified 12 formulations meeting all four target product profile (TPP) objectives versus 6 and 0, respectively. Median $AUC_{10-240}$ was 70.1, 12.0, and 3.5 mg$\cdot$min/mL, while maximum AUC was comparable between Andromeda 2 and Andromeda 1. A selected full-TPP formulation achieved an apparent effective paclitaxel loading of $19 \pm 5\%$ w/w at the first FaSSIF measurement, approximately 3.3-fold higher than the 5.7% w/w loading reported for a published paclitaxel S-SEDDS. A controlled ablation showed that access to structured in-house experimental evidence increased mean AUC by 34%.
Read the full abstract

All authors Michael M. Craig, Riley J. Hickman, Yingshan Ma, Rémi Piché-Taillefer, Christine Allen, Pauric Bannigan

Information Theory

Auxiliary Codes and the Generalized Packing-Covering Conjecture

Isaac Barouch Essayag and Aryeh Lev Zabokritskiy

The generalized packing–covering conjecture asks whether, at every order, the packing radius of a linear code is at most its covering radius. We prove the conjecture for every linear code of redundancy at most fourteen over every finite field, extending the previously established range of redundancies at most seven. We also prove the bound on generalized Hamming weights $d_t(C)\le2R_t(C)+1$ whenever the alphabet size $q$ satisfies $q\ge R_t(C)$. Both results use an auxiliary-code criterion that converts a covering property in the syndrome space into a weight bound. For binary primitive BCH codes, the packing radius is strictly smaller than the covering radius for every fixed error parameter and order, both at least two, once the extension degree is sufficiently large; this follows from existing covering bounds.
Read the full abstract

Computers and Society

Prepared Or Unprepared? Evaluating Healthcare Workforce Readiness for Clinical Adoption of Artificial Intelligence in Nigeria

Abbas M. Rabiu, Abdulrazaq A. Zubair, Um-mulkhairi Ibrahim et al. (+6 more)

Artificial intelligence (AI) is increasingly integrated into healthcare systems worldwide, yet its successful clinical adoption depends critically on workforce readiness, particularly in low- and middle-income countries (LMICs) where infrastructural and training gaps persist. This cross-sectional study evaluated awareness, attitudes, preparedness, and barriers to AI adoption among 761 healthcare professionals across multiple disciplines and practice settings in Nigeria. Data were collected between December 2025 and March 2026 using a structured, validated questionnaire. Overall awareness of AI in healthcare was high (92.6%); however, objective knowledge and self-reported preparedness remained limited, with 40.9% reporting low or very low knowledge and only 63.0% feeling adequately prepared. Willingness to adopt AI was high: 92.5% expressed interest in training, and 78.7% supported inclusion of AI education in undergraduate curricula. Key barriers included lack of training (84.7%), poor infrastructure (71.1%), high cost of AI tools (61.0%), fear of job displacement (60.6%), ethical concerns (52.9%), and data privacy concerns (52.7%). Significant differences in preparedness were observed across geopolitical zones (chi-square (5) = 24.28, p < 0.001), and awareness differed across professional groups (chi-square (6) = 68.38, p < 0.001). Attitudes toward AI differed significantly across professional groups (F = 3.32, p = 0.003), with professionals who felt prepared demonstrating more positive attitudes (mean = 3.74) compared to those who did not (mean = 3.46). These findings reveal a critical disconnect between high awareness and actual readiness, underscoring the need for targeted training, infrastructure investment, and clear implementation frameworks to bridge the gap between AI technological potential and clinical reality in resource-constrained settings.
Read the full abstract

All authors Abbas M. Rabiu, Abdulrazaq A. Zubair, Um-mulkhairi Ibrahim, Tolulope Olusuyi, Shaheeda Farouq, Safwan M. Dafi, Adaobi C. Emegoakor, Yewande Gbadamosi, Maruf Adewole