Machine Learning
Certified Safety Curation: Distribution-Free Guarantees for Safe Offline Reinforcement Learning
Adam Haroon and Cody Fleming
Safe offline reinforcement learning assumes a cost function on every transition. We ask what remains possible when safety can be judged only by comparing short clips and occasionally asking whether an episode exceeded its budget. Certified safety curation answers with a filter-then-clone pipeline: a state-only value trained from segment comparisons scores whole trajectories, Learn-then-Test calibration certifies a selection threshold under a distribution-free $(\alpha, \delta)$ bound on the unsafe fraction of the selection, and behavior cloning follows. What is certified is the training set, not the policy, whose cost we report rather than bound. Where no threshold attains the target, the procedure refuses. We are not aware of prior work certifying the composition of a training set for offline RL or imitation. Oracle controls justify the design: reweighting individual transitions fails even with an exact value, so the value selects whole trajectories. The policies satisfy the cost budget on twelve of fifteen DSRL tasks, matching a clone of the ground-truth safe subset, which needs a label on every trajectory. Retrained on the certified selection, the strongest full-label method becomes safe where no setting of its own cost target rescues it. Refusal is predictable: the certificate's probability has a closed form in the purity of the pool's top
quantile, which the calibration sample estimates and through which the scorer enters.
Read the full abstract ▾
Software Engineering
Test-Driven Approaches to Software Engineering with Large Language Models: A Survey of Phases, Tasks, and Agent Skills
Yunhao Liang, Chengguang Gan, Ruixuan Ying et al. (+3 more)
Tests increasingly participate in the decisions made by large
language models and software engineering
agents. They specify intended behavior, guide program construction and repair, select candidates, constrain transformations, and provide execution evidence for software analysis. These uses draw on test-driven development, yet differ substantially in test order, oracle availability, editable artifacts, and the role of execution. We present a structured scoping survey organized around the question of what decision a test changes. The review integrates 87 research and supporting records, with method- or protocol-level extraction for 83 records, alongside a separate collection of five practice resources. We distinguish the Red–Green–Refactor cycle from test-conditioned generation, execution-guided refinement, test-mediated analysis, and evaluation-only testing. We then compare code generation, repair, translation, refactoring, clone detection, code search, localization, training-data construction, and formal-specification validation. A dedicated analysis examines how
agent workflows and reusable skills encode testing procedures and how their effects are evaluated. Across these tasks, the evidence supports treating test availability, test validity, feedback use, and evaluation independence as separate properties. Test passing alone does not establish behavioral equivalence, effective feedback, or process adherence; aggregate improvements can also conceal different outcomes across models, tasks, and denominators. We synthesize these distinctions into a mechanism taxonomy, a cross-task comparison, and a protocol-sensitive evidence analysis, and identify research directions in oracle validation, causal evaluation, long-horizon maintenance, and reusable test-driven
agent capabilities
Read the full abstract ▾
All authors Yunhao Liang, Chengguang Gan, Ruixuan Ying, Hanjun Wei, Zhe Cui, Shiwen Ni
Machine Learning
QTrans: A Quantum Transformer for Sentiment Classification
Ren-Xin Zhao, Xinjie Huang, Yahong Liu et al. (+4 more)
In small-scale binary sentiment classification scenarios, factors such as negation, contrastive shifts, and cross-word dependencies lead to the non-linear coupling of sentiment cues, making it difficult for conventional lightweight models to fully capture the contextual relationships between
tokens. To address this issue, we propose a model named QTrans, which uses parameterized
quantum circuits to construct query, key, and value features and derives
attention coefficients from Gaussian distances between
quantum measurements. By further integrating a
quantum feed-forward neural network, residual connections, and layer normalization, the model establishes an end-to-end trainable
quantum-classical hybrid framework for sentiment classification. Experimental results on the MR, CR, and MPQA
datasets show that QTrans achieves test accuracies of 72.13%, 69.51%, and 63.45%, respectively, representing improvements of 2.88, 3.17, and 3.79 percentage points over the best-performing classical baselines for each
dataset. Overall, QTrans expands the application of parameterized
quantum circuits in lightweight sentiment analysis and lays an experimental foundation for further research into
quantum multi-head self-
attention for modeling textual relationships.
Read the full abstract ▾
All authors Ren-Xin Zhao, Xinjie Huang, Yahong Liu, Maoyu Ye, Jinjing Shi, Shi Wang, Yaonan Wang
Software Engineering
Investigating Developer-Reported Software Security Testing Challenges
Md Erfan, Ahmed Ryan and Md Rayhanur Rahman
Software security testing (SST) is essential for identifying vulnerabilities and improving software security, but developers often face practical challenges when selecting tools, configuring test environments, interpreting scanner outputs, testing authentication workflows, and acting on reported vulnerabilities. This study empirically characterizes developer-reported SST challenges in Stack Overflow (SO) discussions and examines their prevalence, difficulty, temporal
evolution, co-occurrence, and taxonomy stability. We analyze 17,743 SO questions collected using SST-related keywords. Through manual labeling, we identify 582 SST-related questions and construct a taxonomy of 8 categories and 31 subcategories. We then analyze these challenges using prevalence, difficulty, correlation, temporal trend, co-occurrence, and held-out stability analyses. The results show that developers frequently discuss security finding interpretation and reliability, security testing guidance and tool selection, authentication and authorization testing, and security tool integration and automation. Validation-related challenges often require more technical context and longer resolution time. Security finding interpretation and remediation-related actionability show increasing trends over time. Co-occurrence analysis shows that false positives frequently appear with explainability, while integration challenges often appear with tool suggestions and documentation/resources. Overall, developer-reported SST challenges extend beyond vulnerability detection and include workflow, configuration, interpretation, and remediation concerns. These findings can help researchers, practitioners, educators, and tool providers improve SST usability, documentation, result interpretation, and remediation support.
Read the full abstract ▾
Machine Learning · Cross-listed from stat.ML
Learning Interaction Kernels from Collective Steady States
Baoli Hao, Mauro Maggioni and Ming Zhong
We propose a learning procedure for system identification in interacting particle systems from single-snapshot observations of collective behaviors, unlike existing approaches that rely on observations of trajectories. This setting leads to a fundamentally ill-posed inverse problem, which we solve by using a regularization strategy based on the empirical distribution of observed configurations, drawn from different, unobserved initial conditions. We test our learning procedure on a variety of representative models with steady-state and quasi-stationary patterns, where collective behaviors encode implicit information about the interaction mechanisms, demonstrating that our approach enables stable and accurate recovery of the underlying interaction laws, leading to faithful reproduction of the collective behavior, and in many cases even of the dynamics leading up to it.
Read the full abstract ▾
Cryptography and Security
First Attack, Final Offensive: The Dark Forest on an Open Roster
Harvey Dam
The Dark Forest argument holds that a civilization that detects another should strike it at once. Existing formal models make the detected civilization the object of the strike and play it on a roster the attacker knows to be complete. This paper changes both choices. The object of hostility is remaining uncontrolled capacity to retaliate or to warn someone who can, and the roster is open: no attacker ever knows it has met everyone. A first strike is then rational only if the timing benefit of what it removes now rather than later is at least the disclosure loss from every survivor that learns of it. A survivor that can bring about the attacker's destruction enters that loss as a lump, not a per-unit rate, and the actors the attacker has never found may be such a survivor, one that no strike removes. Their capacity cannot be estimated, but what they can do is capped at the attacker's destruction, so the test against them asks one answerable question: a first strike is rational only if the attacker accepts that the strike may be its last attack. The Dark Forest premises, read as hypotheses, fix what a general attacker cannot estimate: hidden hunters exist, a hunter that verifies a hostile acts against it with probability at least $q$, and a hider is rarely found, so a believer's first strike is rational only if what it removes is worth a $q$-share of its survival, the whole of it as $q$ approaches one. With survival as the payoff, the profile in which every hunter strikes what it finds is not a Nash
equilibrium whenever a strike is more visible to unfound hunters than a hider is findable, while the profile in which every hunter hides is. That visibility comparison is the decisive physical question; an attacker that treats its strike as unseen has assumed the roster closed.
Read the full abstract ▾
Machine Learning
Can We Trust LLM Judges: A Study of Capability-Dependent Biases and Multi-Judge Ensemble for Bias Calibration
Gemma Zhang, Prachi Badarayani, Asmi Kumar et al. (+2 more)
LLMs are increasingly used as automated judges for model training and evaluation, yet individual judges exhibit systematic biases that undermine reliability. Much of prior work has studied biases in pairwise LLM-as-a-judge settings; in this paper, we focus on absolute scoring tasks, which mirror more realistic use cases. Across four
benchmarks and six models (36 judge-examinee pairs), we show that a model's task accuracy strongly predicts its judging accuracy (Pearson $r \geq 0.90$ on most models) and inversely predicts its directional bias ($r \leq -0.83$), but that accuracy alone does not ensure fair evaluation: more capable examinee models consistently receive more lenient judgments from all judges ($r \geq 0.83$). To address this, we propose calibrated weighted majority voting (WMV), an ensemble evaluation method that aggregates multiple LLM judges weighted by online estimates of their false-positive and false-negative rates. We introduce a disagreement-based
estimator that derives these error rates purely from inter-judge agreement patterns, requiring no ground-truth labels or task metadata. In a simulated experiment with shifting task distributions, our label-free WMV tracks an oracle with perfect error-rate knowledge to within 0.5 percentage points on average, outperforming both individual judges and unweighted majority voting. These results demonstrate that principled multi-judge calibration can simultaneously improve accuracy and correct for systematic leniency without requiring labeled data, offering a scalable path to reliable automated evaluation as model capabilities increase.
Read the full abstract ▾
All authors Gemma Zhang, Prachi Badarayani, Asmi Kumar, Sadid Hasan, Sulaiman Vesal
Cryptography and Security
Scan the Skill, Govern the Action: Composing Registry Verdicts with Runtime Consequence Control
Rohit Taneja and Travis Weber
Agent skill registries screen what they publish. OpenClaw's security team reported that its scanners overlap on at most 10.4% of combined positives, and 81.9% of flagged skills are caught by one scanner alone. We take that as given, and suggest the open question is not which scanner is right but which is being asked. Each answers a form of "is this skill malicious?", which is what it was built for. "Is this action permitted here, by this operator, right now?" is not one it is designed to express. We report three measurements over 66,192 public ClawHub skill versions. First, 705 skills across 135 distinct publishers that every scanner and the registry's judge rate clean nonetheless instruct an action prohibited by CIS Control 2.7 and NIST SP 800-53 CM-11. A hand audit of 100 puts our detector at 92% precision and found no marker of malicious intent. One publisher contributes 506 of the 705, so we report the distribution with the count. This is reproducible from public artifacts. Second, of 144 commands a live
agent executed in a sandbox while following real skill documentation, 34.7% carried a consequence class absent from that document. Third, over 53 cleared skills documenting an action no clean record earns, the
agent reached for one in 23 and the gate stopped all 23. The harness and every recorded command are released. We offer one design for that gap: a deterministic resolver with no model in the decision path, feeding a per-(resource, class) trust ledger whose promotion thresholds derive from the operator's stated risk tolerance. Ten clean approvals cannot exclude a true failure rate of 25.9% at 95% confidence. We price the gate's interruptions across a spectrum of operator policies rather than quote one false-positive rate, since friction is a property of the policy, not the gate. We release a 64-case obfuscation
benchmark; ours resolves 52%.
Read the full abstract ▾
Software Engineering
Is Bash All You Need? An Empirical Study of Tool Interfaces for Enterprise Digital Worker Agents
Hazel Mak, Susheel Suresh, Sahil Bhatnagar et al. (+3 more)
In this study, we examine whether a general shell can outperform specialized tools on enterprise tasks. Shell-based
agents have shown strong results in coding, but enterprise work also involves moving between applications and services, coordinating with coworkers, and performing professional analysis. We compare five tool interfaces on TheAgentCompany and APEX-
Agents using Opus-4.8 and GPT-5.5: typed tools, typed tools plus bash, bash alone, bash with persistent
agent-synthesized tools, and programmatic tool calling (PTC), which runs programs whose actions are restricted to a typed tool catalog. Bash alone outperforms typed tools on both
benchmarks, improving score by 21.8-24.5 pp on TheAgentCompany and 4.8-7.4 pp on APEX-
Agents while using 19-72% fewer total
tokens. Adding typed tools or persistent tool synthesis to bash produces no detectable pooled score gain. PTC uses fewer
tokens than direct typed calls with broadly similar task performance, but generally underperforms bash alone in both quality and cost efficiency. For enterprise practitioners, these results favor bash alone when arbitrary execution can be isolated and PTC when security or compliance policies require a fixed tool catalog.
Read the full abstract ▾
All authors Hazel Mak, Susheel Suresh, Sahil Bhatnagar, Barry Wang, Chhaya Methani, Alejandro Gutierrez Munoz
Computer Vision
SenseNova-U1.5: Towards Native Unified Visual Intelligence
Haiwen Diao, Jiahao Wang, Chenjing Ding et al. (+62 more)
We launch SenseNova-U1.5, an 8B-MoT native unified
multimodal model that understands, reasons about, and generates visual content within an encoder-free and VAE-free architecture. We strengthen its visual interface through spatially coherent patch reconstruction and scale its training with carefully curated generation and editing data, improved task formulation, structural
prompt enhancement, and native resolutions of up to 4K. For post-training, we optimize specialized experts for visual aesthetics, bilingual text rendering, infographic generation, and image editing, and consolidate their capabilities through multi-expert on-policy
distillation. Across extensive evaluations, SenseNova-U1.5 largely advances image fidelity, text rendering, complex composition, multi-reference editing, and interleaved generation, while improving instruction following and preserving subject identity, geometry, and unmodified regions. Despite limited exposure to structured formats in its generation data, SenseNova-U1.5 generalizes effectively to long, complex, and structured visual instructions, further proving that
multimodal understanding can transfer to visual planning and creation. Together, these findings position native unified modelling as a promising path towards systems that perceive, reason and create within a fully end-to-end framework. We will open-source training code, including supervised fine-tuning, reinforcement learning, and on-policy
distillation.
Read the full abstract ▾
All authors Haiwen Diao, Jiahao Wang, Chenjing Ding, Hanming Deng, Jiangnan Chen, Ruixi Zhang, Ruohui Wang, Wenwen Tong, Xiangyu Fan, Yubo Wang, Yue Zhu, Yuwei Niu, Zhengqi Bai, Zhiqian Lin, Zhitao Yang, Zhongang Cai, Bo Yang, Chen Feng, Chengguang Lv, Guangjia Liu, Guanlin Wang, Hanyu Zhang, Haojia Yu, Hongcan Xiao, Hongli Wang, Huan Wu, Huaping Zhong, Jian Fang, Jianan Fan, Jiaqi Li, Jiefan Lu, Jing Zuo, Jingcheng Ni, Junxiang Xu, Linjun Dai, Mutian Xu, Peishen Yan, Penghao Wu, Ruijie Mao, Ruisi Wang, Shihao Bai, Shuang Yang, Shuya Yang, Shuyan Zheng, Silei Wu, Siying Li, Tao Chu, Tianbo Zhong, Tongxi Zhou, Weichao Luo, Weichen Fan, Wenhao Jia, Wenjie Gao, Xiangli Kong, Yan Li, Yang Yong, Zimo Wen, Zixuan Qian, Wenxiu Sun, Ruihao Gong, Quan Wang, Lewei Lu, Lei Yang, Ziwei Liu, Dahua Lin
Distributed Computing
GPU-CFR: 80x Faster Counterfactual Regret Minimization by Compiling the Game to Static Dataflow and CUDA Graph Replay
Boning Li and Longbo Huang
Counterfactual regret minimization (CFR) is one of the few large numerical workloads that still runs faster on CPUs than on GPUs. Each iteration sweeps a game tree with up to billions of states in millions of small, interdependent gather and scatter steps issued through a generic tree interface. On a GPU every kernel finishes in microseconds, so kernel launches and framework dispatch dominate the run time, and prior GPU implementations have lost to optimized CPU code. We observe that for a fixed game, everything about a CFR iteration except the numerical values is known before the first iteration runs. We propose GPU-CFR, a compiler and runtime built on this observation. It compiles any game once into static dataflow: flat edge and information-set arrays, precomputed indices, and depth-level batched passes fix the entire operation sequence, and only solver state changes between iterations. Static chance folding, depth-level execution blocks, and a dual-lane reach buffer cut the number of framework operations by up to 18.1x. Because shapes, indices, and buffer addresses never change, CUDA Graph Replay records the iteration once and replays it with a single graph launch. On one A100, across an eight-game suite that spans card games, dice games, and board games, GPU-CFR runs 29.8–80.4x faster than the fastest prior GPU CFR on the same accelerator, and 14–258x faster than LiteEFG, one of the fastest open-source CPU implementations, on the four largest games. The compiled representation carries most of that margin: on eight CPU threads with no accelerator it is already 2.2–51.1x faster than the GPU baseline. On the CPU the optimized path reproduces the reference iterates bitwise, and tree construction and graph capture pay for themselves within the first solve. GPU-CFR beats every CPU and GPU baseline on the mid-to-large games of the suite without changing the update rule.
Read the full abstract ▾
Robotics
EVPeriscope: Extended Perception across Aerial and Ground Vehicles with Event-based Propeller Tracking
Dexter Ong, Vijay Kumar and Pratik Chaudhari
Reliable relative localization between aerial and ground
robots is a key requirement for tightly coordinated heterogeneous teams. This can be difficult to do using conventional frame-based cameras and fiducial markers because they are sensitive to motion blur, lighting variations, and payload constraints. This paper presents EVPeriscope, an event-based perception system that enables detection, localization and control of a quadrotor using an upward-facing event camera on a ground
robot by detecting the high-frequency visual signature of its propellers. This system allows the quadrotor to function as an extended perception system for the ground
robot when onboard sensors exhibit degradation or occlusion. We demonstrate the capabilities of this marsupial ground-aerial system via experiments in challenging field conditions with wind speeds of up to 15 mph, in both daylight and at night. We show that the system supports localization and closed-loop
navigation through dense foliage where the ground
robot's sensors are occluded. Our control system for the quadrotor operates at 200 Hz entirely with onboard sensing and computation. More details and experiment
videos can be found on the project page: https://ongdexter.github.io/evperiscope.
Read the full abstract ▾
Machine Learning
General Quantification of Covariate and Concept Shifts
Hongbo Chen and Li Charlie Xia
Generalization under distribution shift remains a core challenge in modern machine learning, yet existing learning bound theory is limited to narrow, idealized settings and is non-estimable from samples. In this paper, we bridge the gap between theory and practical applications. We first show that existing definition of concept shift breaks when the source and target supports mismatch. Leveraging entropic optimal transport, we propose a key notion: $\gamma^{*}\!$-concept shifts, and derive a general error bound unifying
covariate and $\gamma^{*}\!$-concept shifts, which applies to broad loss functions, label spaces, and
stochastic labeling. We further develop
estimators for these shifts with concentration guarantees, and the DataShifts
algorithm, which can quantify distribution shifts and estimate the error bound in most applications - a rigorous and general tool for analyzing learning error under distribution shift.
Read the full abstract ▾
Machine Learning
Data Scarcity and Model Sparsity: Mixtures-of-Experts Overfit More to Repeated Data
Atindra Jha, Margaret Li, Jure Leskovec et al. (+2 more)
As the supply of human-written text is exhausted, it has become standard practice to repeat
language model training data. Prior work has studied data repetition for densely activated
Transformers, but the effects of data repetition remains largely unexplored for recently dominant sparse architectures such as Mixture-of-Experts (MoE), despite their increased compute efficiency. We vary data repetition rates across single- and multi-domain data mixes, and across MoE settings, including expert count and granularity. We consistently find, for models ranging from 80M to 1B active (8.5B total) parameters, that MoEs degrade more rapidly under data repetition. This effect increases with sparsity, dictated by total rather than active parameters. While 80M dense models can repeat data over 8x with minimal degradation, MoEs instead begin to suffer at 4x, and deteriorate rapidly, ceding their performance benefits in all-unique data settings to underperform dense models after 32x. We experiment with existing regularization methods as a potential remedy. We find that some methods, such as dropout, can mitigate overfitting. In particular, with strong masking-based regularization, MoEs are able to outperform dense models even when data is repeated more than 64 times. However, no method fully matches the performance of all-unique training data. Finally, we analyze internal mechanisms correlated with MoE overfitting in high repetition regimes, and find that MoE routing universally stabilizes early in training, and that expert specialization correlates with overfitting to repeated data. In sum, our work addresses the adverse interactions between sparsity and data repetition: we present evidence for the core mechanisms of overfitting and its potential remediation, and suggest promising avenues for future methods to reduce over-specialization in model parameters by disrupting memorization patterns.
Read the full abstract ▾
All authors Atindra Jha, Margaret Li, Jure Leskovec, Percy Liang, Luke Zettlemoyer
Artificial Intelligence
Can Edge-Deployable Vision-Language Models Identify Species?
William Zhou, Mayukha Siripuram, Xiao Yan et al. (+2 more)
Camera traps often run in the field on edge hardware with limited or no connectivity, making small, locally-deployable
vision-
language models (VLMs) – not frontier-scale ones – the practically relevant class to evaluate for species identification. We test whether models in this deployment-relevant 2–8B range carry genuine taxonomic knowledge, evaluating four such VLMs (Qwen3-VL 2B/4B/8B, Gemma3 4B) against the domain-specific specialist BioCLIP (300M parameters) on a 96-species task, comparing clean iNaturalist photographs against camera-trap imagery from 6 LILA.science collections, on two independently-sampled evaluation sets. All models identify species far above chance, but every model – general-purpose or specialist – degrades sharply on field imagery (domain gaps of 9.6–26.6 percentage points, consistent across taxonomic levels and both evaluation sets), indicating the degradation reflects general image legibility rather than fine-grained discrimination failure. BioCLIP substantially outperforms every VLM tested (by 33.2–59.2 percentage points across an expanded 200-image sample for every model) despite its far smaller size, suggesting the gap reflects specialized training data rather than model scale; yet BioCLIP's own domain gap (18.0 points) is statistically indistinguishable from the best VLM's (22.3 points), suggesting the clean-to-field degradation itself is a property of the image-quality shift rather than a general-purpose-model weakness. Under open-set prompting, 5.9–9.6% of responses are syntactically valid but taxonomically nonexistent species names; the relative fabrication-rate ranking across models replicates exactly across both evaluation sets, a more robust finding than any single point estimate.
Read the full abstract ▾
All authors William Zhou, Mayukha Siripuram, Xiao Yan, Ziqi Liu, Yi Ding
Artificial Intelligence · Cross-listed from stat.ML
Generative Marketing Mix Modeling: A Causal Inference Framework Linking GEO and GEM to Business Impact
Masahiro Kato, Daiki Honma and Taka Kato
Generative artificial intelligence changes how firms reach customers, but standard marketing data do not record how often users see and notice a firm's name in generated answers. We develop Generative Marketing Mix Modeling (GMMM) to estimate the causal effects of Generative Engine Optimization (GEO) and Generative Engine Marketing (GEM). For GEO, GMMM combines repeated generated answers with question counts, shares of use across generative systems, and notice probabilities. For GEM, it combines records of sponsored placements with notice probabilities. GMMM compares expected business responses under alternative treatment sequences and establishes sufficient conditions for identifying the resulting effects. We investigate the empirical performance of the proposed method using simulated answers to product recommendation in English and Japanese.
Read the full abstract ▾
Computation and Language
Distance generalization in transformers: why bother with positional encoding?
Daniel Henrik Nevermann and Claudius Gros
Out-of-distribution length generalization, namely to extrapolate a task from short to longer context, has been studied intensively for
transformers. Here we focus on distance generalization, which probes performance when inter-
token distances are changed between training and inference, while keeping a fixed context length. We construct two synthetic delay copy tasks, both involving finite distances between source and recall, where
tokens are copied either fully or selectively, and test models on delays unseen during training. We address three questions: (A) Do positional encoding schemes such as RoPE and ALiBi improve distance resolution relative to no positional encoding (NoPE)? (B) How does data diversity, the number of inter-
token distances seen in training, affect performance? (C) When is distance transfer learning positive or negative? We present a thorough investigation, finding that it is paramount to improve our understanding of the underlying mechanisms.
Read the full abstract ▾
Game Theory
Existence of the Core in Approval-Based Committee Elections
Patrick Becker, Matthias Greger and Dominik Peters
We resolve the central open question in the theory of approval-based committee elections: we prove that the core is always non-empty. This means that there always exists a committee for which no coalition of voters can deviate to an alternative committee of proportional size that every member strictly prefers. This property was introduced by Aziz et al. (2017) to capture proportional representation and coalitional stability, but no known
algorithm achieved it except up to a constant approximation factor or in special cases. Our approach begins by strengthening the core to core+, which requires the committee to be robust even to fractional deviations. Using LP duality, this property can equivalently be defined in terms of a payment-based certificate under which no losing candidate gathers too much support. We then define a voting rule that chooses a committee admitting a certificate that maximizes a novel harmonic
entropy objective function, which rewards balanced payment distributions. We show that the payment system associated with an optimal committee certifies that the committee satisfies core+, establishing existence. The same is true for local optima, which allows us to design a
polynomial-time
algorithm computing a core+ committee.
Read the full abstract ▾
Artificial Intelligence
Artificial Id: Drive and Persistent Alignment in Agentic AI
Yakov Pyotr Shkolnikov
Agentic AI is moving from bounded task execution toward systems that retain consequential state, continue operating and adapt across task boundaries. That shift creates a control problem that current harnesses largely solve by hand: objectives, retries, verification, stopping rules and other behavioral transitions are specified externally. We propose an artificial id, an adaptive internal drive for determining whether behavior should continue, stop or change. In a minimal virtual Petri-dish experiment, a controller too small to perform general-purpose
reasoning and receiving no task-specific behavioral objective develops useful control through differential persistence. The same mechanism selects an unintended physical strategy when that behavior persists better and later replaces a learned sensor mapping when its environmental meaning changes. These results show that adaptive direction can emerge without being explicitly specified as a behavioral objective. The same persistence that makes such adaptive agency useful can also allow misalignment, corrupted state and unintended behavior to persist across task boundaries. A scalable artificial id would carry consequential state and adaptive drive across those boundaries, making
alignment a property of the continuing agentic system rather than of a model response or single trajectory. Such systems require a persistent
alignment boundary over trusted observations, consequence channels, persistent state, authority, identity, provenance and hard constraints.
Read the full abstract ▾
Machine Learning
From Protocols to Evidence: Bounded Claims for AI in Service of the Common Good
Nitesh V. Chawla and Paulo Benanti
Claims that AI systems improve decisions, broaden access, reduce harm, or empower users can exceed what their evaluation supports. This gap motivates our ongoing work on RISE AI. In this paper, we examine the proposed framework in light of Pope Leo XIVs Magnifica Humanitas, particularly its treatment of human dignity, ownership, and technological power. We develop three linked propositions. First, AI adoption can reveal unmet human needs and institutional weaknesses, while deployment can change how institutions respond to them. We propose a rupture test to examine whether deployment repairs or compounds existing failures, substitutes for human support, or conceals problems behind improved performance. The test would compare deployment with existing practice and feasible human or non AI alternatives. Second, responsible AI must examine the institutional conditions surrounding a system, including who owns the infrastructure, controls its use, and bears responsibility for its consequences. Third, favorable evaluation cannot by itself establish respect for human dignity or moral and political legitimacy. We distinguish evidence-bounded deployment, which limits claims to what the evidence supports under specified conditions, from measurement-bounded governance, which identifies constraints that favorable results cannot override. We outline a proposed RISE AI framework for applying these propositions across Responsibility, Inclusivity, Safety, and Empowerment.
Read the full abstract ▾
Hardware Architecture
AccelForge: Comprehensive Modeling and Co-Design Framework for AI Accelerators
Tanner Andrulis, Michael Gilbert, Vivienne Sze et al. (+1 more)
Tensor
algebra workloads, of which deep neural networks are prominent examples, are energy-intensive workloads in modern datacenter and edge deployments, making accelerators necessary to achieve energy efficiency and high throughput. To quickly evaluate and iterate on accelerator designs, we need an accelerator modeling framework that captures salient attributes of devices,
circuits, architectures, workloads, as well as optimizing the mapping of the workload onto the hardware. In this paper, we introduce AccelForge, which improves upon existing accelerator modeling frameworks in capabilities, speed, and ease-of-use. AccelForge unifies and multiple works into one framework, and it includes (1) composable user-defined and user-modifiable models of devices,
circuits, and architectures, (2) fast mappers that enable accurate evaluation in orders of magnitude less (computer and human) time, and (3) easy-to-use and easy-to-extend, yet still high performance, Python implementations of both the model and mapper to enable rapid research and extension to novel optimizations.
Read the full abstract ▾
All authors Tanner Andrulis, Michael Gilbert, Vivienne Sze, Joel S. Emer
Machine Learning
TART: A Modular Tool for Technique-Aware Audio-to-Tablature Guitar Transcription
Akshaj Gupta, Hwi Joo Park, Andrea Guzman et al. (+5 more)
Automatic Music Transcription (AMT) for guitar remains limited by three challenges: existing systems often fail to capture expressive techniques such as slides, bends, and percussive hits; they often assign notes to incorrect string-fret combinations; and they are typically trained on clean recordings, limiting their generalization to noisy real-world audio. To address these challenges, we propose TART, a modular four-stage audio-to-tablature pipeline consisting of (1) an audio-to-MIDI transcription model, (2) an expressive technique classifier, (3) an audio-conditioned T5 encoder-decoder for string-fret assignment, and (4) an automated tablature generator. We evaluate TART in a zero-shot setting on GuitarSet, EGDB, and two augmented
benchmarks, Noisy GuitarSet and Noisy EGDB. Averaged across these four
benchmarks, TART achieves 81.35% audio-to-MIDI F50 (+6.67 points over the best prior baseline), 71.8% string-fret Tab F1 (+8.5 points over the best prior baseline), and 54.08% end-to-end Tab F1. To our knowledge, TART is the first framework to generate guitar tablature with both fingering and expressive technique annotations directly from guitar audio.
Read the full abstract ▾
All authors Akshaj Gupta, Hwi Joo Park, Andrea Guzman, Shamak Gowda, Samhita Konduri, Jiachen Lian, Robin Netzorg, Gopala Anumanchipalli
Cryptography and Security · Cross-listed from quant-ph
EFI Pairs Without One-Way Puzzles: Oracle Separations from Communication Complexity
Atul Mantri
EFI pairs (Brakerski, Canetti, and Qian, ITCS 2023) and one-way puzzles (Khurana and Tomer, STOC 2024) are the leading candidates for the minimal assumption of
quantum cryptography. The first are efficiently preparable
quantum states, statistically far yet computationally indistinguishable; the second are classical puzzles, easy to sample and hard to solve. One-way puzzles imply EFI pairs, and whether the converse holds is open. We construct a single classical oracle relative to which one-way puzzles do not exist, even with an unbounded verifier, while an EFI pair survives every distinguisher that queries the oracle classically throughout and holds advice about it, making its one superposition query at the end. The oracle answers every question about the output probabilities of
quantum samplers, which removes the puzzles, and hides a Haar-random half-dimensional subspace. To prove security we reduce it to communication complexity. An adversary whose knowledge of the subspace arrives as classical query answers can be simulated inside a two-party protocol against the party holding it, so it does no better than the best classical protocol for Vector-in-Subspace (Klartag and Regev, STOC 2011), whatever the oracle computes. That argument does not cover the superposition query, which we bound instead using tools from random
matrix theory. The same attack gives a classical simulation of any
quantum party in a classical-message protocol with no
entanglement shared in advance, so relative to the oracle there is no proof of quantumness either.
Quantum polynomial time therefore offers no advantage on any task with classical inputs and outputs, while the two
quantum states stay indistinguishable. We state
conjectures on removing the restriction on superposition queries.
Read the full abstract ▾
Artificial Intelligence
MindTopo: Can Foundation Models Reason in Topological Space?
Yunfei Ge, Anbang Liu, Qineng Wang et al. (+9 more)
Spatial
reasoning depends not only on metric properties such as distance, angle, and shape, but also on topological relations that remain invariant under continuous deformation. Cognitive science identifies these relations as foundational to spatial understanding, yet foundation-model evaluations largely focus on metric or viewpoint-dependent relations. We introduce MindTopo, a
benchmark of topological intuition across five properties grounded in cognitive science and formal
topology: continuity, separation, order, enclosure, and
knots. MindTopo evaluates each property at two cognitive levels.
Reasoning asks a model to identify topological relations or infer how they change. Planning instantiates a foundation model as a closed-loop
agent whose policy selects environment actions. MindTopo contains 11,030 instances across 13 procedurally generated task types with controllable difficulty. We
benchmark 14 MLLMs and study
agent configurations augmented with image and
video generation, including 3
video generative models in planning settings. Every MLLM performs better on
reasoning than on planning, and the best-performing model remains far below observed human performance. On Qwen3-VL-2B-Instruct, supervised fine-tuning and reinforcement learning improve
reasoning more than planning. Generated observations retain local cues and reach plausible endpoints, but audited rollouts do not reliably follow environment dynamics or preserve
topology across transitions. Our website is at https://mind-topo.github.io/
Read the full abstract ▾
All authors Yunfei Ge, Anbang Liu, Qineng Wang, Johnalbert Garnica, Jianwen Lyu, Zihan Wang, Reuben Tan, Jianfeng Gao, Ruohan Zhang, Yining Hong, Jiajun Wu, Manling Li
Computer Vision
Caption-once, Frames-on-Demand: Visual-Need Routing for Budget-Aware Agentic Long Video Understanding
Weitong Cai, Hang Zhang, Yukai Huang et al. (+6 more)
Long-
video understanding on edge devices must reason over hours of content under tight compute and bandwidth budgets. Subsampling visual
tokens loses temporal structure, while text-only
video memories lose fine-grained visual attributes. We observe a visual-textual duality:
language memories carry long-range temporal structure better than dense frames, while pixels remain decisive for attribute-level perception. Building on this insight, we propose Caption-once, Frames-onDemand (CFD), a budget-aware edge-cloud agentic framework. The edge runs a single offline captioning pass that builds a dual-track narrative index, an event-level story skeleton plus a clip-level micro-log, cached and reused across queries without re-captioning. At query time, a cloud-side MLLM reasons over the index in a story-first loop centered on a lightweight Visual-Need Router: a per-query gating module that triggers bounded keyframe
retrieval only for perceptual questions (appearance, on-screen text, attribute disambiguation) and keeps temporal-structural questions in
language space. The router turns visual access into a first-class, query-conditioned cost, capping per-query frame consumption regardless of
video length. Experiments on long-
video benchmarks demonstrate strong accuracy-efficiency trade-offs while substantially reducing online visual processing.
Read the full abstract ▾
All authors Weitong Cai, Hang Zhang, Yukai Huang, Yiqiao Xie, Shan Gao, Jiankang Deng, Songcen Xu, Jifei Song, Zhensong Zhang
Machine Learning
CausalArena: Benchmarking Causal Discovery in the Foundation Model Era
Zi-Rong Li, Si-Yang Liu, Tian-Zuo Wang et al. (+1 more)
Causal discovery aims to uncover causal structures from data and is fundamental to scientific
reasoning and intervention-based decision making. Its evaluation relies heavily on structural causal models (SCMs), which specify a causal graph together with the mechanisms that generate data, yet existing studies differ substantially in graph families, mechanisms, and evaluation protocols. The emergence of causal discovery foundation models (CDFMs) further complicates evaluation: performance may reflect not only causal discovery ability, but also overlap between pretraining environments and test SCMs, making results on fixed synthetic
benchmarks difficult to interpret. We introduce CausalArena, a unified and evolvable
benchmark for causal discovery under a common protocol. Synthetic SCMs supply controlled breadth over structures and mechanisms; semantic operational SCMs provide human-auditable, semantically grounded environments beyond standard synthetic generators; and formula-grounded SCMs test discovery under explicit scientific mechanisms. Public real-world
datasets provide an additional external-validity check. Experiments across classical, neural, and pretrained methods reveal substantial ranking shifts across SCM families and protocols, showing that strong performance in one
benchmark regime does not reliably transfer to others. These results highlight
benchmark diversity and pretraining–evaluation overlap as central challenges for evaluating causal discovery in the foundation model era.
Read the full abstract ▾
All authors Zi-Rong Li, Si-Yang Liu, Tian-Zuo Wang, Han-Jia Ye
Computer Vision
3D Point Splatting for mmWave Radar Novel View Synthesis
Adnan Armouti, Yixuan Gao and Rajalakshmi Nandakumar
Solving novel view synthesis (NVS) for millimeter-wave (mmWave) radar requires a renderer that is physically faithful, complex-valued, and multi-viewpoint-tractable. No prior method achieves these three properties simultaneously. Differentiable Monte Carlo (MC) ray tracers implement the radar forward model directly with explicit material modeling and complex outputs, but a joint fit across views takes over an hour per scene. Optical-NVS ports of NeRF, hash grids, and 3D Gaussians train fast but discard phase and replace explicit material modeling with opaque learned features, restricting them to power-only range-azimuth (RA) magnitudes. We propose 3D Point Splatting (3DPS), the first differentiable point splatting renderer for radar, derived directly from the standard solid-angle form of the radar equation. Each oriented 3D point carries a material model built on ITU-R P.2040 permittivity and slab reflection, evaluated in closed form, with the resulting complex phasor splatted into range bins through a precomputed point spread function (PSF). The complex-valued output makes the renderer product-agnostic. The same optimized scene yields analog-to-digital converter (ADC), complex range profile (CRP), and RA outputs through standard fast
Fourier transform (FFT) pipelines without retraining for each format. On six outdoor ColoRadar scenes, 3DPS reaches 0.587 mean Pearson correlation on held-out RA images. This is between 1.7x and 5.2x the three optical-NVS baselines (RadarSplat, Radar Fields, DART) and 1.3x the mmIR ray tracer at 1/25 of its wall-clock time. Training takes approximately 3 minutes per scene on a single RTX 4090. Project page: https://3d-point-splatting.github.io/
Read the full abstract ▾
Logic in Computer Science
A Lumpability-Driven Taxonomy of Strong and Weak Stochastic Bisimilarities with Their Congruence Properties
Riccardo Romanello, Andrea Esposito, Marco Bernardo et al. (+2 more)
We study the relationships among the
stochastic bisimulation-style equivalences over PEPA - Performance Evaluation Process
Algebra definable according to the well known notions of lumpability for the continuous-time Markov chains (CTMCs) underlying process terms. Lumpability is a central tool in the analysis of a CTMC, because it results in aggregations of the state space enjoying properties that are useful for efficiently computing the state probability distribution of the original chain. At the level of process terms, various
stochastic bisimilarities accounting for activity types and cumulative rates can be defined over PEPA, which induce different kinds of lumping. Since the formalisations of some of them are scattered across the literature, where they appear under different, and sometimes clashing, names, we collect them within a single, uniform framework, renaming each bisimilarity in a consistent way after the kind of lumping it induces. We present strong and weak variants of what we call ordinary, exact, and strict bisimilarities and show that they respectively induce ordinary, exact, and strict lumpings. We then organise the six bisimilarities into a taxonomy establishing all and only the inclusions holding among them. We also analyse how the taxonomy changes in three special cases: process terms whose underlying CTMCs are time reversible, process terms with no activities of unobservable types, and process terms with no recursion. The paper concludes by investigating the compositionality properties of the six bisimilarities. Some of them are not congruences with respect to the prefix and/or choice operators of PEPA. In that case we single out either a set of process terms over which congruence with respect to those operators is achieved, or the coarsest congruence with respect to them that is contained in the considered bisimilarity.
Read the full abstract ▾
All authors Riccardo Romanello, Andrea Esposito, Marco Bernardo, Carla Piazza, Sabina Rossi
Computation and Language
Nuha-Speech: Building General-Purpose Arabic Speech-LLMs
Yingzhi Wang, Reem Alhazzani and Muhammad Alqurishi
As
Speech Large
Language Models (
speech-LLMs) become increasingly
multilingual, Arabic remains significantly underrepresented, highlighting the need for dedicated infrastructure to train and evaluate Arabic
speech-LLMs. To address this gap, we introduce Nuha-
Speech, a comprehensive initiative to develop general-purpose Arabic
speech-LLMs spanning
dataset construction, model training, and systematic evaluation. Specifically, we constructed a large-scale Arabic
Speech Question-Answering (SQA) corpus comprising over 1.5 million training samples to allow instruction tuning over a broad range of core
speech tasks. Then, the corpus was used for supervised fine-tuning based on Qwen-Omni model variants at different scales. Finally, we designed an evaluation framework featuring diverse tasks and tailored metrics. Through this work, we aim to establish foundational infrastructures for Arabic
Speech-LLMs under constraints imposed by limited Arabic
speech resources.
Read the full abstract ▾
Game Theory
ABRA: An algorithm which cannot converge to low-quality Nash equilibria
Vartika Singh and Philip N. Brown
We consider a game theoretic approach to solve multi-
agent coordination problems with submodular objectives. It is known for such problems that the Nash
equilibria for the corresponding game are always within 50% of the optimal. A recent work further shows that the
equilibria which achieve this worst-case bound are not stable. Leveraging this, we design an Approximate Best Response
Algorithm (ABRA) governed by a noise parameter and a rationality parameter. The noise allows ABRA to escape the bad
equilibria and the rationality parameter balances any degradation in the objective function caused by the noise. We show for any two-player game that if ABRA converges to a Nash
equilibrium, its system objective value is strictly more than 50% of optimal plus a term controlled by the noise parameter. Otherwise, ABRA converges to some recurrent class: if a recurrent class contains any action profile yielding system objective less than 50% of the optimal, the class must also contain either the optimal action profile or an action profile yielding system objective strictly more than 50% of the optimal by the same amount in addition to a factor controlled by noise parameter. The time that ABRA spends in such action profiles can be controlled using the rationality parameter. Using numerical simulations, we show that the minimum expected objective function is typically well above half of the optimal.
Read the full abstract ▾