Numerical Analysis
C1 Virtual Element Methods for the Optimal Control of Oseen Equations with Stream-Function Formulation
Arbaz Khan, David Mora, Alberth Silgado et al. (+1 more)
This work analyzes a $C^1$-conforming virtual element method for the optimal control of generalized Oseen equations, formulated using the stream-function on simply connected polygonal domains. The method is based on a conforming discretization in $H^2$ of arbitrary order $k \ge 2$. The discrete scheme considers an approximation of the state and co-state equations which involves a specifically designed operator for the convective term and a variational discretization of the control variable. We derive quasi-optimal a priori error estimates in the $H^1$ and $H^2$-norms for the stream-function, and in the $L^2$-norm for the control, under standard assumptions on the family of polygonal meshes. The proposed method recovers the fluid velocity, vorticity, and pressure using suitable projections. Finally, we report several numerical experiments to support the theoretical findings using different polygonal meshes including the cavity problem. We highlight that this analysis also covers OCPs governed by Brinkman and Stokes equation.
Read the full abstract ▾
All authors Arbaz Khan, David Mora, Alberth Silgado, Harpal Singh
Computation and Language
Measuring and Reducing Unusable Replies of LLM Agents
Yilin Jiang, Fei Tan, Xuanyu Yin et al. (+3 more)
People delegate multi-step work to LLM
agents and read only the reply that the
agent hands back. Current evaluation scores task completion and the faithfulness of reports, and it leaves open whether the requester can understand and use the reply. We call this property reply usability and measure it with a reader model that takes the requester's position and tests whether the reply can be interpreted from what the requester has seen, is in the requester's
language and answers the request. Its agreement with the majority of five annotators lies within the range of the individual annotators. Across eight models from seven families, 54% of 480 replies fail, and the best model still fails on 30%. Failed replies mostly point to material the requester has not seen or use labels that the
agent coined during its work. Stating explicit requirements for the reply reduces the failure rate from 0.52 to 0.43 together with errors and omissions, and a secondary model that rewrites the reply reduces it to 0.36, which human annotators confirm in a blind comparison. Reply usability can thus be scored alongside task success and improved with one appended message or one call to a secondary model.
Read the full abstract ▾
All authors Yilin Jiang, Fei Tan, Xuanyu Yin, Guanchu Wang, Xia Hu, Yutao Yue
Computational Engineering
BioPRM: Step-Level Consistency Verification of Biological Protocols
Bowen Shao, Ziyang Ling, Ronald Xu et al. (+1 more)
Process reward models (PRMs) provide fine-grained supervision for assessing intermediate steps in
language-model outputs, but their application to biological protocols presents distinct challenges. Protocol validity depends on both the appropriateness of individual operations and their consistency with the experimental objective and surrounding procedure, while experimental outcomes are typically unavailable during verification. We introduce BioPRM, a contextual process reward model for identifying procedural inconsistencies in structured biological protocols. We construct a supervision corpus from SciRecipe and protocols collected from protocols.io and Bio-protocol using LLM-assisted construction and source-specific review by personnel with biological expertise.
Read the full abstract ▾
All authors Bowen Shao, Ziyang Ling, Ronald Xu, Mingzhai Sun
Robotics
Accelerating VLA Inference with Perturbation Informed Execution
Jehun Lee, Hajun Lee, Jimin Ryu et al. (+4 more)
Action-chunking
vision-
language-action (VLA) models predict sequences of future
robot actions. Under fixed-horizon execution, the
robot executes a fixedlength prefix of each predicted chunk before invoking the policy again, leaving the remaining predictions unused. For a given number of executed actions, short execution horizons require more policy calls. Extending the execution horizon amortizes policy inference cost over more actions. However, uniformly applying long horizons across episodes can limit opportunities for precise corrections. To address this limitation, we propose PICES (Perturbation-Informed Chunk and Execution Horizon Selection), a training-free method that jointly selects an action chunk and the number of actions executed before the next policy call. Within a single policy call, the action expert generates a batch of action chunks from multiple initial noise samples and their locally perturbed counterparts, using the same conditioning features across all samples. PICES exploits differences between corresponding actions in each nominal chunk and its counterpart to determine candidate-specific execution horizons and select a nominal chunk for execution. Experiments on simulation
benchmarks and real-world manipulation tasks demonstrate that PICES achieves speedup by up to 2.3x in wall-clock policy inference time on Jetson Orin and Thor relative to fixed horizon baselines while improving the success rate.
Read the full abstract ▾
All authors Jehun Lee, Hajun Lee, Jimin Ryu, Youhan Lee, Beomseok Kang, Jonghyun Choi, Jae-Joon Kim
Computation and Language
HACHIMI-II: From Role-Play to Learner Behavior Modeling for Faithful Student Simulation
Yilin Jiang, Fei Tan, Xuanyu Yin et al. (+2 more)
Simulated students let researchers test tutoring systems and teaching strategies before real learners are available, but only if the simulation reproduces where a particular learner succeeds and fails. The common approach asks a large
language model to role-play a student, but a role does not model what this learner knows or will do next, so the model's own competence fills the gap. Simulated students perform at a level set by the model, differ little from one another, and seldom make the real learners' errors. We model the learner's behavior and recast student simulation as third-person prediction of the learner's next action. HACHIMI-II builds a student model from the learner's history, infers the learner's state for the current item or tutor turn, and compiles it into a behavior harness that constrains the next action. On three item-response
datasets, the Wasserstein-1 distance between simulated and real student ability is 2.4–8.4$\times$ smaller than that of the strongest baseline. On two dialogue
datasets, HACHIMI-II reproduces real student errors with the same knowledge type, locus, and mechanism 1.8–5.1$\times$ more often than the strongest baseline, and ablations trace the gains mainly to the explicit learner state. Predicting the learner makes capable models usable as simulated students.
Read the full abstract ▾
All authors Yilin Jiang, Fei Tan, Xuanyu Yin, Jing Leng, Aimin Zhou
Machine Learning
On Global Joint Lower Bounds in Zeroth-Order Nonconvex Optimization
Yuxuan Xia and Xiao-Tong Yuan
Recent work has sought to transfer first-order nonconvex optimization guarantees to zeroth-order methods through gradient
estimators, typically incurring a factor linear in $d$. \citet{kornowski2024} obtained an $\mathcal{O}(d\delta^{-1}\epsilon^{-3})$ oracle complexity for nonsmooth nonconvex optimization and asked whether its dependence on all three parameters is jointly optimal. Although the dimension dependence and the first-order dependence on $(\delta,\epsilon)$ are separately known to be unavoidable, a matching zeroth-order lower bound has remained open. We answer this question in the unrestricted full-space setting. For smooth
stochastic nonconvex optimization, we establish a scalar-oracle lower bound of $\Omega\!\left(dL_0^2\min\{\Delta H,L_0^2\}/\epsilon^4\right)$ assuming a smooth, globally lower-bounded population objective and a second-moment bound on sample Lipschitz constants. A smooth reduction then yields a lower bound for Goldstein stationarity, proving the joint minimax optimality of the dependence on $(d,\delta,\epsilon)$ under explicit high-dimensional and small-accuracy conditions. Crucially, our results allow
algorithms to query arbitrary points in $\mathbb{R}^d$, adaptively select sample-function labels, reuse the same sampled function at any number of locations, and output points without spatial restrictions. Thus, unlike lower bounds based on bounded query regions or fresh evaluation noise, our guarantees apply to a fully adaptive, reusable-sample scalar oracle. We also establish a separate noiseless exact-value lower bound against randomized
algorithms, and hence also against deterministic methods. Our proof combines a globally defined sequential nonconvex construction with an exact Gaussian scalar channel, multistage random-field estimates, and an antithetic finite-sample realization that preserves information hardness under adaptive reuse.
Read the full abstract ▾
Computer Vision
SPECTRA-VLA: Base-Fine Hyperspectral Token Transfer at Frozen Vision-Language-Action Interfaces
Chih-Chung Hsu
Hyperspectral imaging distinguishes RGB-similar objects, but a pretrained
vision-
language-action model needs a state its frozen decoder can use. SPECTRA-VLA provides a native-width spectral upgrade without retraining the visual encoder or action decoder. A learned continuous residual enriches each target
token through its own normalized false-color reference; projection, norm control and validation-calibrated injection regulate the change. Across 86 held-out acquisitions, category balanced accuracy rises from 0.812 to 0.883. With identical residuals and scale, own-
token addition improves reuse of an external category-derived probe on frozen decoder logits: 0.701 versus 0.590 with pooled replacement, at similar image-disjoint recognition. Five grouped tests covering the same 86 acquisitions recover within-category spectral shape with $R^2=0.802/0.337$ from continuous and posterior-code states. Category-matched spectral swaps further show that own-
token composition approximately doubles the target-specific recovery increment after frozen decoding. Spectral enrichment and receiving-
token preservation thus work together at the pretrained interface.
Read the full abstract ▾
Cryptography and Security
AWARE-RG: Abstraction Aware Explanation of Resiliency Graphs for Cyber Physical Systems
Shadaab Kawnain Bashir, Rakesh Podder, Philip D. Hopkins et al. (+3 more)
Understanding the security posture of cyber physical systems (CPS) requires
reasoning across both information technology (IT) and operational technology (OT). However, a security analyst often holds an incomplete, role-specific view of the underlying system which has most likely resulted from their knowledge limited by a need-to-know framework. Such an incomplete view can potentially lead them to incorrectly assess if a cyber attack produces an untoward physical consequence resulting in making uninformed decisions about system resilience. In this work, we present AWARE-RG (Abstraction Aware Explanation of Resiliency Graphs), a semi-automated, human-in-the-loop framework that provides an analyst with a role-bounded, need-to-know explanations of resiliency paths in a CPS. The AWARE-RG abstraction structure is derived using Formal Concept Analysis over MITRE ATT&CK for ICS tactics, ordered by the ICS Cyber Kill Chain. For valid attack-fault queries, plan repair and backward means-end analysis identify the missing dependencies, explain why the physical hazard is reachable, and suggest defensive strategies. For invalid attack-fault queries, AWARE-RG localizes the first abstraction level at which the path fails, and reports confirmed blocking conditions as hardening pointers.
Read the full abstract ▾
All authors Shadaab Kawnain Bashir, Rakesh Podder, Philip D. Hopkins, Sarath Sreedharan, Indrakshi Ray, Indrajit Ray
Computer Vision
Mapping Arctic Polynyas from Sea Ice Concentration Data Using Hierarchical Partitioning and Differentiated Region Growing: Sensitivity to Threshold and Product Choices
Tianyu Zhang, Haiyi Ren, Zhilun Zhang et al. (+4 more)
Accurately delineating Arctic coastal polynyas from sea ice concentration data remains challenging because of complex coastal geometry and spatially heterogeneous ice conditions. We develop a daily sea ice concentration (SIC) mapping framework based on hierarchical partitioning, connected-component analysis, and differentiated region growing for polynya and open-water regions. Applied to September-May ice seasons from 2002/03 to 2024/25, the framework achieves a mean overall accuracy of 96.74% and a mean kappa coefficient of 0.93 in the 63-scene visual assessment. Sensitivity experiments reveal a consistent pattern: the absolute magnitude of SIC-defined polynya extent is strongly configuration-dependent, whereas major temporal features are comparatively more stable. Relative to a 75% upper SIC threshold, seasonal extent integrals differ by 13.48%, 32.47%, and 65.04% at thresholds of 80%, 85%, and 90%, respectively, while the broad interannual structure remains recognizable. The response is also strongly regional and seasonal, with the largest threshold sensitivity in the Central Arctic Ocean, very weak sensitivity in the Gulf of St. Lawrence, and greater pan-Arctic curve separation from January onward. At an 80% threshold, product-comparison MAPE is 68.19% between the 6.25 and 25 km products and 11.47% between the 12.5 and 25 km products under their respective comparison periods and reference definitions. Regional product disagreement is likewise heterogeneous. Together, these results show that reproducible long-term polynya monitoring requires a fixed and explicitly documented combination of SIC product, threshold, and spatial classification rules, while broad temporal patterns can remain informative even when absolute extent differs substantially.
Read the full abstract ▾
All authors Tianyu Zhang, Haiyi Ren, Zhilun Zhang, Yang Hong, Chunlei Mi, Xiao Cheng, Fengming Hui
Hardware Architecture
MFSA: A Multi-Format Systolic Array with Native Micro Scaling Support
Jiayi Wang, Kearnan Bishop and Ang Li
AI workloads increasingly employ low-precision formats such as BF16 / FP16, FP8 variants, FP4, Micro Scaling (MX), and INT modes across models, layers, and execution stages to balance accuracy,
memory footprint, and throughput, which in turn requires hardware to support these formats in a flexible and efficient way. We present MFSA, a weight-stationary multi-format systolic array that achieves area efficiency through two architectural choices. At the PE level, MFSA uses dot-product-accumulator-based processing elements extended from an existing open-source trans-precision FPU to support reduced-precision formats (FP32/FP16/BF16/CFP8/FP4/INT16/INT8/INT4) with a shared datapath and proportional throughput scaling. At the array level, MFSA employs Online Block-Scale Rebasing (OBSR) for block-scaled formats, which folds each block scale into the running FP32 partial sum at block boundaries without adding a second cross-block accumulator, thereby reducing the additional overhead of block-scaling support. In TSMC 28 nm at 1 GHz, matched-throughput BF16/FP8/FP4 cascaded FMA-PE baselines are 1.5x/2.5x/4.5x larger than the single-format DPA-PE, the gap growing with subword parallelism. A routed 16x16 MFSA reaches a peak 0.5/1/2/4 TOPS of FP32/BF16/FP8/FP4, and OBSR cuts the incremental MX overhead by 64.2% in area and 67.5% in energy versus a naive MX implementation baseline, without hurting the numerical stability on real LLM traces. Adding support for all other formats based on a BF16+CFP8 systolic array costs 25.7% additional area. OBSR also extends to non-power-of-two block scales: folding the fractional part of an E4M3 scale into the MFPE dot product supports NVFP4 alongside OCP MX for 11.8% area and 7.3% power over a CFP8+FP4 base, less than half the cost of a naive implementation.
Read the full abstract ▾
Computation and Language
Selective Reasoning for Typed Decision Models: When to Start, Read, and Stop
Bin Zheng and Zheng Chen
Typed decision models need an interface that can use additional
reasoning while retaining candidate outputs. We train a shared candidate-answer reader on a frozen Qwen3.5-4B backbone to unify direct decisions with on-demand, interruptible
reasoning. The reader returns distributions from empty and partial
reasoning prefixes. A benefit gate starts
reasoning, a natural-state trigger requests explicit reads, and an
entropy rule accepts acquired answers and cancels generation. Measurements distinguish answer-query work, generated output, and pipeline time. Across 768 questions from ProofWriter, LogiQA 2.0, and ARC-Challenge, accuracy rises from 70.96% for direct reading to 84.38%. Relative to 512-
token terminal reading, accuracy improves by 7.29 percentage points with 2.25% more mean output work. Relative to 1,024-
token terminal reading, pipeline time falls by 46.30% with an accuracy difference of -1.17 points. Exact-prefix controls isolate the saving from interruption, while read-scheduling controls distinguish reduced observation work from shorter response time.
Read the full abstract ▾
Artificial Intelligence
Model What Matters: Decision-Guided Selective World Modeling for Language Agents
Maolin Ran, Minda Chen, Di Huang et al. (+3 more)
Reinforcement learning provides a direct mechanism for optimizing task objectives in large
language model-driven
agents, but task rewards are typically sparse trajectory-level signals that only evaluate task success, without directly supervising action-conditioned environment transitions, leaving the model with limited explicit understanding of action consequences and environment dynamics. Recent work introduces auxiliary supervision through policy and world modeling co-training, yet typically treats complete environmental observations uniformly as world modeling targets, overlooking the varying decision relevance of observation content. We propose DGS-WM (Decision-Guided Selective World Modeling), a decision-guided policy-world modeling co-training approach for
language agents. DGS-WM employs a Decision-Guided Observation Selection component that filters observation units with decision value as world modeling targets based on their support for subsequent policy responses, and a Confidence-Adaptive Weighting component that adaptively adjusts supervision strength according to the model's prediction confidence on selected targets. Together, these components form a decision-aware auxiliary world modeling loss, jointly optimized with the RL loss on the same policy model. Across multiple
benchmarks covering single-hop/multi-hop question answering and interactive web tasks, DGS-WM achieves consistent improvements under different model scales and RL
algorithms, demonstrating more stable and effective performance compared to full-observation world modeling methods.
Read the full abstract ▾
All authors Maolin Ran, Minda Chen, Di Huang, Wei Xiong, Fei Huang, Weiwen Liu
Human-Computer Interaction
"The Rose Garden Is a Cemetery": Spatial Dissonance and Divergent Public Experiences of an Indigenous Augmented Reality Tour
Grace Fujii, Vittorio Murtas, Sarah Sallee et al. (+5 more)
Community-authored augmented reality (AR) can contest dominant heritage narratives by juxtaposing stories with physical surroundings. We examine the Thámien Ohlone AR Tour, developed with members of the Ohlone Native American community at Mission Santa Clara and Santa Clara University. Combining paired pre/post surveys from 57 participants with collaborative thematic analysis, we compare reception among Ohlone community members, university affiliates, and Mission visitors. Spatial dissonance captures felt tensions when AR challenged familiar campus readings or when surroundings conflicted with Ohlone histories the AR affirmed, such as a garden's significance as a burial ground. Cultural frames shaped interpretation; contemporary people and relationships made Ohlone continuance tangible. Participants appreciated the tour and called for permanent physical acknowledgment. We propose staging reflective encounters, clarifying community-authored meanings, and using AR to prototype public acknowledgment and support community-directed advocacy. These findings foreground relationships to land and place, informed by Indigenous scholarship, in designing and evaluating AR.
Read the full abstract ▾
All authors Grace Fujii, Vittorio Murtas, Sarah Sallee, Isabella 'Amne Gomez, Lauren Baines, Danielle Heitmuller, Amy Lueck, Kai Lukoff
Machine Learning
Synthetic reaction data from transformation rules for graph-to-sequence pretraining in biodegradation pathway prediction
Irsyaad Rijwan, Liam Brydon, Aidan Jared et al. (+1 more)
The scarcity of observed biodegradation reactions constrains the training of product and pathway predictors. We present enviGraph, a framework that generates and curates synthetic reaction data, uses these data to pretrain a graph-to-sequence predictor, and fine-tunes the predictor on observed environmental reactions for product and recursive pathway prediction. Applying inherited environmental transformation rules to structures from PubChem, NORMAN SusDat and EPA DSSTox, followed by curation, produces 776,851 canonical parent-product pairs for pretraining. We compare this
dataset with three United States Patent and Trademark Office (USPTO) reaction
datasets: USPTO-50K, USPTO-MIT and USPTO-Stereo. We evaluate enviGraph and the sequence-based enviFormer using ten folds split by pathway on the EAWAG Biocatalysis/Biodegradation Database (BBD), regulatory pesticide biodegradation data (Soil) and activated-sludge biodegradation data (Sludge). For both predictors, synthetic pretraining gives the highest BBD mean precision-recall area under the curve (PR-AUC) among the evaluated pretraining
datasets for single-generation and multi-generation prediction. enviGraph achieves BBD single-generation PR-AUC of $0.202 \pm 0.050$ with synthetic pretraining, compared with $0.169 \pm 0.065$ for the retrospectively selected strongest USPTO condition, USPTO-Stereo (mean $\pm$ sample standard deviation across folds). Its exact BBD top-1 and top-5 accuracies with synthetic pretraining are 0.355 and 0.594. The strongest USPTO conditions give higher PR-AUC means than synthetic pretraining in most Soil and Sludge comparisons. enviGraph has higher Soil multi-generation PR-AUC means than enviFormer under each of the four main pretraining
datasets, and with synthetic pretraining it also leads enviFormer on BBD single-generation PR-AUC and exact top-1 and top-5 accuracy.
Read the full abstract ▾
All authors Irsyaad Rijwan, Liam Brydon, Aidan Jared, Jörg Simon Wicker
Computation and Language
J-tau: A Fully Localized Japanese Benchmark for Tool-Agent-User Interaction
Chihiro Yano, Jun Hirako, Hiroaki Yamagiwa et al. (+1 more)
We present J-tau, the first publicly available Japanese
benchmark for evaluating tool-using LLM
agents in interactive customer-support scenarios. While tau-bench is widely used to evaluate LLM
agents, it is English-centric and cannot evaluate
agents in other
languages. Existing multilingual extensions offer no public Japanese version and rely primarily on machine translation, leaving locale-specific entities such as addresses and currencies inconsistent with the target region. To enable reliable evaluation in Japanese, we carefully localize tau-bench through machine translation, entity adaptation, and human review. During this process, we also uncover and fix two flaws in the original tau-bench: invalid tasks and a score aggregation error that inflates certain models' results. Experiments show that J-tau yields fewer evaluation errors than a naively machine-translated counterpart and that our fixes resolve both flaws.
Read the full abstract ▾
All authors Chihiro Yano, Jun Hirako, Hiroaki Yamagiwa, Ryota Hirobuchi
Numerical Analysis
What Inverse Problems Can Be Solved Using Neural Networks?
A.S. Leonov and D.V. Lukyanenko
The relationship between classical methods for solving inverse problems and neural network methods is examined. An answer is provided to the question of what inverse problems can be solved using neural networks. The answer is that neural network
algorithms can solve only conditionally well-posed problems (well-posed according to Tikhonov). The reason is that the design of standard neural network
algorithms violates the well-known Bakushinsky veto from the theory of ill-posed problems. It requires that any method theoretically guaranteeing a stable solution to an ill-posed problem must depend explicitly on the error level of data. The article highlights the distinction between the concept of regularization (RA) in the theory of ill-posed problems and regularization as understood in neural network training, where Bakushinsky's veto is violated. Due to this violation, any changes to the neural network architecture, regularization during training, or training
dataset augmentation cannot alter the answer specified above. It is theoretically demonstrated that an ill-posed inverse problem can be solved only by using a parametric set of neural networks that explicitly depend on the known error levels (as parameters) of data. Accordingly, as an alternative to standard neural network
algorithms, \neural network based regularization
algorithms (NNBRAs) are proposed to solve ill-posed inverse problems. One approach to their construction involves using a regularized
dataset. Such a
dataset can be generated from perturbed inverse-problem data using a specific base RA explicitly depended on the error level of the data. Test solving the simplest finite-dimensional ill-posed inverse problem demonstrate that the accuracy of the NNBRA approximate solutions is comparable to that of the base RA. At the same time, errors of conventional neural network methods may be unacceptable.
Read the full abstract ▾
Machine Learning
Sparse Autoencoders Are a Shared Coordinate System for Symbolic Matching
Xiaocong Yang, Xuanyu Meng, Yuji Zhang et al. (+2 more)
Large
language models (LLMs) hold broad knowledge in one set of weights, but lack interpretability and trustworthy
reasoning, especially in high-stakes use cases. A neuro-symbolic model, with its interpretable architecture and System 2
reasoning capacity, is a promising alternative if built at the scale of LLMs; however, its symbolic backbone is usually constructed with human effort, so existing neuro-symbolic models are bottlenecked by the scope of the symbol component and usually domain-specific. A data-driven method could instead build a larger symbolic system by aligning and merging existing ones. We target its first, foundational step: matching units across these heterogeneous systems. Our method, SAE-IDF, encodes a symbol in its native context into a sparse code with a sparse autoencoder (SAE), re-weights each dimension by its rarity and matches across systems. On 12 tasks across 6 kinds of symbolic system, SAE-IDF outperforms the same LLM's dense baseline on all tasks with Gemma-2-9B and all but one with Llama-3.1-8B, by up to 45 points, consistently across SAE layers and configurations. SAE-IDF is also interpretable: every dimension of the sparse code has a human-readable meaning, so each match decomposes into named concepts (features). Our work paves the way to a universal symbolic backbone.
Read the full abstract ▾
All authors Xiaocong Yang, Xuanyu Meng, Yuji Zhang, Jiawei Han, ChengXiang Zhai
Robotics
Eye, Robot: Learning Expressive Gaze Dynamics via a VLM-Guided Transformer-VAE
Yuhang Hu, Junlin Lyu, Yuan Fang et al. (+6 more)
Gaze coordinates
attention in human interaction through coupled eye, head, and eyelid motion. A humanoid
robot must choose where to look while generating a suitable movement toward that target; fixed tracking rules alone do not model the temporal structure of human gaze. We separate these tasks with an asynchronous
vision-
language model that selects a scene referent, a reactive perception module that maintains fixation, and a Realistic Gaze
Transformer (RGT) that generates target-conditioned motion. RGT is a
Transformer-VAE trained on markerless human recordings retargeted to the
robot's 11-DoF joint space: self-supervised pretraining encodes recent full-head history, and autoregressive fine-tuning exposes the model to its own predictions during rollout. At inference, a four-dimensional binocular-eye trajectory conditions coordinated neck and eye motion; an auxiliary blink predictor triggers eyelid templates during playback. On a two-second
benchmark in which all controllers receive the same ground-truth target, RGT-Base obtains the lowest reported overall seven-joint MSE, and physical demonstrations show the integrated targeting and control pipeline. The evidence establishes
robot-space kinematic fidelity and real-time RGT inference; perceived naturalness and open-vocabulary target-selection accuracy remain questions for controlled evaluation.
Read the full abstract ▾
All authors Yuhang Hu, Junlin Lyu, Yuan Fang, Xiaoying Shen, Lechen Zhang, Jiong Lin, Judah Goldfeder, Steven Tian, Hod Lipson
Machine Learning · Cross-listed from stat.ML
Risk-Controlled DFT Selection for Machine-Learned Interatomic Potentials
Kun Ryu, Yeo Jin Jung, Shyue Ping Ong et al. (+2 more)
Automated materials discovery requires evaluating large pools of candidate configurations, with density functional theory (DFT) as a major throughput bottleneck. Pretrained machine-learned interatomic potentials (MLIPs) approximate DFT cheaply, but their errors vary by orders of magnitude across configurations, making it difficult to decide when to trust the MLIP predictions and when to fall back to DFT. We frame this decision as a risk-controlled selection problem and solve it within a conformal risk control (CRC) framework. Each configuration is mapped from atomic numbers and Cartesian coordinates to a fixed
geometric descriptor, which a lightweight predictor uses to estimate an MLIP-DFT disagreement score in energy, average force, and maximum force. CRC then calibrates this score into a selection threshold for DFT labeling such that the MLIP error on the unselected configurations, which keep their MLIP labels, stays below a user-chosen fraction $\alpha$ of the expected error. Under an identical guarantee across eight
dataset-MLIP pairs, our predictor routes 7% and 14% fewer configurations to DFT at $\alpha=0.3$ than committee baselines. Because committee disagreement overlooks errors the MLIPs share, our gains are largest when the DFT labels and MLIP training data differ in DFT functional and basis set, and narrow when the two agree. Without model access, the structure-only predictor also ranks errors as well as the target MLIP's latent representation and outperforms widely used descriptors such as Smooth Overlap of Atomic Positions (SOAP) and Atom-Centered
Symmetry Functions (ACSF).
Read the full abstract ▾
All authors Kun Ryu, Yeo Jin Jung, Shyue Ping Ong, Claire Donnat, Ying Shirley Meng
Computer Vision
Self-Conditioning Enables Deep Sequential Reasoning in Flow Matching
Zeyang Zhang, Linxiang Gao, Meiqi Gu et al. (+4 more)
Recent work has explored visual
reasoning through image generation, where models solve visual-
reasoning problems by directly generating solution images. Intuitively, iterative samplers such as flow matching are well suited to this task, since each sampling step may resemble one
reasoning step. However, in this work, from a
circuit complexity perspective, we show that this intuition is misleading. We prove that as long as the model outputs satisfy certain mild regularity conditions, the trajectory of the vanilla flow-matching sampler can be simulated by a constant number of sequential rounds of parallel model evaluations. Consequently, additional sampling steps cannot increase the expressive power of a constant-depth backbone model under the standard complexity-theoretic model of
transformers. We then reveal that self-conditioning, which conditions the model on the previous step's estimate of the final image, plays a previously unrecognized role in removing this bottleneck. Controlled experiments on diverse visual-
reasoning tasks show that flow matching with self-conditioning achieves higher accuracy and greater
reasoning depth than vanilla flow matching, and its performance improves with more sampling steps. Theoretically, we prove that with self-conditioning, a constant-depth backbone can achieve expressive power equivalent to that of space-bounded Turing machines. Our study suggests a design principle for future visual
reasoning research: carry more information between sampling steps, so that additional steps translate into deeper
reasoning.
Read the full abstract ▾
All authors Zeyang Zhang, Linxiang Gao, Meiqi Gu, Xingyan Chen, Minrui Luo, Kaifeng Lyu, Tianxing He
Robotics
E2DRL: End-to-End Differentiable Reinforcement Learning for 3D Obstacle Avoidance in Quadruped Robots
Cheng Fan, Bingyang Zhou, Gang Yang et al. (+7 more)
Differentiable reinforcement learning shows strong promise for
robot policy learning, but its application to legged locomotion has remained limited to blind walking or simulated 2D tasks. Extending it to end-to-end visual obstacle avoidance is challenging because hard collision constraints and early termination upon contact corrupt first-order gradients, trapping optimizers in local minima. We present E2DRL, which addresses this with a soft differentiable obstacle-interaction formulation: penetration penalties across multiple body keypoints with velocity-conditioned stop-gradient shaping to provide the first-order training signals for 3D obstacle avoidance. To realize a deployable perception-control system, a privileged teacher trained via Soft Analytic Policy Optimization (SAPO) in a differentiable simulator is distilled into a recurrent depth-based student via DAgger, then blended with a base locomotion policy using a terrain-aware gating module for deployment. In simulation, E2DRL achieves higher sample efficiency than PPO and demonstrates superior velocity-tracking performance and 3D obstacle-avoidance capability compared with both PPO and Duality-based DCBF NMPC. We present the first sim-to-real validation of end-to-end differentiable RL for 3D obstacle avoidance on a Unitree Go2 in static and dynamic environments.
Read the full abstract ▾
All authors Cheng Fan, Bingyang Zhou, Gang Yang, Zixuan Zhuang, Aoqian Zhang, Pengzhi Yang, Xin Liu, Chunzheng Wang, Yan Rui Tan, Fan Shi
Computation and Language
DAGFormer: Global Topology Prediction for Transformer Cross-Layer Connections
Xiaocong Yang, Yuren Hao and ChengXiang Zhai
We propose DAGFormer, a
Transformer language model whose cross-layer connections are planned by a jointly trained
topology predictor. Beyond the residual connections in a standard
Transformer, DAGFormer adds direct connections from earlier layers to later ones, and the predictor controls the strength of every connection based on input
tokens. Unlike existing cross-layer routing architectures, which set each layer's connections separately, DAGFormer plans the routing of the whole model at once. On matched OLMo-2 pairs from 75M to 1B parameters, DAGFormer lowers WikiText-2 perplexity by 17% to 25% over the vanilla
Transformer, and a 1B DAGFormer trained on 5B
tokens outperforms the vanilla model trained on 10B. Against four routing baselines with the same data and budget, it reaches the lowest perplexity at 75M, 300M and 1B. The gain carries over to 13 commonsense, science, reading and math evaluation tasks (2.0 to 2.5 points higher mean accuracy at 300M and 1B) and to instruction finetuning (63% to 70% AlpacaEval win rate against the vanilla
Transformer, leading every routing baseline), and under structured
pruning DAGFormer degrades the least in five of six settings.
Read the full abstract ▾
Computer Vision
Adaptive Observation Control for Active Visual Recognition
Dikai Li, Weijia Wang and Yuan-Gen Wang
Visual recognition models usually process a fixed view under a fixed computation budget, although images often benefit from different scales and amounts of spatial evidence. Active
vision can adapt by observing a coarse scene and then selecting informative fixations, but the public AdaptiveNN-DeiT-S pipeline still fixes both field of view and observation count. We extend this fixed-step recognizer with a controllable observation interface that adapts both the field of view and the number of fixations to the input. Specifically, the model predicts a per-fixation scale that sets its field of view, refines each selected crop with optional scale-gated foveation and a residual high-resolution detail-
token branch, and uses label-grounded stop heads for input-dependent early termination. Experiments across fine-grained
benchmarks, full ImageNet-1K, and ImageNet-A/R-derived classification splits show that the interface remains competitive with fixed-step references while exposing a controllable observation budget. The same checkpoint enables threshold-controlled accuracy-compute trade-offs without per-threshold retraining. On sequential ImageNet-1K, the learned stop rule outperforms fixed-step truncation of the same checkpoint, sustaining 81.9% top-1 using 2.45 of the four focus steps and exceeding three-step truncation at lower cost. On each
benchmark, a variant combining scale control and detail-
token fusion achieves the highest accuracy among the tested component-added non-exit variants. Our code is available at https://github.com/GZHU-DVL/LI-Dikai.
Read the full abstract ▾
Computer Vision
MagicGarment: Benchmarking Single-Image Standalone 3D Garment Reconstruction
Jia Chen, Ruyang Zhao, Jun Bai et al. (+3 more)
Single-image 3D reconstruction has advanced rapidly, yet standalone garments remain challenging due to thin-shell geometry, open boundaries, and layered structures. Existing
datasets and evaluation protocols provide limited support for systematic evaluation in this setting. We introduce MagicGarment, a
benchmark for single-image standalone 3D garment reconstruction with 1,518 professionally constructed assets across 17 composite garment types, aligned
multimodal annotations, and a unified evaluation protocol. We further establish a garment-aware reference baseline by adapting a pretrained image-to-3D backbone at two levels: Grounded Semantic Refinement (GSR) provides garment-focused visual conditioning, while Flow-Time-Route LoRA (FTR-LoRA) adapts the frozen 3D generative backbone using flow-timestep,
token-routing, and expert-load information. Experiments demonstrate MagicGarment's
benchmark utility and the effectiveness of garment-aware adaptation. Project page: https://1019538157.github.io/MagicGarment/.
Read the full abstract ▾
All authors Jia Chen, Ruyang Zhao, Jun Bai, Chao Huang, Saishang Zhong, Xinrong Hu
Artificial Intelligence
Are AI Decision Models Biased? A Case Study of Jev
Ilaria Imperatrice, Taisia Kameneva, Adam Eric Greenberg et al. (+1 more)
Do AI models designed for fast, structured decisions exhibit the cognitive and social biases observed in human judgment? We evaluate Jev, a model described as a System One decision-maker, using 41,500 responses across cognitive reflection tasks, five classical cognitive-bias paradigms, and a pricing experiment testing ethnic and gender bias. At the level of selected answers, the results are largely encouraging. We confirm previous findings that Jev performs extremely well on cognitive reflection problems. We also observe that it generally avoids the characteristic choice patterns associated with several well-documented human biases, and exhibits only small differences among demographic groups in the tested pricing scenario. However, this apparent robustness conceals important vulnerabilities. Its judgments are sensitive to irrelevant numerical information and the ordering of response options. Moreover, several cognitive-bias manipulations substantially affect returned probabilities even when selected answers remain unchanged. Most strikingly, Jev answers a well-known probability problem correctly in every response but violates the same underlying probability rule in every response to an adapted version. We investigate this discrepancy using 15,000 additional responses across 30 conjunction tasks. Jev violates the rule in 54% of responses, with accuracy varying dramatically across formulations and answer orders. These findings suggest that evaluating decision models solely on familiar
benchmarks and selected answers may substantially overstate their reliability in practical applications. They also identify vulnerabilities for developers to address and practical considerations for users integrating such models into automated decision-making systems.
Read the full abstract ▾
All authors Ilaria Imperatrice, Taisia Kameneva, Adam Eric Greenberg, Alessandro Romano
Robotics
F2A-ObjectNav: An Adaptive Agentic Architecture for Object-Goal Navigation
Seyed Ali Mirghasemi and Alireza Taheri
Object-goal navigation requires an embodied
agent to explore an unfamiliar environment, identify a target object, navigate toward candidate instances, and reliably determine whether the observed object satisfies the mission goal. This work investigates this problem through a two-stage development process. In Stage I, a fixed modular framework is used to examine combinations of exploration, object detection, and target validation methods. The results reveal clear trade-offs among navigation performance, validation reliability, execution time, and model-related cost, with no single fixed configuration remaining preferable across all evaluated conditions. These observations motivate F2A-ObjectNav (Fixed-to-Adaptive Object-Goal Navigation), an adaptive agentic architecture in which a rule-based Supervisor coordinates specialized components for navigation and exploration, object detection, target validation, semantic guidance, and Mission
Memory. The architecture uses event-driven recovery, strategy revision, candidate management, and conditional semantic guidance while retaining lightweight execution during normal operation. F2A-ObjectNav is evaluated over 25 episodes in each of AI2-THOR, RoboTHOR, and ProcTHOR, achieving success rate (SR) / success-weighted path length (SPL) values of 0.84/0.52, 0.40/0.22, and 0.44/0.37, respectively. In addition to task-level metrics, architecture-specific behavioral metrics are used to characterize semantic-guidance usage, strategy switching, recovery activation,
memory-supported behavior, and decision stability. The results show different patterns of adaptive intervention across the three environments, with higher intervention frequencies observed in RoboTHOR and ProcTHOR than in AI2-THOR.
Read the full abstract ▾
Robotics
Instruction-Conditioned Motion Control for Robotic Arms: Language-to-Code Decomposition and Reinforcement Learning
Fan Huang, Dezhong Tong, Changyu Chen et al. (+2 more)
Instruction-Conditioned Motion Control (ICMC) separates parameter specification, instruction generation, and code synthesis for
language-driven
robot control, making execution outcomes traceable to instructions and programs. We compare one-shot generation with ICMC under o1 and o4-mini on cube pick-and-place and letter-reshaping tasks for a UR5e arm in MuJoCo. We then train an open-weight instruction policy by GRPO through a frozen code generator on cube placement onto two- and five-cube letter layouts, averaging the rewards of five programs per instruction. The logged positive-reward rate rose from 31.6% to 35.3% (253/800 to 282/800) between the first and last five training steps. A log audit identifies positive binary labels associated with
geometric-failure messages: at least 19 in that run, 18 in the dense-reward run, and 5 in the run with one program per instruction. In one case, all five rewards were 1.0 while the log reports a 0.9515 m miss against a 0.05 m tolerance; the verdict came from the program's own output stream. We distinguish logged reward rates from independently verified task success and report descriptive results for each configuration's single training trajectory. We introduce an independent evaluation protocol that checks task completion against fixed specifications, separating
robot control from success assessment to support reproducible evaluation.
Read the full abstract ▾
All authors Fan Huang, Dezhong Tong, Changyu Chen, Haewoon Kwak, Jisun An
Robotics
PolyMorph: Learning Locomotion Policy for Cross-Embodiment Adaptation
Hyunsik Oh, Seunghun Jeon, Donghoon Youm et al. (+5 more)
Reinforcement learning has enabled robust locomotion for legged
robots, but learned policies are typically tied to a specific
robot morphology and require additional engineering when the number of legs, actuators, or mechanical properties change. We present PolyMorph, a morphology-conditioned framework that learns a single locomotion policy for heterogeneous legged
robots. PolyMorph converts each
robot's URDF into joint-link modules and combines a recurrent encoder, graph-based
Transformer, and per-joint decoder to generate actions across variable leg counts and joint configurations. To improve training stability, PolyMorph uses morphology-normalized rewards, adaptive
robot sampling, and URDF-derived PD-gain initialization. We evaluate PolyMorph in simulation across bipedal, tripedal, and quadrupedal
robots, including unseen morphology variants and platforms, and deploy the policy on real quadruped platforms operated in multiple configurations. The results show that a single PolyMorph policy generalizes across diverse
robot morphologies without per-
robot policy retraining.
Read the full abstract ▾
All authors Hyunsik Oh, Seunghun Jeon, Donghoon Youm, Jungwoo Hur, Hyeongjun Kim, Jeong Hyun Lee, Moonkyu Jung, Jemin Hwangbo
Machine Learning
Divergent Paths: Learning an Outcome-Predictive Representation of LLM Agent Trajectories
Alexander Gill, Guram Gogia and Francisco Guzmán
In this work, we reframe agentic trajectories as paths through a shared
embedding space of actions and environmental observations. We show that successful and failed rollouts of the same task separate in this space, with simple per-task discriminators predicting held-out rollout outcomes at up to 0.95 AUROC across three
agent benchmarks and three policy models. To exploit this signal across tasks, we introduce Precog-RM, a
transformer-based model that meta-learns a representation in which outcome prediction can be performed in a few-shot setting. We show that Precog-RM generalizes to unseen tasks and models, and gives confident predictions of trajectory success long before termination. Deployed as an early stopping controller for Group Relative Policy Optimization (GRPO) on Tau2-Bench, Precog-RM cuts training FLOPs by up to 47.3% while maintaining performance comparable to baseline GRPO.
Read the full abstract ▾
Computation and Language
Are We Really Measuring Forgetting? Pitfalls in Evaluating Machine Unlearning for Multimodal LLMs
Oscar Chew, Po-Yi Lu, Yi-Jie Cheng et al. (+4 more)
As machine unlearning for
multimodal large
language models (MLLMs) rapidly advances, rigorous evaluation of its effectiveness becomes increasingly important. However, existing
benchmarks largely inherit evaluation protocols from text-only unlearning and overlook the unique challenges of unlearning in
multimodal settings. In this work, we identify three major pitfalls that may lead to misleading conclusions: the lack of heldout evaluation to distinguish genuine concept-wise forgetting from instance-wise overfitting, the reliance on synthetic, fine-tuned knowledge rather than real-world knowledge acquired during pre-training, and unfair method comparisons caused by applying the same training settings to different unlearning methods. To address these challenges, we introduce GEMMU (Generalizable Evaluation for
Multimodal Machine Unlearning), a
benchmark built on real-world knowledge and a principled evaluation protocol. Re-evaluating representative unlearning methods under GEMMU reveals substantial generalization gaps and challenges conclusions drawn from previous
benchmarks. Our findings highlight the importance of rigorous evaluation for advancing
multimodal machine unlearning and provide guidelines for future
benchmark design.
Read the full abstract ▾
All authors Oscar Chew, Po-Yi Lu, Yi-Jie Cheng, Kunal Jain, Hsuan-Tien Lin, Zhengzhong Tu, Kuan-Hao Huang