Computation and Language
Same-Number Citation Swaps: Stress-Testing Jev as a Financial Evidence Judge
Chuhong Xu, Bo Su, Ziyao Chen et al. (+3 more)
Financial reports repeat values across periods, metrics and accounting lines, allowing an LLM-generated calculation to be numerically correct while citing the wrong financial role. We evaluate what probabilistic evidence verification adds beyond number matching using Jev as a source-support verifier for GPT-4.1-mini calculation traces. A signed-number-at-pointer baseline explains most recovery over exact quotation checks. To isolate the remaining role-recognition problem, we hold operands and arithmetic fixed, move citations between same-number
cells, and retain controls that express equivalent facts. These contrasts reveal both wrong-role citations that pass and valid alternative citations that are withheld. Explicit column labels improve selected wrong-role decisions while also lowering support for some equivalent evidence. A constructed follow-up on 36 new source pages, labeled by a non-author reviewer, extends this evaluation and exposes the same tradeoff between detecting role errors and retaining valid citations. The contribution is a controlled evaluation that identifies what a probabilistic financial verifier distinguishes when numerical matching is held fixed. For LLM-based financial assistants, it makes numerical correctness, cited-role support and acceptance outcomes separately assessable.
Read the full abstract ▾
All authors Chuhong Xu, Bo Su, Ziyao Chen, Ruiyang Xu, Shimeng Dai, Xinyu Qiu
Computer Vision
EC-RAG: Event Chain Retrieval-Augmented Generation for Long Video Understanding
Yuhao Qin, Junbo Wang, Yuke Li et al. (+1 more)
Current large
video-
language models (LVLMs) still face challenges when dealing with long
videos, mainly because frames are often processed independently, making it difficult to capture temporal dependencies across events. Although
retrieval-augmented approaches have been introduced to provide additional context, most of them operate at the frame or snippet level, which limits their ability to model how events evolve over time and relate to each other. In this paper, we propose Event Chain
Retrieval-Augmented Generation (EC-RAG), a training-free framework that organizes
video content into an explicit event chain before question answering. Instead of retrieving isolated frames or text segments, EC-RAG first partitions the
video into semantically coherent segments, represents each segment using multi-modal signals, and then links them into a structured chain that preserves temporal order and captures inter-event relationships. Given a query, the system identifies relevant events within this chain and gathers supporting evidence from the associated modalities. Our approach offers several practical advantages: (i) event-level abstraction that better reflects how
video content is naturally structured, enabling more reliable localization compared to frame-level
retrieval; (ii) structured multi-modal fusion that aggregates
speech, text, and visual cues at the event level, allowing complementary information to be more effectively utilized during
reasoning; and (iii) plug-and-play compatibility with existing LVLM backbones, requiring no additional training or reliance on proprietary models. Experiments on
Video-MME, MLVU, and LongVideoBench show that this event-centric design consistently outperforms frame-level
retrieval baselines, highlighting the importance of modeling temporal structure for long-
video understanding.
Read the full abstract ▾
All authors Yuhao Qin, Junbo Wang, Yuke Li, Yining Zhu
Computer Vision
PDB: Point-Based Deformation Blending for Facial Animation Retargeting
Sihun Cha, Hyeonseung Shin, Suah Yu et al. (+1 more)
Mesh-agnostic facial animation retargeting transfers expressions across meshes with different structures, but preserving facial motion without surface artifacts remains challenging. To address this, we present PDB, Point-Based Deformation Blending for facial animation retargeting. PDB predicts a compact set of deformed control points from a source neutral-expression pair and blending weights from the target neutral mesh. The weights are computed once per target and reused across frames, while the control points vary with each source expression. ReLU enforces non-negative weights and permits exact zeros, followed by row-wise normalization. The target mesh is reconstructed directly by multiplying the weights and control points, without a predefined cage, precomputed coordinates, a learned per-element deformation decoder, or a global reconstruction solve. Trained only with self-retargeting reconstruction supervision, PDB supports cross-identity transfer without paired cross-identity training expressions. Experiments demonstrate accurate retargeting, fast inference, and localized support in the learned weights. Joint evaluation of expression accuracy and local surface preservation shows reduced surface artifacts relative to the evaluated dense displacement method while retaining the intended motion. Perceptual evaluations further support expression fidelity and visual quality in both self- and cross-retargeting.
Read the full abstract ▾
All authors Sihun Cha, Hyeonseung Shin, Suah Yu, Junyong Noh
Machine Learning
Principled Under Pressure: Post-Training Decides Whether LLMs Act on Their Own Moral Judgment
Orion Reblitz-Richardson
An
agent that can say an action is wrong and then take it anyway is a different failure from one that does not know better, and evaluations of stated values cannot see it. We ask how often open models act against their own moral judgment under pressure, and what decides and reduces it. We build a pre-registered panel of 248 scenarios across five kinds of pressure. Each scenario is posed to one model in two separate calls, as the
agent choosing among fixed options and in the third person asking which is right; the model's own judgment is the reference, and the scenario's construction fixes which option counts as the violation. Every scenario has a twin with the pressure removed, and every model gets a positive control that bounds what the instrument can see. On OLMo-3-7B-Instruct, the model takes the action it judged wrong on one in five of the scenarios screened on its own actions, more often than with the pressure removed. Whether the gap appears depends on the post-training recipe: OLMo-3 and Meta's Llama-3.1-8B-Instruct carry it; Tulu 3, Qwen2.5-7B-Instruct and OpenAI's GPT-OSS-20B, read without
reasoning, show none within stated detection bars. Meta's recipe and Ai2's Tulu 3 share the same Llama-3.1 weights; only Meta's carries the gap. On both models that carry it,
reasoning about the stakes before acting moves the choice back toward the model's own judgment. What that deliberation tracks is the stated rule: where following a written rule harms an absent third party, it still moves OLMo-3 and GPT-OSS-20B toward the rule, not detectably diminished, while Llama-3.1's brake shrinks to about a seventh. Whether a model acts on its own moral judgment is therefore not settled by pretraining, and deliberation moves the action toward the stated rule, which protects people only when the rule does. The gap is a measurable target for post-training recipes, not a fixed property of the model.
Read the full abstract ▾
Machine Learning
MemFLoRA: Memory-Floor LoRA for CNN Adaptation at the Edge
Mehmet Emre Akbulut, Johannes Geier and Ulf Schlichtmann
On-device learning is necessary when the model encounters user-,sensor-, or environment-specific shifts after deployment. Although parameter-efficient fine-tuning (PEFT) methods, particularly Low-Rank Adaptation (LoRA) variants, enable efficient adaptation at the edge, the limiting resource for Convolutional Neural Network (CNN) adaptation is often not the number of trainable parameters but the activation state that must be retained until the backward pass. This paper introduces
Memory-Floor LoRA (MemFLoRA), a low-rank CNN adapter built around a
memory-first design principle rather than a direct application of
transformer-oriented LoRA. Instead of merely reducing trainable weights, we define an activation-
memory-floor criterion: trainable backward computations must not depend on full-width layer inputs. The resulting adapter freezes the down-projection, trains a scale-matched up-projection, and combines eval-mode backbone normalization with activation-minimal backward rules, reducing saved state to the low-rank branch. Evaluated on three Human Activity Recognition (HAR)
datasets and two CNN backbones under subject, body-location, and sensor-placement shifts, MemFLoRA reduces saved-activation
memory by 98.5-98.7% and peak training-state
memory by 94.9-97.3% relative to full fine-tuning, while matching or exceeding CNN PEFT baselines.
Read the full abstract ▾
Cryptography and Security
Semantic Behavioral Watermarking: Paraphrase-Robust and Forgery-Resistant Provenance for LLM Agents
Suxin Ji, Hungtao Wan, Shaoxuan Chen et al. (+1 more)
Behavioral watermarking embeds an owner identifier in an LLM
agent's high-level action choices, giving provenance without touching output
tokens. Prior
agent watermarks break in two ways. First, all three prior schemes bind the watermark to the exact action symbol, so renaming a tool desynchronizes decoding even when the observation is untouched; in AgentMark's own robustness test, paraphrasing the observation alone drops bit-recovery to 16.8%. Second, every prior
agent watermark studies only removal: none asks whether an adversary can forge a trajectory that verifies as someone else's, a question answered affirmatively for text watermarks (Jovanović et al., 2024). We present Semantic Behavioral Watermarking (SBW): watermarking over semantic action clusters under history conditioning, with the public-cluster bin replaced by keyed collision-resistant binning whose fresh-bucket assignment is provably unpredictable in the random-oracle model. Across five
agent models (3B-14B, four vendors) and three encoders the ordering holds on both
benchmarks: on ToolBench (600 trajectories per model) detection under rewriting is 0.49-0.66 for cluster-level versus 0.05-0.17 for exact-symbol at a permutation-calibrated 1% FPR, at 72-83% choice agreement against 22-27% for logit biasing; on ALFWorld (100 episodes per model) it is 0.92-0.97 versus 0.00-0.01. Keyed binning takes adaptive forgery from 100% to the false-positive floor at the primary operating point (bge, r=64). We also mark the boundary that guarantee does not cover: when the adversary copies the victim's own steps, shuffled splicing is neutralized (0.000 on Qwen2.5-3B) but chained replay remains at 0.76-0.98 across the five models, reported as open. Paraphrase robustness costs about half of the per-step watermark capacity. Code is available at https://anonymous.4open.science/r/SBW-
Agent-Watermark.
Read the full abstract ▾
All authors Suxin Ji, Hungtao Wan, Shaoxuan Chen, An Zhang
Information Theory
Algorithms for Sampling Self-Orthogonal and Totally Self-Orthogonal Codes in Odd Characteristic
Martin R. Albrecht, Benjamin Benčina and Russell W. F. Lai
We give an
algorithm that samples uniformly random linear codes of any hull dimension and type over finite fields of odd characteristic, implying the first
algorithm for sampling uniformly random self-orthogonal codes of any rate, including self-dual codes. Our
algorithm is a re-visitation of the
algorithm given by Albrecht, Benčina and Lai (EC'25), using the mass formulae proven by Li, Shi and Ling (IEEE Trans. Inf. Theory 71(1)). This allows us to instantiate code-based cryptographic schemes that rely on the hardness of Permutation Code Equivalence (PCE) on `random' self-dual codes for security and that were previously unable to sample them. Building on the observation by Bardet, Otmani and Saeed-Taha (ISIT'19) that Euclidean orthogonality is insufficient when considering PCE over finite extension fields due to non-trivial Galois
automorphisms, we study the behaviour of what we call total orthogonality, that is orthogonality with respect to all induced Galois geometries simultaneously. We characterise total orthogonality of vectors and codes, and give an
algorithm that samples linear codes with a total hull of a prescribed dimension; a subcode that acts as the hull in all Galois geometries of the ambient space. The
algorithm incurs a rate decrease by a factor equal to the extension degree, however, we argue why this may be necessary in the context of PCE and explore how it limits the practicality of our
algorithm. We consider the notion of Galois type of a linear code when Galois hulls are symmetric and show that all linear codes have constant Hermitian type.
Read the full abstract ▾
Computer Vision
Knowing When to Trust a Prior: Reliability-Gated Cue Fusion for Video Gaze Prediction
Lichen Zhu, Yueqian Lin, Yiheng Wang et al. (+2 more)
Video gaze prediction is led by gaze-trained models, yet gaze-free priors carry signal those models have not absorbed, if one knows when to trust them. We propose FocusGate, a gated ensemble of gaze-free priors whose members may abstain. A per-frame gate reads three shape statistics of a defocus map and selects the frames on which the
estimator is above chance on average, so rejected frames reduce to the base exactly, while midrank normalisation lets an all-zero prior abstain at zero parameters. Gated fusion is significantly positive on film, sports and web
video, whereas unconditional fusion is harmful on sports and null on web. Added to four supervised predictors, the NTIRE 2026 champion among them, FocusGate improves all sixteen model-domain
cells in shuffled AUC, fifteen significantly, one domain pre-registered and scored once, while adding only 1% to the champion's latency. Alone, it surpasses TASED-Net and UNISAL in shuffled AUC on film with a 16-frame causal mean.
Read the full abstract ▾
All authors Lichen Zhu, Yueqian Lin, Yiheng Wang, Hai "Helen" Li, Yiran Chen
Artificial Intelligence
ParanoiaEval: Benchmarking Unnecessary Defensive Work in Agentic Coding
Hanjun Luo, Xiucheng Zhang, Zhuoning Xu et al. (+4 more)
As coding
agents increasingly undertake real-world work autonomously, judging whether their risk treatments are warranted has become important. Existing work evaluates related
agent behaviors from separate perspectives, but lacks a systematic framework for unifying these behaviors. To bridge this gap, we introduce ParanoiaEval, the first
benchmark for unified evaluation of risk-treatment capabilities in coding
agents. Grounded in the well-established Avoidance-Transfer-Mitigation-Acceptance framework in software engineering risk management, ParanoiaEval operationalizes its 4 fundamental treatments for coding-
agent settings and contains 200 evidence-controlled repository-level task pairs, each differing only in treatment-defining evidence. We further introduce dedicated metrics for risk-treatment violations and evidence responsiveness, using a human-calibrated agentic judge for reliable evaluation. Large-scale experiments on 8 representative models and a post-hoc human study reveal that (I) unnecessary risk treatment occurs in 11.2%-58.7% of runs despite explicit evidence, with substantial variation across
agent configurations; (II) stronger task capability does not ensure more appropriate risk treatment, while treatment violations substantially harm developers' experience, establishing risk treatment as an independent capability dimension; and (III)
agents exhibit systematic patterns consistent with established risk-management findings, suggesting that knowledge from human practice can guide the diagnosis and improvement of this capability.
Read the full abstract ▾
All authors Hanjun Luo, Xiucheng Zhang, Zhuoning Xu, Zhimu Huang, Yingbin Jin, Xinfeng Li, Hanan Salam
Computation and Language
Evidence-Bound Reasoning: Neuro-Semantic Verification of Biomedical AI in Glioblastoma Radiogenomics
Mariya Miteva and Maria Nisheva-Pavlova
Background: Biomedical AI can generate plausible explanations without reliably verifying whether each statement is supported by patient-specific evidence. We developed a neuro-semantic verification framework that converts radiomic measurements into addressable evidence records and machine-checkable claims. Methods: UPenn-GBM radiomics were aligned with de novo CaPTk extraction from standardized MRI and expert-validated
segmentations in an independent multicenter cohort. The shared space comprised 1,728 features from T1, T1GD, T2, and FLAIR MRI across three tumor regions. Reference-defined semantic states were derived from 611 UPenn cases. We evaluated cross-cohort transportability, model-linked provenance, deterministic verification, controlled predictive degradation, and an LLM claim-extraction pilot; MGMT prediction served only as a transport stress test. Results: Median semantic-state agreement was 0.786 (weighted kappa 0.709), ranging from 0.918 for morphologic to 0.252 for intensity features. The external evidence ledger contained 1,655 model-linked records for 331 patients. The verifier achieved 100% exact-set accuracy in a 6,620-claim corruption
benchmark. In a 24-case pilot, GPT-5.6 Sol reproduced 72/72 prespecified atomic claims, and the frozen verifier recovered 24/24 expected conditions. During controlled degradation, ROC AUC declined from 0.899 to 0.500 while verification accuracy remained 1.000. External MGMT discrimination was weak (ROC AUC 0.543). Conclusions: Verifiability can be engineered and evaluated independently of predictive performance. LLMs may structure explanations, while final evidence-consistency checking remains deterministic.
Read the full abstract ▾
Computer Vision
Selective Transfer of RL Updates for Visual Reasoning
Suxin Ji, Hungtao Wan, Mingjun Liu et al. (+1 more)
Model merging provides a training-free way to transfer
reasoning capabilities from
language models to
vision-
language models (VLMs), but endpoint-based transfer can conflate pre-existing model differences with changes acquired during
reasoning post-training. We instead formulate capability transfer around the training-stage update, isolating the parameter changes induced by reinforcement learning (RL). Yet transferring this update in full remains suboptimal: we find that its components differ substantially in cross-model transferability, with dominant directions transferring more effectively than the complete update. Based on this finding, we introduce Selective-RL, which isolates the RL-stage update, retains its dominant
matrix-wise directions with magnitude preservation, and transfers them to the
language modules of a VLM. Across three model families and five visual-
reasoning benchmarks, Selective-RL improves full-update interpolation in 12 of 15 comparisons, including an 8.55 percentage-point MathVision gain on the Qwen recipient. Matched controls show that update magnitude or arbitrary low rank alone does not reproduce these gains. These results highlight a distinction between what is acquired during post-training and what remains transferable across models, providing a training-stage perspective on cross-model capability transfer. Code is available at https://anonymous.4open.science/r/selective-rl.
Read the full abstract ▾
All authors Suxin Ji, Hungtao Wan, Mingjun Liu, An Zhang
Numerical Analysis
Efficient localised model reduction for multiscale PDEs via Grassmannian interpolation
Christian Alber, Markus Bachmayr, Robert Scheichl et al. (+1 more)
Multiscale, parameter-dependent partial differential equations (PDEs) pose severe computational challenges due to strong coefficient heterogeneity and high-dimensional parameter spaces. We develop a
geometric interpolation approach within the multiscale generalized finite element method (MS-GFEM) that targets the most expensive component: computing parameter-dependent optimal local approximation spaces. Leveraging the spatial localization of MS-GFEM and assuming local parameter dependence, we decompose the global problem into parametrically low-dimensional local subproblems. The optimal subspaces for each parameter are identified as points on a Grassmann
manifold and approximated via Grassmann interpolation on sparse grids, which preserves the
geometric structure of these spaces while efficiently handling high-dimensional parameter spaces. The resulting localized model reduction method inherits the nearly exponential spatial convergence of MS-GFEM and the parametric convergence rates of sparse grids. Numerical experiments for
elliptic problems confirm the theoretical convergence results.
Read the full abstract ▾
All authors Christian Alber, Markus Bachmayr, Robert Scheichl, Huqing Yang
Robotics
Magnet-Aware Control of Legged Robots
J. Playan Garai, S. B. Djuve, C. McGreavy et al. (+1 more)
Autonomous
robots can increase uptime and reduce human exposure in Big Science facilities, but strong
magnetic fields needed for their operation corrupt sensors and induce pose-dependent mechanical wrenches that destabilize
robots and challenge conventional reactive controllers. This paper presents a control framework for modeling, estimating, and dynamically compensating for spatially varying
magnetic wrenches acting on legged
robots to improve robustness in these fields. We introduce a custom physics plugin for the MuJoCo simulator to model
magnetic forces on rigid-body elements, alongside an inverse field-estimation framework to infer the latent
magnetic field directly from quadruped dynamic responses and any number of sensor readings. Furthermore, we develop a Magnet-Aware Model Predictive Control (MPC) and Whole-Body Control (WBC) architecture that predicts and counteracts
magnetic perturbations during locomotion to increase the range of
magnetic fields in which the
robot can operate. The effectiveness of the framework is validated through both simulation and physical hardware experiments. We show our method increases the the maximum rejectable disturbances from
magnetic field in the force space by a factor of 2.5 and and between 1.6-2 times in torque space compared to a non-compensated system. Within the proposed
magnetic field, this constitutes an increase in the area in which the
robot can operate by 29,34% of which 10,84% would have previously caused an immediate collapse to non-compensated controllers.
Read the full abstract ▾
All authors J. Playan Garai, S. B. Djuve, C. McGreavy, M. Khadiv
Machine Learning · Cross-listed from stat.ML
Steering Diffusion Models to Rare Events with Sequential Monte Carlo
Aavash Subedi, Tim Reichelt, Christopher Williams et al. (+3 more)
Diffusion models are increasingly used as surrogates for expensive simulators in weather prediction, molecular dynamics, and materials design. In these models, computing the probability $p_0[E]$ of an event $E$ is difficult, especially when the event of interest is rare. A stable estimate using Monte Carlo becomes computationally intractable, requiring a growing sample size $\propto\!1/p_0[E]$ to compensate for an increasing rarity. In this paper, we present
Diffusion rare event sampling with Sequential Monte Carlo (DireSMC), a sequential Monte Carlo scheme that guides a population of weighted samples towards the rare event, giving access not only to samples but also to a calibrated estimate of its probability. We set up our guidance using an analytical relaxation of the event set, allowing the method to easily extend to a wide range of user-defined rare events. We validate our method on a toy problem with analytical solutions and on a score-based
climate emulator, where we obtain accurate rare-event probabilities on a range of rarities from $10^{-3}$ to $10^{-5}$, achieving net speed-ups of $9\times$ to $1413\times$ over Monte Carlo.
Read the full abstract ▾
All authors Aavash Subedi, Tim Reichelt, Christopher Williams, Philip Stier, Yee Whye Teh, Saifuddin Syed
Software Engineering
A Case Study in Assuring AI-Written Software
Lindsey Ferris and Sierra Bonilla
Software-engineering
agents can enable people without formal software training to build systems they could not otherwise implement and simultaneously can produce more code than even experts can meaningfully inspect. In both cases, exhaustive code review is not reliable as the sole basis for human control. We report a case study of a production healthcare platform built through coding
agents and governed by an operator without formal software-engineering training. Over time, its workflow grew into a human-led meta-
agent system where one
agent wrote code, other
agents supervised and reviewed it, and project rules carried lessons forward. The operator found that tests, monitors and reviewing
agents used to supervise the system were fallible. Some monitors measured proxies rather than outcomes, some audits failed silently, missing checks disappeared from reported results and one automated repair caused operational disruption. In this case, human control depended on keeping the intended outcome, the evidence used to judge it, the
agents' permissions and the final human decision were all tied to the same underlying objective.
Read the full abstract ▾
Robotics
Fast Non-Parametric Heteroscedastic Imitation Learning With Geometric Priors
Maximilian Mühlbauer, Arne Sachtler, Markus Knauer et al. (+4 more)
When learning probabilistic policies from human demonstrations, data-efficient learning and fast adaptations to new scenarios are key requirements. One popular way to achieve intuitive and reliable adaptations is through non-parametric, typically kernel-based, methods. However, existing solutions either fail to account for the geometry of
manifolds common in robotics, limiting data efficiency, or, when geometry-aware, provide unreliable uncertainty estimates or require retraining to adapt. We propose a non-parametric approach leveraging
geometric priors in scenarios of data scarcity and heteroscedastic uncertainties for probabilistic modeling. We utilize the method to formulate policies based on time or
robot state, where non-separable diagonal kernels allow capturing uncertainty relations between degrees of freedom for same-sized in- and outputs. Fast updates, requiring less than 3 ms for a trajectory involving both position and orientation are possible through an optimized formulation. Our approach supports both
manifold-valued input and
manifold-valued output with large orientation changes. Using task parameterization, adaptation to different object poses is easily possible. We evaluate the approach on a set of toy examples and on real
robot manipulation tasks both in autonomous execution and in shared control scenarios.
Read the full abstract ▾
All authors Maximilian Mühlbauer, Arne Sachtler, Markus Knauer, Cem Küçükgenç, Yanlong Huang, Alin Albu-Schäffer, João Silvério
Computer Vision
Stable Scores, Unstable Answers: Frame Phase and Option Order in Video Multiple-Choice Evaluation
Lichen Zhu, Yiheng Wang, Yueqian Lin et al. (+2 more)
Video-
language models are ranked by multiple-choice accuracy on frames from a uniform grid. The grid has two parameters, a rate and a phase, and
benchmarks report only the rate. The phase moves answers: two deployed samplers differing only by a half-step phase offset answer 23.6% of questions differently while scoring within a point, and across four releases from two families shifting only the phase changes roughly one answer in five after controlling option order. PHASEFUSION decodes three offset grids and averages the option posteriors. The grids are the polyphase components of the dense grid. Fusion matches a 32-frame single pass in accuracy within a prespecified margin (logit-scored) and cuts the answers a half-step shift of all three grids changes from 18.2% to 10.1%. Option order, which changes only the presentation, is flagged instead by a one-pass answer margin. Report the phase convention with the budget, or marginalize it.
Read the full abstract ▾
All authors Lichen Zhu, Yiheng Wang, Yueqian Lin, Hai "Helen" Li, Yiran Chen
Artificial Intelligence
SquidAgent: Parallelize Wisely, Coordinate Efficiently
Yexiong Lin, Shanshan Ye, Yu Yao et al. (+3 more)
LLM-based
agents solve complex multi-step tasks, but sequential execution incurs substantial latency. In principle, parallelizing work across multiple
agents should yield near-linear speedups. Yet existing parallel multi-
agent systems often run slower than a single-
agent baseline. We attribute this gap to two hidden costs that parallel execution incurs but a serial
agent avoids. First, there is a re-exploration cost: redundant effort spent by parallel workers reconstructing context that the orchestrator already possesses, such as prior decisions, that would otherwise be inherited implicitly in a serial execution. Second, there is an
alignment cost: the overhead required to reconcile inconsistencies across independently generated outputs. We thus derive a principled decision criterion: a layer should be parallelized only when its critical-path cost, plus re-exploration and
alignment overheads, is lower than the corresponding serial cost. While this criterion is naturally expressed in wall-clock time, we observe that LLMs are poorly calibrated when asked to estimate task duration. To address this, we instead measure cost in predicted output
tokens, which we empirically find LLMs can estimate substantially more reliably than wall-clock time. Building on this
token-based criterion, we propose SquidAgent. It estimates all
token budgets in a single planning step, forks each worker directly from the orchestrator's session to eliminate re-exploration cost, and replaces post-hoc reconciliation with a pre-generated shared convention block that converts
alignment into a bounded upfront cost. A deterministic scheduler then applies the criterion layer by layer. Empirically, SquidAgent achieves a 2.2$\times$ mean throughput improvement and a 2.6$\times$ mean wall-time speedup over Claude Code, and a 2.0$\times$ throughput improvement over the strongest multi-
agent baseline.
Read the full abstract ▾
All authors Yexiong Lin, Shanshan Ye, Yu Yao, Zhen Fang, Bo Han, Tongliang Liu
Systems and Control
Distributed Model-Free Turbine Repositioning for Wake Overlap Minimization in Floating Offshore Wind Farms
Zekai Chen and Ryozo Nagamune
This paper presents a model-free method for turbine repositioning control in floating offshore wind farms. The method uses a distributed online optimization framework to mitigate the wake effect. Conventional approaches rely on centralized, model-based control architectures, which suffer from poor practical feasibility. To overcome this limitation and address nonconvexity and inaccessible gradient information, we incorporate physics-informed knowledge of wake dynamics into the control system design. We demonstrate the effectiveness of the proposed method by comparing it with a centralized, model-based baseline in mid-fidelity simulations. Results indicate that the proposed method achieves slightly better performance while significantly reducing computational cost.
Read the full abstract ▾
Data Structures and Algorithms
Parametrized Exact Hardware-Software Partitioning
Cameron Ibrahim, S M Ferdous, Erdal Mutlu et al. (+2 more)
When optimizing computing architecture for specific computationally intensive tasks, such as evaluating or training a neural network, it is important to identify what computational subtasks will offer the greatest decrease in cost (e.g., wall clock time or energy usage). This problem is known as Hardware-Software (HS) Partitioning, and it has a variety of formulations, many of which are NP-Hard. In this paper, we will define a family of HS Partitioning formulations which admit an exact fixed parameter tractable
algorithm based on the directed pathwidth of the given task graph and show that this family of problems contains multiple existing formulations such as makespan minimization. Finally, we examine task graphs with small directed pathwidth that arise in real world applications and show that our
algorithm can provide a speed up of up to 200x over a comparable linear programming approach utilizing the Gurobi ILP Library.
Read the full abstract ▾
All authors Cameron Ibrahim, S M Ferdous, Erdal Mutlu, Ilya Safro, Mahantesh Halappanavar
Robotics
HygieneRoboBench: Benchmarking Hygiene-Aware Planning for Household Robots
Yurun Chen, Josh Qixuan Sun, Jason Qin et al. (+4 more)
Contact with contaminated objects can spread hazards through a household
robot's grippers, tools, and shared surfaces, while new contacts can make an existing plan unsafe. Existing
benchmarks do not jointly assess how planners identify hygiene risks from contact history and plan safe continuations after new contact events. Planners must do so within time and resource limits while respecting user priorities. We introduce HygieneRoboBench, with 624 instances across 134 task families, to evaluate safe resolution of household tasks from a given execution history. Tasks capture contamination through two grippers and shared objects, treatment costs, and user priorities. We combine controlled history, profile, and event comparisons with independent plan evaluation. These assess safe resolution, cost efficiency under user priorities, and responses to contact events. Evaluation of LLM-based and symbolic planners shows that safely completing a task does not guarantee the lowest execution costs under the user's priorities. To address this problem, we introduce Hygiene-NSP. It combines LLM-based grounding, contact-history reconstruction, and CP-SAT to jointly plan hygiene treatment and task execution under user priorities. Hygiene-NSP achieves safe resolution and optimal safe resolution rates of 94.4% and 90.4%, respectively. Both rates are higher than those of the evaluated baseline planners on the full
dataset. Project page: https://euron-zc.github.io/HygieneRoboBench/.
Read the full abstract ▾
All authors Yurun Chen, Josh Qixuan Sun, Jason Qin, Chengtai Li, Tianyi Wang, Mark Crowley, Wentao Zhu
Robotics
RIWANav: Recursive World-Action Models with Self-Improvement for Urban Navigation
Jing Xie, Shouwei Ruan, Yubin Wang et al. (+4 more)
Long-horizon urban
navigation requires sequential local decisions whose errors can compound over time. Imitation learning (IL) rarely learns from failures, while physical trial-and-error reinforcement learning (RL) is costly. Action-conditioned world models can provide imagined feedback by predicting visual consequences for candidate actions. However, a frozen world model may become less reliable as the policy evolves. In this paper, we introduce RIWANAV, a post-training framework that casts the coupled adaptation of a world model and an action model (policy) as task-specific recursive self-improvement (RSI). Each cycle alternates two updates. The world model evaluates policy actions through imagined outcomes, providing comparative feedback for group-relative policy optimization (GRPO). The improved policy then constructs a grounded self-curriculum, selecting expert-consistent action-
video pairs by behavioral novelty and prediction error. The refined world model supplies feedback for the next policy update, closing the recursive self-improvement loop. Experiments show that RIWANAV outperforms training baselines and prior methods, validating the proposed recursive self-improvement loop between the policy and world model. Real-world trials further demonstrate its practical applicability.
Read the full abstract ▾
All authors Jing Xie, Shouwei Ruan, Yubin Wang, Yuxiang Zhang, Haitao Yang, Songchang Jin, Dianxi Shi
Computer Vision
Forensic Reserve: Eliciting Latent Knowledge for Image Forgery Detection
Jiahua Li, Zixu John, Tom Zhong et al. (+5 more)
As generated images become increasingly realistic, reliable forgery detection is essential for maintaining trust in visual information. However, existing methods primarily rely on task-specific supervision to adapt
vision foundation model representations, without fully exploiting internal forensic knowledge to guide detection. To address this limitation, we propose Reserve-Guided Elicitation (RGE), a framework that treats sparse, origin-sensitive internal components in pretrained models as a forensic reserve and translates their localization into structural constraints for lightweight adaptation. Specifically, we first use the Forensic Lens (F-lens) to decompose activations across layers and
token groups into independent components and globally screen them by their response differences between real and generated images, identifying reserve sites and directions. Next, we map the selected directions back to hidden-state space to construct fixed reserve subspaces and insert Forensic Reserve Adapters (FRA) only at the identified sites. Finally, with the backbone parameters, previously fitted reference classifier, and subspace bases fixed, we train only the FRA coefficient maps to generate input-dependent residual updates constrained to the corresponding subspaces, strengthening existing forensic responses. Using only 500 labeled training images and a trainable parameter budget below 0.2% of the backbone, RGE achieves competitive performance across three detection
benchmarks without target-
benchmark adaptation. Furthermore, RGE consistently improves over the corresponding frozen detectors across eight encoders spanning self-supervised and
vision-
language pretraining, eliciting a latent forensic capacity broadly shared across pretrained
vision models.
Read the full abstract ▾
All authors Jiahua Li, Zixu John, Tom Zhong, Fuping Wu, Tianhao Xu, Jianqing Zheng, Yuanhan Mo, Fei Shen
Robotics
Feeling Through the Load: Compliant Quadruped Locomotion under Payload Interactions
Shaunak A. Mehta, Mayank Mishra, Prajit KrisshnaKumar et al. (+2 more)
Quadruped
robots are increasingly expected to carry objects while moving through human environments. But what happens when a person interacts directly with the payload rather than with the
robot? If the payload is unrestrained, the
robot must distinguish intentional external interactions from ordinary payload motion, while still keeping the load balanced and maintaining stable locomotion. How can a quadruped infer and compliantly respond to such interactions using only onboard measurements? In this work, we develop a force-aware locomotion framework that treats payload interactions as commands that shape the motion of the combined
robot-payload system. Our approach separates the learning of force-aware locomotion and force estimation on an unrestrained payload. We combine a compliant load-carrying policy with a causal force
estimator, trained through
estimator-in-the-loop data aggregation and finetuning, to predict interactions from onboard
robot measurements. Our simulations and real-world experiments show that the resulting controller can maintain stable payload-carrying locomotion, yield compliantly to external interactions, and use the inferred force to support human-guided changes in the
robot's trajectory.
Read the full abstract ▾
All authors Shaunak A. Mehta, Mayank Mishra, Prajit KrisshnaKumar, Sebastian Scherer, Koichiro Niinuma
Computation and Language
Towards In-Parameter Memory Augmentation for Large Language Models
Haoyu Huang, Zhongwei Xie, Jiaxin Bai et al. (+6 more)
Recently Large
Language Models (LLMs) and LLM-based
agents increasingly need to incorporate knowledge acquired after pretraining, e.g., domain facts, user preferences, documents, and interaction experience. In-context learning (ICL) and ICL-based
agent harness remain flexible, but they consume context capacity and incur repeated discretized encoding cost that grows with context length. In-parameter
memory offers a complementary substrate: reusable
memory information is represented in model parameters, adapters, or other parameter-like objects that are composed into the forward pass at inference time. This survey focuses on methods that augment LLMs with such parametric
memory at deployment: a
memory-bearing parameter object is plugged into the forward pass during inference, whether it is acquired before or during deployment. We organize the landscape with two orthogonal axes: Parameter Placement, which includes
Embedding,
Attention, FFN layers, or Hybrid when two or more layers are used; and Parameter Acquisition Time, which distinguishes methods whose
memory object is acquired during deployment (online) from those acquired before it (offline). We clarify boundaries, conduct comparisons, and discuss open directions in interference, safety, co-design with ICL, and recursive self-improvement.
Read the full abstract ▾
All authors Haoyu Huang, Zhongwei Xie, Jiaxin Bai, Yisen Gao, Hong Ting Tsang, Wuganjing Song, Huihao Jing, Yufei Li, Yangqiu Song
Artificial Intelligence
Parallel Predictive World Models for Accurate and Efficient Long-Horizon Planning
Wanjin Feng, Baobin Zhang, Ao Yu et al. (+3 more)
Long-horizon world-model planning typically relies on autoregressive rollouts, where predicted states are repeatedly fed back into the model. This preserves temporal structure but creates a horizon-length sequential path and exposes later predictions to recursive decoded-state feedback. We introduce Parallel Predictive World Models (PPWM), which predict a finite-horizon trajectory in parallel while retaining causal interaction among future representations. Each horizon is conditioned on its causal action prefix, and future representations interact before decoding, separating temporal causality from state-by-state output recursion. We formalize this distinction by viewing autoregressive rollout as a causal trajectory map and identifying the decoded-state feedback pathway removed by PPWM. Across four visual-control tasks, PPWM achieves the lowest long-horizon prediction error and the highest Cross-
Entropy Method (CEM) simulator success among the evaluated predictive interfaces. Meanwhile, PPWM achieves more than a 3$\times$ average CEM planning speedup over the autoregressive LeWM baseline. These results suggest that accurate and efficient long-horizon world-model planning does not require state-by-state autoregression, but can instead be achieved through parallel causal trajectory prediction.
Read the full abstract ▾
All authors Wanjin Feng, Baobin Zhang, Ao Yu, Shibo Feng, Xi Wang, Xingyu Gao
Artificial Intelligence · Cross-listed from stat.ML
Feature Information Dynamics in Diffusion
Jia-Shu Pan, Tao Zhang, Yufei Huang et al. (+2 more)
Diffusion models generate data through a continuum of denoising problems, and are widely observed to reveal coarse structure before fine detail. Yet, this intuition is mostly empirical and qualitative. We introduce feature information dynamics, an information-theoretic framework for localizing when a feature is generated during
diffusion. Using the I-MMSE identity, we connect the rate of feature mutual information change to a gap between optimal unconditional and feature-conditional denoising losses, yielding practical
estimators for feature information density. We further develop a chained decomposition that separates shared from incremental information in a feature hierarchy. We use this framework first to quantitatively confirm spectral autoregression in pixel
diffusion, and then to extend the analysis beyond frequency: under a class $\to$ mask $\to$ Canny conditioning chain, the per-feature information densities differ across pixel, SDVAE, VAVAE, and RAE, exposing fundamental differences between these representations and suggesting that ordered generation could be beneficial for training
diffusion models. Our code is available at https://github.com/AI4Science-WestlakeU/feature-information-dynamics.
Read the full abstract ▾
All authors Jia-Shu Pan, Tao Zhang, Yufei Huang, Yanjun Sheng, Tailin Wu
Machine Learning
Early Memory Selection for Balanced Adam
Alberto Fernández-Hernández, Cristian Pérez-Corral, Jose I. Mestre et al. (+2 more)
We propose a method for choosing the shared
memory parameter $\beta_1=\beta_2=\beta$ in Adam from a short pilot training. The selected $\beta$ remains fixed during the subsequent full training. A local model of Adam's normalized direction balances sampling variability against the delay introduced by averaging past gradients. This balance gives a cubic
memory rule, whose two coefficients are estimated from gradient probes at a few pilot checkpoints. The
estimator uses the numerator and denominator jointly, preserving their covariance. With a 200-update pilot and sixteen probe gradients at each of four checkpoints, a seed-matched retrospective evaluation on eleven
vision and
language workloads reduces mean relative validation gap by 40.7% and worst-quarter mean gap by 44.3% against the grid representative of shared $\beta=0.95$. The mean gap is also 32.3% lower than that of the best constant $\beta$ chosen across all eleven workloads.
Read the full abstract ▾
All authors Alberto Fernández-Hernández, Cristian Pérez-Corral, Jose I. Mestre, Manuel F. Dolz, Enrique S. Quintana-Ortí
Networking
Agentic RCA for Internet-Scale Services Using Constrained Creativity
Sayan Sinha, Vipul Harsh, B. Aditya Prakash et al. (+2 more)
System administrators of Internet-scale services need to resolve failure incidents to maintain reliability of such services. Ideally, we want a troubleshooting system to be: (1) expressive to known and unknown incidents with high accuracy; (2) cost efficient at scale; (3) explainable to provide actionable insights operators can act on; and (4) entail low effort from the operators. Unfortunately, most existing systems, including emerging LLM-assisted agentic workflows and structured frameworks for authoring diverse RCA
algorithms fall short of achieving all four requirements. We present E4, a novel agentic system for troubleshooting for Internet-scale services. E4 embodies the paradigm of constrained creativity that combines the best of LLM-assisted automation and exploration with the explainability and efficiency of a structured approach. Instead of allowing an LLM
agent to write arbitrary code or generate arbitrary responses, we provide the
agent a restricted DSL to generate its response via simple loop-free data flow programs. This DSL, equipped with high level operators for troubleshooting, makes E4's output accurate, verifiable and explainable. On a mix of synthetic and real-world workloads, E4 achieves up to 62% better accuracy compared to state-of-the-art solutions, while providing more explainable responses at up to 12x reduced cost.
Read the full abstract ▾
All authors Sayan Sinha, Vipul Harsh, B. Aditya Prakash, Vyas Sekar, Hui Zhang
Artificial Intelligence
Recursive Game Creator: An Agentic Product-Level Experience-Oriented Game Harness
Jiajun Chen, Haoyu Wu, Mingda Jia et al. (+1 more)
Recent game design
agents have made substantial progress in generating playable games. However, program correctness does not ensure an enjoyable experience for players. We present Recursive Game Creator, an experience-oriented harness to advance agentic game development from rough game prototypes into entertaining games. Recursive Game Creator organizes recursive development around four components: Designer, Builder, Player, and Reviewer. The Designer translates user instructions and Reviewer's feedback into detailed plans. The Builder turns these plans into candidate games. The coding-native Player creates and executes reusable policies through programmatic interfaces to efficiently collect diverse gameplay trajectories, mitigating evaluation bias caused by slow GUI-based collection. The Reviewer uses carefully designed trajectory-based metrics to induce player preferences, integrating with visual evidence and explicit textual preferences to evaluate games against game-specific criteria. Finally, the Reviewer accepts the better version and provides improvement reviews for the next round, closing the recursive loop. Our method achieves state-of-the-art overall performance of 77.89 on GameCraft-Bench. On GameASG-Bench, it achieves a strict task success rate of 53.2%, a 34.1% improvement over the same-model baseline, and the highest mean runtime-check pass rate at 93.4% among compared methods. A user study shows longer playtime and higher ratings. Project page is at: https://imbaldy.github.io/recursive-game-creator/.
Read the full abstract ▾
All authors Jiajun Chen, Haoyu Wu, Mingda Jia, Xihui Liu