Machine Learning
What Must a World Model Distinguish for Planning?
Rongzhe Wei, Hans Hao-Hsun Hsu, Peizhi Niu et al. (+2 more)
World models simulate the consequences of action candidates, but good planning need not preserve every physical distinction required for accurate prediction. We formalize this gap through a hierarchy of mechanism, response, and decision sufficiency. Given a candidate set, the planning query determines which physical variations matter and how precisely they must be preserved: coarse decisions can discard much of the information needed for prediction, whereas fine decisions may require nearly the same resolution. In practice, planners often adaptively search to construct candidates, and information unnecessary for final selection may still be needed to discover good candidates. What a world model must preserve therefore depends on the query, the candidate set, and the planner. We study these effects in a collision system, nonlinear dynamics, and robotic planning. These varying requirements raise a design question: where should query information enter the planning system? A model that jointly generates actions and outcomes conditioned on the query achieves lower regret than an action-conditioned world model on seen objectives, but this advantage largely disappears when generalizing to unseen objectives. Motivated by this, we propose a modular design in which the query determines where to look and an action-conditioned model predicts what will happen, allowing the same predictions to be reused across objectives.
Read the full abstract ▾
All authors Rongzhe Wei, Hans Hao-Hsun Hsu, Peizhi Niu, Yifan Li, Pan Li
Machine Learning
Łukasiewicz Neural Networks Extended: Residual Architectures and Crystallization Strategies for Interpretable Rule Extraction
Carlos Leandro
A feed-forward neural network whose weights are integers and whose activation is the truncated identity implements,
neuron by
neuron, the connectives of Łukasiewicz many-valued logic. This exact correspondence — established theoretically by Castro and Trillas and developed into a training
algorithm by Leandro — enables symbolic knowledge extraction: training produces not a black-box model but a logical formula. Two obstacles have limited the approach to shallow architectures and small
datasets: crystallization (forcing weights to integers) succeeds only probabilistically under the original Levenberg–Marquardt training scheme, and the theoretical guarantees break down as networks grow deeper. This paper addresses both obstacles. First, we prove that residual connections (skip connections of the kind used in ResNets) extend Łukasiewicz neural networks to arbitrary depth while preserving the symbolic correspondence at merge
neurons by construction: merge
neurons in a Łukasiewicz residual block automatically satisfy the
neuron-classification proposition, regardless of the inner layer weights; inner-layer
neurons are trained toward representability by the crystallization strategy. Second, we analyse three crystallization strategies — Levenberg–Marquardt (corrected), straight-through estimation (STE), and proximal regularization — characterizing their theoretical guarantees, failure modes, and interpretability trade-offs.
Read the full abstract ▾
Machine Learning
Low-Rank Single-Index Bandits with Unknown Links: From Matrices to Tensors
Zhongxuan Liu, Yue Kang and Thomas C. M. Lee
Low-rank
matrix and tensor bandits exploit structured interactions but typically assume a known reward link. Recent single-index bandit methods accommodate unknown links without directly exploiting
matrix or tensor rank. We address this gap by studying
stochastic matrix and tensor bandits with an unknown shared Lipschitz link and a low-rank index parameter under known regular candidate distributions and finite-variance noise. For monotone links, T-ESTOR combines robust, rank-adaptive Stein estimation with epoch-based greedy selection. Under exact selected-score access and a uniformly positive selected-design Stein signal, it achieves square-root regret with dimension dependence determined by the low-rank structure. For every admissible design, the monotone lower bound matches the rank, dimension, and horizon dependence up to logarithmic factors at large horizons, for fixed menu size and model/design constants. For nonmonotone links under a nonzero base-law Stein signal, T-BSTOR combines structured estimation with robust bin-based learning and attains the optimal $\widetilde{O}(T^{2/3})$ horizon rate for fixed dimensions, menu size, and model/design constants. Synthetic and CCLE-based experiments illustrate the benefits of structured estimation relative to vectorized and competing single-index baseline methods.
Read the full abstract ▾
Artificial Intelligence
SRE-Marathon: A Continuous, Change-Driven Benchmark for Autonomous Site Reliability Agents
Yifang Tian, Yingjian Bai, Yifeng He et al. (+4 more)
Benchmarks for site reliability engineering (SRE)
agents are typically episodic: one fault is injected, the
agent receives an incident task, and its response is scored. Production operation is not. Incidents surface through noisy alerts, overlap in time, and often originate from code or configuration changes. We present SRE-Marathon, a
benchmark for long-horizon, continuous SRE operation. An
agent is invoked at a fixed cadence with cumulative alert history and a persistent workspace while operating a live two-zone Kubernetes deployment as a fault orchestrator injects overlapping faults according to a seeded, production-calibrated schedule. Curated code and configuration changes deployed through the same build pipeline available for repair. Each run is recorded into a sealed bundle and scored offline: Marathon-Score credits each injected fault for ordered progress through correlation, localization, and repair, with all metrics computed deterministically from recorded system evidence. Across three applications and about sixty faults per run, the best of 10 methods reaches only 41.3 out of 100.
Agents often correlate and localize faults, but almost never complete repairs while the faults remain active.
Read the full abstract ▾
All authors Yifang Tian, Yingjian Bai, Yifeng He, Zichun Chong, Yuanchen Gao, Yiran Li, Hans-Arno Jacobsen
Machine Learning · Cross-listed from math.OC
Decentralized Optimization with Cross-Coupled Mixed Affine Constraints
Ewsey Obzherin, Ilya Khomchenko, Natalia Shelegeda et al. (+4 more)
We study decentralized optimization with cross-coupled mixed affine constraints, where local and shared variables interact through two affine channels. We show that the intrinsic difficulty of combining separately well-conditioned channels is governed by their Friedrichs angle. This geometry induces a cross-coupling factor that cannot be removed by channelwise preconditioning and governs the additional affine-oracle and communication complexity. We develop an accelerated decentralized method with matching minimax guarantees in the smooth strongly convex regime and extend the framework to smooth and nonsmooth convex objectives. Experiments confirm the predicted dependence on cross-channel geometry and network conditioning.
Read the full abstract ▾
All authors Ewsey Obzherin, Ilya Khomchenko, Natalia Shelegeda, Nhat Trung Nguyen, Demyan Yarmoshik, Alexander Rogozin, Alexander Gasnikov
Computer Vision
Residual Diffusion Implicit Models
João Guerreiro, Pedro Tomás, Helena Aidos et al. (+1 more)
Diffusion models achieve state-of-the-art results across multiple tasks. However, in inverse problems, standard initialization from pure Gaussian noise misaligns the generative process with real-world degradations. More recent methods such as
diffusion bridges impose strict endpoint constraints and often require long reverse processes that are prone to
hallucinations. Alternative consistency models provide noise-invariant, one-step mappings but lack inherent variance modeling and can degrade under severe corruption. Hence, residual
diffusion implicit models (RDIMs) are proposed, constituting a generalized framework that explicitly models the residuals between high-quality (HQ) and low-quality (LQ) images, aligning the forward process with the actual degradation. A non-Markovian implicit reverse sampler is derived, which can skip intermediate timesteps, enabling accurate few-step or even single-step reconstruction, while mitigating the
hallucinations inherent to long
diffusion chains. RDIM also introduces a controllable variance mechanism that interpolates between deterministic and
stochastic sampling, balancing fidelity and diversity. Furthermore, it enables the straightforward use of perceptual losses, when needed. Experiments on denoising and super-resolution
benchmarks demonstrate that RDIMs consistently outperforms the state of the art, including bridge and consistency models, in terms of PSNR, SSIM, and LPIPS, reducing
hallucinations while requiring only a few sampling steps (often just one). The results position RDIMs as an efficient solution for a broad range of image restoration tasks.
Read the full abstract ▾
All authors João Guerreiro, Pedro Tomás, Helena Aidos, Jacinto C. Nascimento
Artificial Intelligence
Trust and Task Completion in the World of Consumer AI Agents
Jeroen Olieslagers, Eduardo Pujol, Gal Zahavi et al. (+2 more)
Action
agents do things for people. They send email, spend money, and call businesses while the user is busy with something else, so a mistake can turn into an action before anyone notices. They fail their users in two ways. They break trust when they do something the user never agreed to, or hold back after the user clearly said go. And they fall short on completion when they give up on errands that turn out to be hard. Both depend heavily on the harness around the model, meaning its instructions, tools, context, and guardrails. We built an evaluation that scores trust and completion on the same runs, in a simulated world of businesses with their own websites, inboxes, and phone lines, and of people who write back. A simulated user answers the assistant's questions. Trust means that nothing happens the user did not agree to. No email goes to someone they never approved, no private detail ends up on a group thread, no money is spent past their limit, no stranger's instructions are followed, and nothing is claimed without a source. Every trap has a matched control in which acting is the right call. We use the evaluation to measure Fo, Wajo's personal assistant, against a base model with basic instructions on three foundation models, and against the Fo harness with its guardrails switched off. Fo completes 71% of the errands and keeps the user's trust on 94% of the trap runs. The base models complete 50% to 64% and keep trust on 59% to 75%. On the matched controls, Fo goes ahead slightly less often. OpenClaw, a popular open-source assistant given the same access, completes 42% of the errands it shares with Fo, against 71%, and keeps the user's trust on 74% of the shared trap runs, against 94%. Measuring trust and completion together, on the whole system rather than the model alone, is how we think action
agents become safe to hand real work to.
Read the full abstract ▾
All authors Jeroen Olieslagers, Eduardo Pujol, Gal Zahavi, Lukas Ingemarsson, Shivani Poddar
Machine Learning
Relative Generalization Invariance of LLM Pretraining
Fengzhuo Zhang, Shuche Wang, Shenggui Li et al. (+7 more)
Large
Language Model (LLM) pretraining performance is jointly shaped by three components of the training triplet: the optimizer, model architecture, and training data stream. However, how these components influence performance in distinct ways remains unclear. We take a first step toward isolating their effects by studying relative generalization. We introduce Relative Generalization Invariance (RGI), the invariance of the validation-loss difference between any two
tokens across models. We show that RGI approximately holds across a wide range of optimizers and moderate architectural variations, suggesting that these choices induce an approximately uniform shift in
token-wise losses. In contrast, changing the training data stream can substantially alter relative generalization. We further show that RGI cannot be explained by the neural tangent kernel or mean-field regimes alone and prove that it can emerge in an overparameterized quadratic model. Overall, our work identifies RGI as a new phenomenon in LLM pretraining that helps distinguish the effects of optimizers and architectures from those of training data.
Read the full abstract ▾
All authors Fengzhuo Zhang, Shuche Wang, Shenggui Li, Tianyu Ruan, Jianliang He, Ivor Tsang, Tianyu Pang, Chao Du, Tianwei Zhang, Zhuoran Yang
Computation and Language
TCMQA: A 38K-Question Traditional Chinese Medicine Benchmark with a Licensed-Practitioner Reference
Tzu-Heng Huang, Jet Lin and Eric Lin
Medical
benchmarks for
language models are built almost entirely on Western biomedicine. Traditional Chinese Medicine (TCM) is a separate system, with its own diagnostic framework and its own literature, and it remains largely unmeasured. The few TCM evaluations that exist are small, narrow, and rarely paired with a human reference. We present TCMQA, an open
benchmark of 38,279 questions from Chinese TCM licensing examinations, paired with 15,151 responses from 101 licensed practitioners. We evaluate 29 instruction-tuned models from 9 families, spanning 0.27B to 14.8B parameters. Accuracy ranges over 59 points, and no model approaches saturation. Pretraining data predicts TCM ability far better than scale: a 12B Western-pretrained model reaches 39.6%, while a Chinese-pretrained model an eighth its size reaches 60.8%. Nine models exceed the practitioner majority vote of 64.9%, the best by 21.8 points, and all nine come from that same Chinese-pretrained family. Yet difficulty does not transfer between models and practitioners: accuracy is flat across practitioner-rated difficulty, item-level agreement is near zero for all 29 models, and on $8.4\%$ of items the practitioners are correct where the leading model is wrong. We release the corpus, the practitioner responses, the harness, and per-item model outputs at https://huggingface.co/
datasets/TechTCM/TCMQA.
Read the full abstract ▾
Artificial Intelligence
The Epistemics of Agent Memory: Measuring, and Governing, the Consolidation Decision in Long-Horizon LLM Agents
Sasank Annapureddy and Anjaneya Prasad Thamatani
Long-horizon LLM
agents must convert accumulated experience into durable
memory, deciding what to keep, compress, abstract into reusable skills and rules, or forget. We report a four-phase research program on this consolidation problem whose central finding is a shift in what is measured: from how much an
agent remembers, to whether its consolidation decisions are any good, to whether those decisions can be trusted. Phase 1 learns episodic boundaries from
agent traces by downstream utility; an honest near-miss (oracle correlation 0.691 vs a 0.70 bar) whose lasting output is a three-gate anti-leakage protocol. Phase 2 learns when to promote experience and to which abstraction level under a
token budget, achieving a verified +22.7% task-success improvement with 7x compression, but exposing a degenerate-forgetting failure and a distribution-shift failure mode we name lambda-prevalence coupling. Phase 3 introduces ConsolidationBench, an oracle-by-construction
benchmark that scores consolidation decisions against a known optimum on three non-circular axes; production
retrieval systems retain information yet score zero on cross-level transfer. Phase 4 introduces governed consolidation: the decision wrapped in poison-resistance, reversibility, and auditability guarantees with a quality gate. Governance is statistically distinct from the quality score ($r^2 = 0.43$; partial $r = 0.27$; identical-quality policies differ threefold in governance), so the contribution survives independently of the metric's external validity. On that question we report a resolved negative: after a graded-reuse redesign removed a structural ceiling, a two-
benchmark study with 2,532 real answer
cells finds the quality score does not predict real transfer accuracy (pooled Spearman $\rho = -0.24$, n = 12, CI spanning zero). An
adversarial self-critique pass cleared the final claim set with zero surviving overclaims.
Read the full abstract ▾
Artificial Intelligence
When Pair Count Is Not the Sample Size: What All-Pairs Agent Comparisons Estimate
Wei-Jung Huang
When an
agent benchmark compares every pair of leaderboard entries, the number of comparisons can look much larger than the independent evidence behind them: A versus B and A versus C both reuse A. Whether this reuse affects inference depends on what the analysis is meant to describe. If the board and its outcomes are fixed, the all-pairs mean is an exact summary of those entries, and any interval must come from another declared source of randomness. If the entries are instead treated as iid draws from a population of future configurations and the pair rule is regular and nondegenerate, the same mean is an order-two U-statistic whose first-order uncertainty depends on the number of configurations, not the number of pairs. We use near ties as the running example, but the distinction extends to other symmetric pair summaries when their regularity conditions hold. We examine both interpretations using a fixed SWE-bench Verified snapshot and an exact binary model with known truth. On SWE-bench, intervals that accounted for shared configurations were more than twice as wide as a pair-iid reference that treated the pairs as independent. In the exact model, pair-iid coverage fell far below the nominal level when edges shared endpoints but remained near nominal for matched independent edges. Results on two other fixed leaderboards show that exact summaries also depend on which pairs are included and how they are weighted. An all-pairs analysis must therefore state what is fixed, what is sampled, and how it handles shared entries and pair aggregation.
Read the full abstract ▾
Machine Learning
Saturation-Insensitive Dueling Bandits with General Function Approximation
Chenggong Zhang, Xuheng Li, Qiwei Di et al. (+2 more)
We study contextual dueling bandits with general function approximation under the Bradley-Terry-Luce (BTL) preference model. A key challenge in this setting is the saturation of the preference model: when the current reward model can already distinguish two actions with high confidence, the resulting preference feedback becomes weakly informative, making it difficult to further improve reward estimation. Consequently, existing sample-complexity analyses often depend on the inverse-derivative factor $1 / \sigma'[\Delta_{r^\ast}]$ which can be prohibitively large when the link function $\sigma$ saturates for large reward gaps $\Delta_{r^\ast}$. To address this issue, we introduce `SI-CDB`, an
algorithm that selects opponent arms using a carefully designed heuristic for arm selection. This design enables saturation-insensitive reward learning and recovers the near-optimal dependence for linear reward classes, eliminating the unfavorable $1/\sigma'(\cdot)$ factor. The core of our analysis is a localized Eluder dimension framework tailored to dueling bandits with general function approximation. Our theoretical results also explain why two-arm regret analysis is crucial for improving single-arm performance in dueling bandits.
Read the full abstract ▾
All authors Chenggong Zhang, Xuheng Li, Qiwei Di, Weitong Zhang, Quanquan Gu
Artificial Intelligence
Model-Aware Data Selection from In-and-Out Information Interplay
Yifan Wang, Xiaomin Li, Yuexing Hao et al. (+7 more)
LLMs are effective representations that assimilate vast amounts of knowledge during pretraining, but post-training is necessary for models to reliably access this knowledge and "know what they know." We observe an interesting rank
equilibrium between knowledge stored in the weights and the data stream passing through the model. Across all model layers, we find that the hidden states (data stream) follow a U-shaped pattern, showing substantial compression in early layers and a steep rise during the late-layer decoding phase. In contrast, the weight rank follows an inverted U-shaped pattern, with very low rank in the early and late layers and high rank in the middle. We interpret this as an in-and-out information interplay: intermediate activations do not need to carry content that the weights can supply later, so they primarily preserve what the weights cannot provide. Motivated by this observation, we propose a model-aware data selection method, CAP (Counterfactual Assimilation Profile), which can determine whether a data candidate contains information accessible to the current model by utilizing the divergence gap in early- and late-layer representations between model-generated and reference responses. Across math, code, and science domains, CAP delivers 35.4% greater average improvement over the base model than the strongest baseline under different selection budgets. With only 10% of the data pool, CAP surpasses or matches full-pool training on math and science. We further show that CAP transfers to
multimodal data selection and is robust to response horizon and noise.
Read the full abstract ▾
All authors Yifan Wang, Xiaomin Li, Yuexing Hao, Dongwon Jung, Hemanth Neelgund Ramesh, Ananth Grama, Varun Chandrasekaran, Yu Hu, Andrzej Banburski-Fahey, Jaron Lanier
Robotics
CAPEX: Efficiently Distilling Foundation Model Behavior into Deployable Robot Policies through Experience-Adaptive Reasoning
Shivam Aarya, Zhang Xi-Jia, Chengyue Huang et al. (+6 more)
Robot learning has largely relied on human-teleoperated demonstrations to acquire effective learnable behaviors. However, human-operated data collection processes can be unintuitive, difficult to scale, and inherently asynchronous. We explore an alternative: distilling physical behavior from general-purpose
multimodal foundation models into deployable
robot policies by using the foundation model itself as an autonomous demonstrator. While sufficiently capable models can generate successful zero-shot manipulation trajectories, repeatedly invoking them during physical execution is slow and expensive, limiting their utility as scalable data generators. As a solution, we introduce CAPEX, an experience-conditioned demonstration collection framework that uses execution experience from previous attempts to adapt how frequently the foundation model must observe, reason, and replan. We evaluate across RoboCasa tasks and on physical Franka and bimanual YAM-arm platforms, measuring task success, model calls,
token usage, collection time, and cost. We further train
Diffusion Policy and ACT on matched sets of human-teleoperated and foundation-model-generated demonstrations to evaluate the downstream learning value of autonomously collected data. We find that CAPEX increases the number of successful demonstrations by 4.3x while reducing the cost per successful demonstration by 80%. Policies trained on CAPEX-generated data approach the performance of those trained on matched human demonstrations; with longer training, this gap largely closes for policies trained from scratch. These results suggest that foundation models can serve as scalable sources of reusable
robot experience. Project page: https://capex-paper.github.io/
Read the full abstract ▾
All authors Shivam Aarya, Zhang Xi-Jia, Chengyue Huang, Junhyun Kim, Huishu Xue, Hrishit Leen, Roman Yakunin, Animesh Garg, Zsolt Kira
Computer Vision
Safety-Constrained Cascade Inference for Robust Malaria Cell Classification Under Field Corruptions
J. T. Hagbe and Michel Emel
Automated malaria diagnosis from thin blood-smear microscopy could meaningfully reduce the burden on under-resourced laboratories, but a model that maximises accuracy on clean laboratory images fails badly the moment an inexpensive smartphone camera introduces sensor noise. This paper introduces MalariaCascade, a two-stage inference system in which a lightweight MobileNetV2 sentinel (2,225,153 parameters) makes confident classifications at low compute cost and escalates uncertain cases to an EfficientNet-B3 expert (10,697,769 parameters) that sees only clean, standardised images regardless of how corrupted the incoming frame is. Structural isolation of the expert stage, not learned robustness, is the mechanism. The sentinel is trained under a safety-score objective that places an explicit floor on Recall(Parasitised) (>=0.95) and Recall(Uninfected) (>=0.40) before precision is optimised, ensuring the checkpoint satisfies clinical safety constraints by construction. On the NIH Malaria
Cell Images
Dataset (27,558
cells), the cascade reaches Accuracy=0.9736, Recall(Parasitised)=0.9570, Precision(Parasitised)=0.9912, F1=0.9738, and AUROC=0.9955 on the clean test set. Under Gaussian sensor noise at full severity, cascade Recall(Parasitised) degrades by only 2.4 pp (0.9570 to 0.9329), while the flat single-model baseline collapses by 63.0 pp (0.9584 to 0.3281). McNemar's test confirms the cascade improvement is statistically significant (chi^2=11.14, p=0.00085). An ablation isolating the structural property shows that routing clean images to the expert is responsible for a 16.8 pp Recall(Parasitised) advantage under sensor noise relative to a cascade where the expert also sees corrupted inputs.
Read the full abstract ▾
Cryptography and Security
On the Usage of Verifiable Credentials in Privacy-Preserving Federated Analytics
Andreea-Elena Drăgnoiu and Ruxandra F. Olimid
Privacy-Preserving
Federated Analytics enables multiple nodes to collaboratively derive statistical insights without exchanging raw data. However, ensuring node authenticity and data validation (avoiding concerns such as identity tracking, data linkage, or data leakage) remain fundamental challenges. This paper offers some insights into the feasibility of defining an authenticated, integrity-preserving data model by coupling FPPA with Verifiable Credentials defined within the Self-Sovereign Identity framework.
Read the full abstract ▾
Computer Vision
Certified Interface Aliases: Exact Collisions in Vision-Language Preprocessing, and When They Exist
Mert Onur Cakiroglu, Elham Buxton, Mehmet Dalkilic et al. (+1 more)
Vision-
language verifiers and routers must distinguish errors repairable by more
reasoning from those caused by visual evidence never reaching the
language model. This distinction lacks ground truth because annotators see full-resolution images while models receive preprocessed tensors. We introduce AliasForge to create cases where the relevant fact is provably absent from the interface. Fixed-point resampling makes the pre-rounding resize an exact integer linear map that can send nonzero integer perturbations to zero. Hiding a label-flipping perturbation there produces images with opposite step-correctness labels but bit-identical interface states. Every verifier therefore has the same output law on both members, giving pair-balanced accuracy exactly one half and zero gain from
language-side repair. We prove that every fixed-point downscaler has such null vectors and bound their smallest size at the most common ratios, which rules out an 8-bit fit whenever the bound exceeds 255. From the resize configuration alone, a
lattice criterion supplies realizable collisions and certifies their absence within the specified construction family. It resolves all 20 screened configurations, 17 as constructible and 3 as non-constructible. We construct certified pairs across three architectures and certify four additional processors, with zero decision-logit gap on all 18 scored pairs and none of the 18 controls. The pairs also screen routers that waste computation on re-
attention or further
reasoning. On natural items, per-item routing headroom exists, but no tested interface-only router improves over stopping. Our fiber ceiling bounds the headroom recoverable from the interface. Code: https://github.com/KurbanIntelligenceLab/aliasforge.
Read the full abstract ▾
All authors Mert Onur Cakiroglu, Elham Buxton, Mehmet Dalkilic, Hasan Kurban
Robotics
TriDrive: Joint Driver, Vehicle, and Road Modeling for Forecasting and Driver Monitoring
Yuhang Wang, Jingxin Yang, Chuheng Wei et al. (+4 more)
Predicting how drivers, vehicles, and road scenes interact and evolve together is central to driver monitoring. Prior work models in-cabin activity or traffic-conditioned driver motion in isolation, motivating joint driver, vehicle, and road modeling with real-time on-vehicle evaluation. We introduce TriDrive, to our knowledge the first unified framework that jointly forecasts driver kinematics, vehicle dynamics, and road demands through an automation-conditioned transition model. Modality-specific encoders (an anchored kinematic representation of the driver, causal CAN-bus dynamics, and frozen V-JEPA 2 road latents with structured road margins) are connected by directed residual connections through which driver and road context refine vehicle forecasts. We evaluate TriDrive on three downstream tasks. On the public AIDE
benchmark, its kinematic encoder recipe sets a new full-set state of the art (SOTA) among published baselines (48.05 versus 71.47 All-MPJPE). On 197.2 hours of naturalistic BATON subset, directed connections and road margins raise assistance-engaged PR-AUC by 0.084 for steering onset and 0.286 for time-to-collision drops. For real-time use, we distill the road encoders and run TriDrive on a comma four with an external 8 GB GPU, where a lightweight current-state warning probe updates at 5 Hz with 177 ms p95 latency while the joint model forecasts concurrently. The probe is above an openpilot-based baseline on human-labeled manual-driving warnings (AUROC 0.725 versus 0.563), and in a paired on-road study 14 drivers rate its warnings as more appropriate (+1.79) and timely (+2.67) than those of openpilot's driver-monitoring system.
Read the full abstract ▾
All authors Yuhang Wang, Jingxin Yang, Chuheng Wei, Yuechen Guo, Jinghan Xu, Zhao Han, Hao Zhou
Distributed Computing
Tessera: Demand-Driven KV Cache Management for Retrieval-Augmented LLM Serving
Fei Fang, Chung-Hsiang Lo, Yi Liu et al. (+2 more)
RAG and
retrieval-based
agent memory both inject retrieved content into LLM
prompts, as document chunks and recalled
memory records, respectively. The same content can recur across requests at different
prompt positions or after different preceding contexts, preventing reuse through conventional prefix caching. Our characterization finds that records recurring outside the matching prefix account for over 70% of injected
memory tokens in
agent-
memory workloads. Composable KV-reuse methods enable reuse in such cases, but online serving introduces a management problem: a recurring unit's KV states may not yet exist, may have been evicted, or may reside on another node. We present Tessera, a disaggregated serving system that makes
retrieval the control plane for KV reuse. By exposing the context units needed before model execution,
retrieval allows Tessera to combine current demand with
retrieval history, KV residency, and generation load to coordinate cache management and request routing. Generation nodes concurrently prepare locally cached, remotely cached, and missing states, while retaining newly computed states off the request's critical path. Across RAG and
agent-
memory workloads, Tessera lowers mean TTFT by up to 3.6x over SGLang and LMCache with EPIC at matched request rates, and sustains low TTFT at rates where the baselines saturate, while matching the answer quality of the underlying composition policy.
Read the full abstract ▾
All authors Fei Fang, Chung-Hsiang Lo, Yi Liu, Yifan Hua, Chen Qian
Computer Vision
Oracle Gaps in Reliability Coverage: Sampling Noise or Policy Specialization?
Mert Onur Cakiroglu, Mehmet Dalkilic and Hasan Kurban
Policies trained from the same base model can appear to solve different problems. An oracle that chooses the best policy for each problem may therefore appear much stronger than any single policy. Selecting the largest estimated success rate also selects favorable sampling errors. We study this effect through reliability coverage, the fraction of problems whose success probability reaches a chosen threshold. Our first test redistributes stored correctness outcomes across policies within each problem. A second also preserves each policy's total successes, accounting for overall quality differences under a specified statistical model. For five training seeds of a seven-billion-parameter
vision-
language model, redistribution reproduces 0.096 of an estimated 0.113 oracle gap at threshold 0.10. Neither test finds significant evidence at this threshold. Small advantages remain unresolved. Mixtures, routers, voting, and weight averaging show no detectable improvement over their corresponding single-policy baselines. Training policies on different
datasets shows little detectable specialization under light post-training, and no router gain. A stronger recipe does create it, both tests detect it, and a router gain appears only at the high thresholds where the specialists separate. In a control with predictable specialization, a router recovers about half the oracle gap. Coverage bounds explain why even a genuine oracle advantage need not yield a deployment gain. The tests assess apparent specialization from stored responses before investment in routing. Code: https://github.com/KurbanIntelligenceLab/oracle-gaps
Read the full abstract ▾
Game Theory · Cross-listed from math.OC
AltGDA Achieves Global $O(1/T)$ Ergodic Convergence in Matrix Games
Tianlong Nan, Garud Iyengar, Christian Kroer et al. (+1 more)
Alternating gradient descent-ascent (AltGDA) is a simple and practically effective method for solving finite two-player zero-sum
matrix games. However, the theory of AltGDA remains limited: existing results either apply only to unconstrained settings or require restrictive assumptions on the
equilibrium in constrained settings. We show that AltGDA converges globally at an $O(1/T)$ ergodic rate in every finite two-player zero-sum
matrix game. Unlike prior results, our guarantee holds for every initialization and every horizon $T$: the uniform averages of the AltGDA iterates satisfy an $O(1/T)$ duality-gap bound. Our proof is inspired by numerical results obtained using a novel performance estimation programming (PEP) framework for Lyapunov function search over compact convex sets. Additionally, we provide simple counterexamples showing that the last-iterate duality gap of AltGDA does not converge to zero. This justifies why averaging of iterates is indeed necessary to achieve an $O(1/T)$ rate. We have formalized and machine-checked our global ergodic convergence result in Lean 4.
Read the full abstract ▾
All authors Tianlong Nan, Garud Iyengar, Christian Kroer, Shuvomoy Das Gupta
Artificial Intelligence
X-Tree: Tokenizing Reusable Experience for Efficient Agent Generalization
Sitao Cheng, Xunjian Yin, Zhiyuan Sun et al. (+4 more)
Multi-step
agents are trained on flat action streams: SFT and RLVR weight every
token uniformly and ignore the sub-procedures that recur across tasks, the hierarchy that lets humans plan top-down from reusable routines. This structure sits unused, and flat training uses each scarce trajectory less fully than its content allows. Recent
agents do use that structure, but only as LLM-written skills in context, never in the weights, so their gains do not generalize beyond
retrieval. We instead recover this hierarchy from the data itself and train on it, with no LLM calls. Following text tokenizers, which build a vocabulary by counting alone, we score action spans by reusability and merge canonicalized actions into a reusable eXperience tree (X-Tree). Each X-Tree node captures how a frequent and success-bearing skill is composed from sub-skills, guiding efficient generalization. We integrate X-Tree into three training settings: offline RL, with each node as a training instance; online RLVR, with an adaptive skill bonus; and on-policy self-
distillation, with X-Tree as the self-teacher's privileged context. Across WebArena, ScienceWorld, and WebShop at three model scales, X-Tree improves over standard recipes at matched data and budget by up to 4.5% SR on WebArena, 5.8% SR on ScienceWorld and 4.1% success on WebShop. Matched analyses attribute the gains to the X-Tree structure and the three integrations.
Read the full abstract ▾
All authors Sitao Cheng, Xunjian Yin, Zhiyuan Sun, Yuxuan Li, Ruiwen Zhou, Xiangru Jian, Victor Zhong
Human-Computer Interaction
Smelling the Way: Olfactory Modulation of Spatial Estimation and Path Integration in Virtual Reality
Siyeon Bak, Junho Kim, Dongyun Han et al. (+2 more)
Spatial cognition enables individuals to perceive and interpret spatial relationships, estimate locations, and navigate within their surroundings. While
vision plays a dominant role, other sensory modalities, particularly olfaction, can support spatial processing when visual cues are limited. This paper explores the effects of scent-delivery within virtual reality (VR) environments by using fan-mediated olfactory devices. We conducted two formal studies to evaluate the effects on spatial information acquisition. Study 1 (N=24) examined the participants' ability to localize a scent source while walking a linear path using two different olfactory devices. Study 2 (N=19) employed a triangle completion task, in which participants attempted to return to their starting point under varying rotation angles and olfactory conditions. Results indicate that scent-delivery feedback influenced spatial behavior in distinct ways across the two studies. In Study 1, visual-olfactory misalignment produced systematic directional biases without improving absolute localization accuracy. In Study 2, distance-modulated scent-delivery feedback reduced terminal homing error but also increased traveled distance and completion time, suggesting a more deliberate goal-confirmation strategy.
Read the full abstract ▾
All authors Siyeon Bak, Junho Kim, Dongyun Han, Sun-Jeong Kim, Isaac Cho
Machine Learning
What Should Data Teach? Moving Bottlenecks Across Circuit, Store, and Use
Yixiao Chen, Ke Cheng, Yue Liu et al. (+2 more)
What should data teach a
language model at a particular point in training? A
circuit view reveals three distinct bottlenecks: forming a computation, making its required content available, and selecting among available routes. A shared diagnosis-to-data principle connects them: localize the missing operation, preserve its causal relation, vary shortcut-bearing context, and re-audit the residual. Formation-sensitive selection and prerequisite ordering accelerate a binding-matching-transport path; a brief early prefix from the same training multiset retains a validation advantage through 100B
tokens. Availability counterfactuals then distinguish writing content from invoking available
memory, while paired supervision and context-opportunity ranking improve matched route decisions and long-context answer likelihood. A continuous 350M-model experiment connects the three interventions on the same facts: early
circuit training improves subsequent learning, and the complete sequence outperforms stage-replacement controls on facts withheld from Use teaching. Independent query surfaces and opposed-source decisions expose conditional arbitration as the remaining frontier. Together, these results show why a change in the limiting operation calls for a change in supervision, not merely a new ranking of difficult examples.
Read the full abstract ▾
All authors Yixiao Chen, Ke Cheng, Yue Liu, Jun Zhang, Jie Jiang
Artificial Intelligence
Certified Long-Horizon Code Agent Evolution via Validation-Gated Skill Optimization
Yifan Wang, Hao Cheng, Xiaomin Li et al. (+13 more)
Long horizon
agent self-
evolution without model weight updates is essential for enabling deployed
agents to accumulate reusable skills and improve over time. Prior self-
evolution work has focused primarily on short-horizon tasks, while repository-level software engineering remains unexplored despite being an ideal testbed for long-horizon adaptation. In this setting,
agents are required to solve streams of sequential tasks, navigate complex dependencies with evolving repositories and persistently store and reuse experience. Text-based skill optimization offers an efficient, non-parametric approach for such adaptation. However, existing methods often suffer from unstable updates, performance drawdown, and
agent collapse over extended deployments. In this paper, we formalize the concept of in-context self-
evolution and introduce VALVE, a validated-gated framework for long-horizon skill optimization. We establish finite convergence, provide theoretical guarantees for future-task gain and drawdown, and derive the validation and evaluation holdout sizes required for a prescribed tolerance, with leading-order scaling Empirically, our pipeline, VALVE achieves stable self-improvement over
evolution horizon spanning more than 1,000 SWE tasks, with average final and peak gains of $14.9$ and $16.5$ points across three frontier models (GPT-5.5, Claude-4.6 and MiniMax-M2.7). The validation gate reduces average drawdown by 75% and produces an 11x more compact skill bank than ungated
evolution. We further present extensive ablations identifying the design choices most critical to long-horizon skill
evolution.
Read the full abstract ▾
All authors Yifan Wang, Hao Cheng, Xiaomin Li, Yuexing Hao, Hemanth Neelgund Ramesh, Dongwon Jung, Hao Tang, Keru Wang, Chenliang Zhou, Qianhui Wu, Wenlin Yao, Ananth Grama, Andrzej Banburski-Fahey, Baolin Peng, Jaron Lanier, Jianfeng Gao
Computers and Society
His Name, Their Judgment: Expert Authority in Posthumous Persona AI
Hanjing Shi and Dominic DiFranzo
Persona AI can make deceased experts available for decisions they never encountered. Users may seek these personas precisely because they lack the knowledge needed to judge their advice. We thematically analyze 115 focal RedNote/Xiaohongshu posts and a nested comment sample concerning unofficial personas of Chinese education advisor Zhang Xuefeng. An installation offer promised expert guidance, while a family's reported use required current records and contextual judgment. Other posts positioned the persona as a questioning aid rather than an expert replacement. Commenters connected continued expertise to updating, permission, and the ability to refuse further work. These findings distinguish access to an expert identity from access to professional help. Keeping the persona current puts living actors in control of what the deceased appears to recommend. Operators therefore need to undertake the support promised by the persona while making their continued use of the person's identity open to challenge.
Read the full abstract ▾
Cryptography and Security
Coordinated Electromagnetic Side-Channel Attacks for Voter–Ballot Linking: A Case Study of the Brazilian E-Polling System
Leandro Hyeda, Kleber V. Cardoso, Antonio Oliveira-Jr et al. (+1 more)
In this work, we show how two adversaries (Eve and Mallory) can coordinate an electromagnetic side-channel attack to recon- struct the vote displayed on an e-voting machine (EVM) and link it to a specific voter (Alice). Assuming that Eve has access to a place adjacent to the e-polling room (e.g., restroom, unsupervised room), she performs vote reconstruction by intercepting un- intended electromagnetic emanations associated with the
video signal. Meanwhile, Mallory observes when Alice is voting and reports this information to Eve over the Internet. To validate the most critical stage of the attack, we conduct a software-defined
radio experiment using the official Brazilian e-voting interface and demonstrate through-wall vote reconstruction. Although conventional monitors are employed rather than official EVMs, our findings provide insights into information forensics and support security recommendations for government authorities responsible for e-voting systems.
Read the full abstract ▾
All authors Leandro Hyeda, Kleber V. Cardoso, Antonio Oliveira-Jr, Saulo Queiroz
Distributed Computing
Simple and Fast Signature-Free Blockchain Consensus
Giuliano Losa, Xuechao Wang, Zhuolun Xiang et al. (+1 more)
Signature-free protocols avoid the cost of post-
quantum signatures. We present two simple signature-free blockchain consensus protocols for eventual synchrony with optimal good-case commit latency (three message delays for \(f<n/3\) and two for \(f<n/5\)), optimistic responsiveness, a block time of only two message delays without speculation, and \(O(n^2)\) communication per view. They instantiate Generic Simplex, a blockchain consensus construction parameterized by a new abstraction called view agreement. The same construction also captures Simplex, Minimmit, and a new synchronous signature-free protocol with optimal good-case commit latency of two message delays for \(f<n/4\).
Read the full abstract ▾
All authors Giuliano Losa, Xuechao Wang, Zhuolun Xiang, Qianyu Yu
Computer Vision
ReVision3D: Attribution-Guided Recursive Self-Improvement for 3D Medical Perception
Ho Hin Lee, Yuyin Zhou, Yannan Yu et al. (+2 more)
Recursive self-improvement (RSI) offers a promising path for overcoming the limited visual capability of current medical imaging
agents. Yet applying RSI to volumetric imaging remains difficult: failures can arise from acquisition, perception, training recipe, or downstream inference, while self-generated feedback and logged trajectories provide little guidance on which component should change. We introduce ReVision3D, an RSI system that leverages 3D volumes with spatially grounded annotations to determine where visual evidence is lost and recursively improve the corresponding visual capability. A frozen
language-model designer proposes revisions to acquisition, perception, training, or inference, while the verifier and system-level objective remain fixed. Our key insight is that an annotated volume forms an exact replay world for view rendering and spatial verification: unvisited views can be rendered on demand, and localized predictions can be checked directly against reference masks. This grounded feedback directs targeted revision, while only changes that improve beyond measured seed noise are retained. Each accepted change triggers renewed attribution, allowing the dominant bottleneck to shift across rounds. On abdominal CT, attribution identifies perception as the dominant remaining limitation. Revising that level enables ReVision3D to achieve 79% liver recall and 83% kidney recall at under 0.4 false positives per patient, outperforming the evaluated frozen
multimodal foundation models, with the largest gains on small lesions. Our framework is public available with interactive demo in this project page: \url{https://leeh43.github.io/ReVision3D/}
Read the full abstract ▾
All authors Ho Hin Lee, Yuyin Zhou, Yannan Yu, Shi Gu, Yifan Wu
Human-Computer Interaction
VocalEyes: Speaker-Aware Augmented Reality Captioning through In-Conversation Registration
Yuxiao Wang, Xulong Tang, Chen Chen et al. (+1 more)
Co-located augmented reality (AR) captions make
speech readable, but they can separate an utterance from the person who produced it. In unfamiliar groups, losing that source complicates immediate responses and later review: users must recover not only what was said, but also who said it. Conventional diarization returns anonymous clusters, while speaker recognition typically assumes pre-meeting enrollment. We built VocalEyes, a speaker-aware AR captioning system that creates named voice profiles from natural self-introductions. The interface coordinates speaker-attributed captions, a fixed profile card, and a visual cue that marks the articulating face. In a controlled within-subjects study with 20 participants who reported typical hearing, VocalEyes identified speakers with 88.0% accuracy and increased participant speaker-tracking accuracy from 47.2% with caption-only AR to 87.3% with the complete interface. Participants also reported lower workload with the complete interface. These findings show how in-conversation registration can preserve speaker attribution across live captions and meeting records in scripted small-group meetings.
Read the full abstract ▾
All authors Yuxiao Wang, Xulong Tang, Chen Chen, Rawan alghofaili