Sound
Audio Token Attention Is Predictable Before the Language Model Runs
Kyoungjun Park, Yunzhe Li and Lili Qiu
A large audio
language model (LALM) turns a minute of
speech into 750-1,500
tokens and prefills every one. Image-
token pruning often cuts after the
language model's first layers, where image
tokens draw little
attention. Audio
tokens draw much more
attention there, and their ranking is still far from final, so audio needs a ranking before the
language model runs. Surprisingly, the
attention an audio
token will receive across the
language model is already linearly predictable from its encoder output, before the
language model runs. A linear map, fitted in closed form without labels, predicts this all-layer
attention ranking at $\rho \geq .69$ on eleven of thirteen LALMs. Our method, Triage, cuts audio
tokens by this prediction and, on multiple choice, cuts again at layer 2, correcting the prediction with the
attention observed there. Triage sets its compression without labels, under two budgets that limit how far its output may differ from the model's own full-audio output. At the conservative budget, its word error rate and accuracy stay within .04 of full audio. At the aggressive budget, Triage beats every baseline in all twelve transcription cases. On multiple choice, at 2.2-5x compression, it outperforms DART, the strongest baseline on average, by .043 in mean accuracy. Because it cuts before the
language model, it raises the audio that fits in Qwen2.5-Omni-3B's context window from 21.8 to about 62 minutes. At its most compressive point, Triage lets one GPU serve 4x as many concurrent 5-minute streams of that model. Project page: https://audio-triage.github.io
Read the full abstract ▾
Machine Learning
On Parameters of Nonlinear Scalar Dynamics from Video: Invariants, Calibration, and Identifiability
Wenjie Wang, Yuanyuan Wang, Zixiang Jiang et al. (+2 more)
Physical parameter estimation from
video aims to recover the parameters of a known family of governing dynamical equations from pixel observations. Existing identifiability theory for this setting has focused on linear time-invariant (LTI) second-order systems, leaving open what can be identified for nonlinear scalar dynamics. We develop an identifiability theory for nonlinear scalar second-order ODEs, organized by how their velocity dependence interacts with changes of the learned state coordinate. Under a shared non-collapsed state map and explicit same-state velocity-coverage conditions, we show that parameter identifiability depends on the ODE family: some parameters are uniquely identifiable, while in other families only invariant parameter combinations are identifiable or external physical calibration is required. For laws that are at most linear in velocity, compatibility forces affine coordinate
alignment, yielding explicit parameter relations, invariants, and calibration conditions. This affine conclusion extends to broader finite velocity-feature families when coordinate
curvature can be separated from the declared velocity dependence. For families admitting a squared-velocity term, nonlinear coordinate ambiguity can remain; a law-derived normalization instead enables affine comparison between canonical laws. Experiments on synthetic systems and real pendulum and free-fall
videos support the predicted parameter relations, coverage effects, and calibration requirements.
Read the full abstract ▾
All authors Wenjie Wang, Yuanyuan Wang, Zixiang Jiang, Shaoan Xie, Mingming Gong
Robotics
DODGER: Safety-Guided Reinforcement Learning for Robot Navigation Among Dynamic Obstacles
Sanghyuk Park, Kwanwoo Lee, Taekyung Kim et al. (+2 more)
Robots operating in human-centered environments must safely navigate among multiple dynamic obstacles to avoid collisions with people and surrounding infrastructure. Control barrier functions (CBFs) provide an effective mechanism for safety filtering, and recent CBF-based reinforcement learning (RL) methods embed such safety information into learned policies. However, executing only safety-filtered actions during training can restrict policy exploration, a limitation that becomes particularly consequential in dynamic scenes where safety depends on relative
robot-obstacle motion. We propose DODGER, a safety-guided RL framework that directly executes policy-generated actions to drive training rollouts while using CBF-filtered references and constraint violations to shape the policy toward collision-avoidance behavior. We evaluate DODGER through a Dubins-car safety analysis and demonstrate goal-directed
navigation among multiple dynamic obstacles in full-order
humanoid simulation and real-world
humanoid experiments using
LiDAR-based perception, without a runtime safety filter.
Read the full abstract ▾
All authors Sanghyuk Park, Kwanwoo Lee, Taekyung Kim, Seohyeon Lim, Yisoo Lee
Cryptography and Security
SoK: A Large-Scale Empirical Study of Emulation-Based Dynamic Analysis Research for ARM Cortex-M Firmware (Extended Version)
Hongyuan Li, Ke Wang, Wei Zhou et al. (+1 more)
Microcontroller (MCU)-based devices are increasingly pervasive, making efficient, scalable firmware security analysis critical. Recent firmware re-hosting work enables automated vulnerability assessment, yet two gaps remain. First, existing tools are evaluated on limited, heavily overlapping
datasets, undermining the generalizability of reported results. Second, prior research advances the state of the art along isolated dimensions, such as emulation, fuzzing, or bug diagnosis, without a holistic understanding of how these components interact and complement one another in dynamic analysis workflows. Building on recently released large-scale MCU firmware
datasets from OTACAP and FirmLine, we present an empirical study of 24 emulation-based firmware analysis tools published in top conferences and journals. We position these tools within a unified automated analysis pipeline: emulation configuration reconnaissance, emulation, bug finding, and diagnosis. At each stage, we evaluate whether a tool's output provides sufficient information to enable the subsequent stage, using a deduplicated and validated subset of 4,571 ARM-based firmware samples. Only 1,580 samples (34.5%) can be successfully fuzzed, even counting a sample successful if at least one existing tool can fuzz it. Among these, fuzzing results are generally poor, with average code coverage of only 10% and many false crashes/hangs. Through a systematic analysis of failed fuzzing attempts and false-positive cases, we expose fundamental challenges and methodological limitations in current approaches. These findings highlight critical gaps in the state of the art and provide actionable insights to guide future research in emulation-based firmware analysis.
Read the full abstract ▾
All authors Hongyuan Li, Ke Wang, Wei Zhou, Le Guan
Numerical Analysis
A Kernel-Aware Two-Grid Preconditioner for Cell-Centered Nearly Incompressible Elasticity
Shubin Fu and Xiang Zhong
Nearly incompressible elasticity is often discretized by mixed methods to avoid locking, but the resulting saddle-point systems can be expensive to solve. We consider a weakly symmetric multipoint stress discretization whose stress and rotation unknowns can be eliminated independently over vertex interaction regions, leaving a symmetric positive definite system for
cell-centered displacement only. Although smaller, the reduced system contains a parameter-dependent Schur complement that becomes difficult to precondition as the Lamé ratio increases. We show that its energy consists of a uniformly coercive shear part and a dominant semidefinite volumetric part. Standard
cell-centered interpolation need not preserve the volumetric kernel and can introduce energy amplified near incompressibility. Motivated by this structure, we develop a two-grid preconditioner combining two complementary coarse subspaces: a conventional displacement subspace and a discrete-curl subspace lying exactly in the fine-grid volumetric kernel. Symmetric vertex-patch smoothing completes the displacement-only solver. The energy splitting and kernel-compatible decompositions yield a condition-number bound independent of the Lamé ratio for each fixed grid pair. Two- and three-dimensional experiments confirm the approximation properties of the locally eliminated discretization and show that the kernel correction prevents the deterioration of the displacement coarse subspace alone, also for discontinuous material coefficients.
Read the full abstract ▾
Artificial Intelligence
Reasoning Externalization for Faithful Large Language Model Narratives of Stock Return Predictions
Sujung Kim, Seung Hwan Cho, Sangjin Park et al. (+1 more)
In finance, interpreting machine learning predictions is essential, yet the numerical outputs of explainable AI can be difficult for non-experts to understand. While large
language models (LLMs) can translate these outputs into natural
language, they may produce errors when inferring numerical changes and feature relations. We propose an LLM narrative framework for cross-sectional stock return prediction that combines temporal Shapley additive explanations (SHAP) evidence with historical regime analogs. Temporal evidence tracks changes in the normalized global SHAP importance of an XGBoost model over six months. Historical analogs are past periods with similar changes in SHAP importance, their model performance and subsequent
market returns are provided as comparative context. Using this framework, we conduct a controlled study of progressive
reasoning externalization, sequentially providing raw SHAP sequences, deterministic temporal descriptors, and feature relations. Each generated claim is verified against provenance-linked evidence. Across Qwen3, externalizing numerical and relational
reasoning improved evidence faithfulness as well as temporal and relational accuracy. Evidence faithfulness increased from 0.696 to 0.996 for Qwen3-32B-Instruct. While historical analogs did not improve structured automatic faithfulness, they received higher human-rated usefulness scores. These results suggest that externalizing verifiable
reasoning enhances narrative faithfulness and that historical context adds interpretive value.
Read the full abstract ▾
All authors Sujung Kim, Seung Hwan Cho, Sangjin Park, Young-Min Kim
Artificial Intelligence
Talk2Agent: Benchmarking Voice Interfaces for Text Agents
Terumi Chiba, Guangzhi Sun, Zheqi Yuan et al. (+1 more)
Large
language model (LLM) computer-use
agents are typically evaluated with clean written instructions, despite
speech being an increasingly popular interface for interacting with such systems.
Speech input introduces an additional failure point: transcription errors can alter task-critical entities, constraints, or targets before the
agent begins
reasoning, while conventional ASR metrics do not directly measure whether the information required for successful execution has been preserved. We introduce Talk2
Agent, a
benchmark for evaluating how effectively voice interfaces convey human-spoken instructions to LLM-based computer-use
agents. Talk2
Agent builds human-spoken versions of tasks from WildClawBench and OSWorld and evaluates a range of voice interfaces, including dedicated ASR models, audio-capable LLMs, contextual biasing, and LLM-based ontology repair. Because repeatedly executing long-horizon computer-use tasks is costly and
stochastic, we further propose an execution-free, task-conditioned evaluation framework that projects the original task grader onto
prompt-addressable intentions and measures how much task-relevant information is retained after the voice interface. On WildClawBench, Talk2
Agent's execution-free native projection provides a practical, execution-grounded measure of voice-interface quality, correlating with downstream task completion and improving Pearson correlation by 0.246 over WER/CER on 32 hours of real human
speech.
Read the full abstract ▾
All authors Terumi Chiba, Guangzhi Sun, Zheqi Yuan, Chao Zhang
Artificial Intelligence
When Context Changes: Understanding Update Failures in LLMs
Junyu Guo, Yuchen Fang, Shangding Gu et al. (+3 more)
As preferences, goals, and facts change, LLM
agents must use the current state while earlier versions remain in context. Yet they can answer with an old value of the same variable, a failure that we call stale binding. To study when models use outdated information and why, we introduce Controlled In-Context
Memory (CICM), a
benchmark for tracking and using updated information in conversations and
agent logs. We observe that even frontier
reasoning models can fail to recover the current state. We find that in open-source models probes can still recover the updated value when the model answers with an old one, pointing to a failure to select information that remains available. Component tests in Qwen and Pythia identify a mechanism for this selection failure:
attention drift, where
attention favors old values over the current one when producing an answer. We study a one-layer
transformer to mathematically understand how this phenomenon happens: when
attention scores are similar, several old values can together receive more
attention than the current value. Guided by this explanation, we redirect
attention toward the current value without further training. When the current value is requested directly, adjusting this intervention for each input corrects most old-value errors across various model families while preserving nearly all initially correct answers. Reliable context management therefore requires more than remembering updated information: models must use it to guide their answers.
Read the full abstract ▾
All authors Junyu Guo, Yuchen Fang, Shangding Gu, Costas Spanos, James Demmel, Javad Lavaei
Computer Vision
AdaOcc: Adaptive 3D Occupancy Prediction for Embodied Tasks
Jinglong Wang, Yunjie Wang, Zhiyang Zhang et al. (+4 more)
Embodied tasks demand accurate, flexible, and semantically rich 3D scene representations. 3D semantic occupancy is well suited to this requirement, as it can model holistic 3D spaces by encoding
geometric occupancy along with semantic categories. However, existing occupancy prediction methods struggle to meet practical deployment requirements, such as adapting to varying computing budgets, sensor setups, and observation views. In this paper, we propose a point-based Adaptive 3D Occupancy Prediction method, called AdaOcc, tailored for
embodied scenarios. To accommodate heterogeneous sensor inputs, AdaOcc uses an adaptive geometry-guided dual-branch encoder that can support RGB images in various numbers of views with (estimated) depth maps or
LiDAR scans. AdaOcc represents occupied regions via sparse semantic points trained with a progressive query learning strategy, allowing the prediction computational budget to be flexibly adjusted through query point numbers and decoder layers. To facilitate high-fidelity
geometric modeling for lightweight point-based occupancy learning, we further propose a novel containment loss that regularizes predicted points to reside within valid occupied regions. Extensive experiments show that our method achieves a new state-of-the-art on Occ-ScanNet with considerable performance improvements over previous methods. Moreover, our framework demonstrates strong practical applicability as an adaptive 3D perception module in real-world
embodied systems.
Read the full abstract ▾
All authors Jinglong Wang, Yunjie Wang, Zhiyang Zhang, Jiawei He, Ye Yuan, Bo Qiu, Jing Zhang
Machine Learning
GeoNest: Learning to Select Failure-Aware Neighborhoods for the Irregular Knapsack Problem in a Circular Container
Zhongman Du, Huiming Zhang, Linlin Yang et al. (+2 more)
The two-dimensional irregular knapsack problem in a fixed circular container is an important combinatorial optimization problem for maximizing material utilization in manufacturing. Conventional
geometric packing solvers can produce tightly packed layouts, yet they often partition the residual space into isolated small pockets that cannot fit valuable unplaced polygons. To overcome this late-stage packing bottleneck, we propose a failure-aware large neighborhood search framework named GeoNest, driven by a graph policy trained via reinforcement learning. Specifically, we first construct neighborhoods by pairing failed target polygons with residual pockets. We then use explanatory poses to identify the placed polygons that block candidate insertions. These diagnosed blocking relations define bounded, fixed-item repair subproblems for the underlying
geometric solver. Finally, the graph policy selects the most promising subproblem for execution. For evaluation, we introduce CircleNest-Bench, a
benchmark comprising 2,391 load-controlled instances from four contour sources, including a held-out industrial CAD source. Experimental results demonstrate that, under the same total time budget, GeoNest improves mean utilization over a state-of-the-art standalone packing solver by about 0.9% on average across the three main test sets and by about 0.6% on the held-out industrial set.
Read the full abstract ▾
All authors Zhongman Du, Huiming Zhang, Linlin Yang, Sheng Xu, Baochang Zhang
Robotics
Efficient Multi-Modal Planning with Reward-Guided Preference Optimization for Autonomous Driving
Chenglin Chen, Lujia Wang, Xinhu Zheng et al. (+2 more)
Safe and efficient trajectory planning is essential in autonomous driving. However, existing end-to-end approaches often fall short in both computational efficiency and safety guarantees. Methods based on imitation learning suffer from causal confusion, while rule-based scoring approaches often incur heavy computational overhead and suffer from objective misalignment. Additionally, preference-based methods rely on strict pairwise annotations, limiting data utilization. To overcome these limitations, we propose EMPlan, an efficient multi-modal trajectory planning method powered by reward-guided fine-tuning. We design a hybrid architecture that combines sparse anchors with an offset refinement module for efficient multi-modal trajectory prediction. Sparse anchors provide coarse trajectory candidates with low latency, which are subsequently refined by the offset module for higher prediction accuracy. To enhance safety without incurring additional inference costs, we adopt a two-stage training paradigm consisting of pretraining and reward-guided fine-tuning. During fine-tuning, we leverage rule-based reward signals and unpaired preference supervision to refine the pretrained policy toward safer trajectory selection. We evaluate EMPlan on the non-reactive NAVSIM
benchmark, where it strikes a favorable balance between planning accuracy and efficiency, demonstrating superior performance under real-time constraints.
Read the full abstract ▾
All authors Chenglin Chen, Lujia Wang, Xinhu Zheng, Jun Ma, Haoang Li
Computation and Language
TRACE: Target-Aware Retrieval, Attributed Evidence, and Contract-Constrained Extraction for LitTraceQA
Sachin Gupta and Divya Godara
Finding a relevant paper is not the same as producing a verifiable answer from it. LitTraceQA requires canonical paper identifiers, exact evidence at the page or object level, and typed answers that match the evaluator. We call the separation between source access and scorer-visible correctness the grounding contract gap. TRACE - Target-Aware
Retrieval, Attributed Evidence, and Contract-Constrained Extraction - addresses this gap with target-grouped
retrieval, independent typed evidence localization,
multimodal table extraction, schema-driven table construction, and fail-closed validation. It indexes 27,487 papers through passage, object, alias, citation, and dense representations while retaining the question target behind each signal. For tables, TRACE predicts the observation unit before extracting values and assembles rows with evaluator-compatible key normalization. Our audited selected clean-track artifact scores 0.760613 on the official 71-question test set, including 0.9728 paper F1, 0.6847 evidence F1, 0.9800 multiple-choice accuracy, 0.5423 table-row F1, and 0.3508 macro
cell accuracy. On 11 public-development table records, a clean baseline and coordinate-aware visual fill obtain row F1 of 0.291 and 0.411, respectively; this diagnostic comparison includes fallback outputs and is not an official-test claim. Remaining errors chiefly concern locator, observation-unit, row-key, and source-value identity.
Read the full abstract ▾
Machine Learning
Optimal Design for Active Preference Learning with Biased LLM Judges
Zhongman Du, Huiming Zhang, Haodong Zhu et al. (+1 more)
Learning from human preferences is central to large
language model (LLM)
alignment, but human preference annotation is costly. Active preference learning reduces this cost by selecting informative comparisons, and LLM judges can provide additional scalable feedback. However, the preferences of the judges may deviate from those of the target human population. Even after calibration on trusted reference data, active acquisition can shift the comparison distribution and expose residual judge bias. We therefore incorporate judge deviations into the acquisition design rather than relying on a separate calibration stage. Under joint estimation, comparisons that appear highly informative about the reward may also reflect judge bias and therefore provide less information about human preferences. To address this issue, we propose Nuisance-Adjusted Optimal Design (NAOD), a comparison-selection strategy that prioritizes policy-relevant target information after nuisance adjustment and uses the Frank-Wolfe
algorithm for optimization. Theoretically, we establish a sharp conditional local asymptotic minimax lower bound on policy risk and construct an
estimator that attains it. We further characterize the finite-sample cost of learning the nuisance representation and show that representation error can reverse an oracle design advantage. Finally, we validate these predictions experimentally and evaluate NAOD on Chatbot Arena data across 17 judges, 15 budget configurations, and 15 random cluster-level splits. NAOD reduces the mean regret of proxy policy by 29.1% relative to a matched target-information design, outperforms existing methods, and improves human-preference prediction on held-out data.
Read the full abstract ▾
All authors Zhongman Du, Huiming Zhang, Haodong Zhu, Baochang Zhang
Robotics
Plan-Conditioned Imitation for Robust Object Retrieval under Self-Occlusion in Dense Clutter
Kowndinya Boyalakuntla, Ajinkya Pawar, Abdeslam Boularias et al. (+1 more)
Retrieving objects from dense clutter requires rearrangement during which the manipulator can occlude objects while moving them. Repeated arm withdrawals to restore visibility interrupt execution. We introduce TRACE, a plan-conditioned imitation framework for
retrieval under self-occlusion. A single unoccluded observation initializes a digital twin, where a privileged teacher generates a fixed nominal rollout. A recurrent student combines local rollout context, partial object observations, and proprioception to select actions that can correct deviations from the prediction. Behavior cloning initializes the student; DAgger refines it with teacher labels on student-visited states. The rollout remains fixed throughout execution, so the deployed student needs neither online teacher queries nor additional simulator rollouts during pushing. On 511 simulation test scenes, TRACE achieves 90.7% success versus 43.4% for nominal replay and 96.7% for the privileged closed-loop teacher. At a matched 26,373-label budget, student-state supervision achieves 87.8% versus 66.7% for expert-only cloning, demonstrating gains beyond additional labels. On a UR5e, TRACE achieves 90.0% success versus 95.0% for the closed-loop teacher, while reducing total execution time from 192.7 s to 67.3 s. It avoids the teacher's 16.8 sensing-related arm retractions per trial during pushing, retaining a final withdrawal for graspability evaluation. Code and data will be released at: https://trace-
retrieval.github.io.
Read the full abstract ▾
All authors Kowndinya Boyalakuntla, Ajinkya Pawar, Abdeslam Boularias, Jingjin Yu
Computer Vision
Decoupling Spherical Reasoning from Dense Prediction for 360 Depth Estimation
Zhijie Shen, Chunyu Lin, Shuai Zheng et al. (+4 more)
The equirectangular projection (ERP) is widely used for panoramic depth estimation, but its spatially varying distortion makes geometry-consistent feature modeling challenging. We revisit panoramic depth estimation by decoupling contextual modeling in native spherical space from dense ERP prediction. To this end, we propose a Fibonacci Spherical Graph (FSG) as an intermediate
reasoning space to lift ERP features onto quasi-uniform Fibonacci nodes on the sphere and capture local and long-range dependencies through complementary spherical neighborhoods. The resulting spherical discretization distributes graph nodes approximately uniformly over the spherical surface, reducing the over-representation of highly stretched regions during relational modeling. Operating on a compact set of Fibonacci nodes also avoids the computational burden of constructing and processing a graph at full ERP resolution. To bridge spherical
reasoning and dense prediction, we propose a Spherical Context Conditioning (SCC) module that adaptively modulates dense ERP features with the enhanced spherical representation, allowing spherical context to guide pixel-aligned depth prediction. Extensive experiments on three
benchmarks demonstrate that the proposed method consistently achieves superior depth accuracy over existing approaches.
Read the full abstract ▾
All authors Zhijie Shen, Chunyu Lin, Shuai Zheng, Feng Li, Runmin Cong, Huihui Bai, Yao Zhao
Robotics
Online Evolution Strategy for Flow-Matching VLA Policies via Self-Supervised Trajectory Distribution Optimization
Gongxin Yao, Yongsheng Zhao, Jiayin Deng et al. (+4 more)
Vision-
Language-Action (VLA) models based on generative frameworks, such as Flow Matching, have recently achieved impressive performance in robotic manipulation. Unlike deterministic policies, Flow Matching enables VLA models to learn conditional action trajectory distributions, where latent noise vectors induce different actions under the same task scenario. However, we observe that these distributions are often ill-formed, with successful and failed behaviors coexisting while considerable probability mass remains in unfavorable regions. To this end, we propose Online-ES, an online adaptation framework for Flow Matching VLAs based on
Evolution Strategy (ES), which refines the learned action trajectory distribution through interaction feedback. Instead of
pruning the latent noise space, our method performs evolutionary exploration directly in the action trajectory space, where diverse trajectories generated by Flow Matching provide candidate solutions for adaptation. By perturbing sampled trajectories and evaluating their execution outcomes, we derive a self-supervised MSE objective that transfers the
evolution direction from trajectory space into model parameter space. Mathematically, we prove that the proposed objective provides an unbiased
estimator of the optimal
evolution direction. Moreover, we also incorporate failure experiences as negative feedback to regularize the
evolution direction, steering the policy away from previously explored failure regions. Experiments in both simulation and real-world environments demonstrate that Online-ES achieves policy improvement comparable to reinforcement fine-tuning, without learning a value model or computing advantages.
Read the full abstract ▾
All authors Gongxin Yao, Yongsheng Zhao, Jiayin Deng, Deng Liang, Han Gao, Lei Zhao, Baoping Cheng
Machine Learning
Mitigating the Length-Scaling Tax with Online Distillation
Xu Wan, Wenyue Xu, Shengjie Zhao et al. (+1 more)
Length scaling during reinforcement-learning (RL) post-training is often viewed as a sign of improved
reasoning ability, especially on difficult problems, but may also make responses to already-solved problems unnecessarily verbose. We quantify this side effect as the length-scaling tax (LST): excess response length on already-solved queries without a commensurate accuracy gain. To mitigate LST, we propose Length Self-
Distillation (LSD), which routes solved
prompts to on-policy
distillation and retains the original RL objective for unsolved
prompts. LSD uses an exponential moving average of the online policy as its teacher, requiring no external model. We find that LSD achieves comparable or better performance than RL across multiple variants, while substantially curbing response-length growth on easy queries. LSD reduces LST from 19.0% to -3.7% on single-turn
reasoning and from 31.4% to 13.7% on multi-turn agentic tasks, demonstrating that LSD effectively preserves concise response patterns on easy queries while supporting efficient exploration on difficult queries during RL post-training.
Read the full abstract ▾
All authors Xu Wan, Wenyue Xu, Shengjie Zhao, Mingyang Sun
Machine Learning
Visualizing Distribution Coverage in Generative Diffusion Models
Yifei Wang, Xiaoyu Wu, Tsu-Jui Fu et al. (+4 more)
Diffusion distillation is widely adopted to accelerate sampling, and the resulting few-step models are broadly believed to match or even surpass their multi-step teachers in generation. However, standard evaluations such as GenEval2 typically draw only one sample per
prompt, so improved scores may fail to reveal losses in distribution coverage. We therefore revisit whether distilled models truly match their teachers beyond single-draw performance using \textbf{pass@$\mathbf{k}$}, which measures the probability that at least one of $k$ independent samples satisfies a quality criterion. At $k{=}1$, pass@$k$ reduces to standard single-draw evaluation. As $k$ grows, the curve reveals whether additional draws find genuinely different successes or merely revisit the same modes, directly exposing how broadly a model covers the space of valid outputs. We first show that classifier-free guidance (CFG), whose quality–coverage tradeoff is well established, is the clearest case: higher guidance improves pass@$1$, but its advantage shrinks and reverses at larger $k$. Applying pass@$k$ to few-step distilled models, we find the same tradeoff splits along training objectives: distribution-matching objectives concentrate the student's output distribution, boosting early-hit rates while eroding large-budget coverage, whereas consistency and trajectory-based objectives better preserve the teacher's coverage even at large $k$. We further show that this tradeoff extends to few-step causal
video generation. Our findings reveal a previously overlooked cost of
diffusion distillation: across both image and
video generation, the choice of training objective fundamentally determines whether a few-step model inherits its teacher's distribution coverage or trades it away for single-draw quality.
Read the full abstract ▾
All authors Yifei Wang, Xiaoyu Wu, Tsu-Jui Fu, Chen Chen, Liang-Chieh Chen, Zhe Gan, Chen Wei
Robotics
Locomotion-Grounded Humanoid Soccer: Task-Gated Reinforcement Learning of a Multi-Directional Kicking Library
Abu Hanif Muhammad Syarubany, Jaehyun Jang, Hwanhee Kim et al. (+3 more)
Recent
humanoid soccer systems make motion tracking the substrate and derive locomotion from it, typically by steering a motion-reference anchor toward the ball. This yields strong shooting results, but locomotion is trained only on the narrow, deterministic command distribution ball approach induces, never evaluated as a capability in its own right. We invert the stack: a general, command-conditioned locomotion policy is trained first as the substrate, and N motion-guided kicking skills are added on top as task-gated layers, so the reachable gait space is set by the locomotion curriculum rather than any reference clip. Because every skill starts from and returns to this same commandable state, locomotion also becomes a composition hub (O(N) transitions rather than O(N^2)), and post-strike stabilisation is handed back to the trained controller rather than scripted per clip. We instantiate this on a 29-DoF Unitree G1 with seven retargeted kicking skills spanning 259.5 degrees of nominal aim direction, including lateral, rearward and weak-foot strikes a single forward-facing reference cannot express, and report shooting accuracy alongside command-tracking, terrain and push-recovery results with the full skill library attached, an axis prior
humanoid soccer systems do not report. The library is validated on hardware across forward, lateral, rearward and commanded approaches.
Read the full abstract ▾
All authors Abu Hanif Muhammad Syarubany, Jaehyun Jang, Hwanhee Kim, Kyuwon Kim, Seungyeon Ryu, Chang D. Yoo
Computation and Language
Where MLLMs Fail and Why: Causal Task Decomposition for Capability Failure Diagnosis
Xia Hu, Brian Potetz, Chun-Ta Lu et al. (+6 more)
End-to-end accuracy on compositional tasks records how often MLLMs fail, but cannot distinguish whether a failure reflects an intrinsic deficit in the targeted capability or a cascading error from an upstream prerequisite. We propose a causal decomposition framework that isolates these two failure modes through controlled interventions on the prerequisite dependencies of each task. Our capability metrics (NC, IC, RC) score each task under unassisted, correct, or incorrect prerequisites to diagnose where failures arise; contribution metrics (N-Score, S-Score), adapted from probabilities of causation, quantify each prerequisite's necessity and sufficiency to determine why. We instantiate the framework in CADET, a diagnostic
benchmark of 10 composite tasks decomposed into 46 unit tasks with over 33,000 human-annotated questions spanning perception, spatial, temporal, and cognitive categories. Diagnosing frontier MLLMs with our framework uncovers systematic patterns that end-to-end accuracy obscures. Capability-wise, supplying correct prerequisites eliminates 54% of errors on cognitive tasks, lifting them from weakest to above spatial and temporal. Prerequisite-wise, causal contributions are concentrated in a few critical prerequisites, and supplying the single most important one alone captures 84% of the gain from supplying all prerequisites.
Read the full abstract ▾
All authors Xia Hu, Brian Potetz, Chun-Ta Lu, Huanfen Yao, Leonidas Guibas, Zhicheng Wang, Howard Zhou, Pengfei Xing, Andrew Gallagher
Artificial Intelligence
OpenJev-RLCD: A Working RLCD Implementation
Zhimin Gao and Pichao Wang
Decision models such as Jev answer questions with probabilities, which are only useful if they are calibrated. Open-source reproductions rely on supervised fine-tuning plus temperature scaling, while reinforcement learning from verifiable rewards (RLVR) makes
reasoning models overconfident. We present a working implementation of reinforcement learning for calibrated decisions (RLCD) for
reasoning models: the model samples a rationale, and we score the answer distribution it commits to afterwards with a strictly proper scoring rule. A variance identity shows that scoring the mixture of several samples rewards disagreeing rationales, and that RLVR is exactly this mixture objective without its diversity term. Optimized naively, the per-rationale objective either switches
reasoning off or is drowned out by policy-gradient noise, which leads to a two-stage recipe: calibrate, then reinforce. With Qwen3-1.7B on two
reasoning tasks (3 seeds, paired tests), RLCD matches or beats SFT, RFT/
STaR and GRPO (each temperature-scaled) in accuracy and beats all of them in selective prediction; on GSM8K answer verification a single query decides \gvTwoCovFive% of the items at $\le$5% error, versus \gvGrpoCovFive% for GRPO. When uncertainty comes from annotator disagreement, RLCD provably cannot beat cross-
entropy. Code and results: https://github.com/ZimmyGao/openjev-rlcd.
Read the full abstract ▾
Machine Learning
Scoring Higher, Answering Worse: Mitigating Reward Hacking in Rubric-Based RL via Protocol-Level Rubrics
Maoqi Liu, Junwei He, Bowen Zhang et al. (+5 more)
Rubric-based reinforcement learning (Rubric-RL) trains
language models where no verifier exists. A judge checks each criterion of a rubric, and the verdicts are aggregated into a reward, most often by a weighted sum. We show that this additive aggregation is the weak point. Under a sum, criteria compensate for one another: a policy that misses the one decision that matters can buy the points back with advice nobody asked for. On clinical consultation, such a policy scores higher and answers worse. Rubric coverage rises while appropriateness on held-out physician criteria falls below the untrained model. The medical criteria are not to blame. Grouped so that they must hold together, the same criteria, unchanged to the word, recover a third of the loss; shorter answers recover almost none. We therefore propose Protocol-level Rubrics (ProRubric), which keeps what the criteria ask for and changes how they are aggregated. It groups a checklist into a few protocol-level dimensions. A dimension counts only when all of its criteria hold and its failure clause does not fire. The grouping is done once, offline, and leaves the optimizer unchanged. ProRubric raises appropriateness by 10.8 points without losing coverage and has the best seven-
benchmark average at both scales. Reward validity is set not only by what a rubric verifies, but by how it aggregates. Code is available at https://github.com/Estrellajer/ProRubric
Read the full abstract ▾
All authors Maoqi Liu, Junwei He, Bowen Zhang, Feiran Li, Wentao Ma, Rongyi Lin, Shuhan Zhong, Quan Fang
Robotics
Coral Grow-out Robotic Assessment System (CGRAS): Scaling Coral Recruit Monitoring Through Robotics and Computer Vision
Dorian Tsai, Scarlett Raine, Emilio Olivastri et al. (+12 more)
Climate change is the largest threat to coral reefs, with increasing global impacts accelerating the need for scalable reef restoration technologies. Large-scale reef restoration depends on the mass production of corals, such as through coral aquaculture. Coral seeding with recruits grown in aquaculture facilities is a feasible restoration approach, but effective production requires consistent, high-frequency monitoring of tens of thousands of macroscopic (0.5-2mm diameter) recruits, making conventional manual assessment prohibitively labor-intensive. To address this monitoring bottleneck, we introduce the Coral Grow-out Robotic Assessment System (CGRAS) which combines robotic imaging and computer
vision to automate data acquisition, perform multi-species detection and counting of corals, and evaluate coral health. CGRAS automatically extracts coral growth, survival and spatial distribution metrics, with the aim of providing timely feedback to operators for optimizing production, grow-out and deployment workflow processes. We demonstrate CGRAS in a large aquaculture facility on standardized coral settlement tiles, reducing the time and labor costs by a factor of 9.6 as compared to manual monitoring, whilst achieving 96.4% agreement for Acropora kenti corals relative to expert counts.
Read the full abstract ▾
All authors Dorian Tsai, Scarlett Raine, Emilio Olivastri, Riki Lamont, Andrew Lui, Timothy Morris, Joshua Esplin, Christopher A. Brunner, F. Mikaela Nordborg, Reginald Wardleworth, Garima Samvedi, Karen Jackel, Matthew Dunbabin, Tobias Fischer, Andrea Severati
Machine Learning · Cross-listed from stat.CO
Learn-Then-Differentiate Gradient Estimation
Nifei Lin, Qingkai Zhang and L. Jeff Hong
Learn-then-differentiate (LTD) estimates gradients by fitting a model to simulation outputs and differentiating it. We develop a unified framework explaining what LTD differentiates and how accurately it estimates gradients. For models with a weighted representation, LTD differentiates a learned representation of the underlying probability measure. We then show how accuracy guarantees for fitted models translate into guarantees for gradients and higher-order derivatives, with rates approaching the standard Monte Carlo rate under suitable smoothness conditions. The framework recovers established results for kernel regression, local
polynomial regression, and kernel ridge regression, and yields further guarantees for multiple kernel learning and smooth neural networks. These results provide a common foundation for understanding and analyzing LTD across learning methods.
Read the full abstract ▾
Numerical Analysis
A fully convergent fixed-point fast sweeping method with the WENO-JS local solver for steady state of hyperbolic conservation laws
Liang Li, Jun Zhu and Yong-Tao Zhang
The fixed-point fast sweeping methods with weighted essentially non-oscillatory (WENO) local solvers are a class of efficient and high-order accuracy numerical methods for solving steady-state solutions of
hyperbolic conservation laws. However, with the classical WENO-JS local solver, the iteration residue of high-order fixed-point fast sweeping scheme often has difficulty to settle down to round-off errors. To achieve the full convergence in a fast sweeping method, the fixed-point fast sweeping methods with non-traditional WENO local solvers based on unequal-sized substencils were designed. However, the WENO schemes based on unequal-sized stencils are more complex and in general more expensive in computational costs than the classical WENO-JS schemes. In this paper, we go back to the classical WENO-JS local solver and develop a new fully convergent fifth-order fixed-point fast sweeping method for solving steady-state problems of
hyperbolic conservation laws. Based on recent studies on the nonlinear weighting process around discontinuities of solution, we apply the technique of frozen weights for avoiding unnecessary adjustment of nonlinear weights in the WENO-JS local solver, which freezes the nonlinear weights once the residual sequence in the fast sweeping iterations has stabilized. Different from the existing work on frozen weights, we design a simple and robust approach to judge stabilization of iteration residues and determine the iteration step when the nonlinear weights are frozen in the fast sweeping method. Extensive numerical experiments on a wide range of challenging two-dimensional steady-state problems demonstrate that, unlike the previous fast sweeping method with the fifth-order WENO-JS local solver, the proposed new scheme consistently drives the iteration residues to round-off errors and achieves the full convergence.
Read the full abstract ▾
Machine Learning
scTrilemma: Balancing Identity, Invariance, and Fidelity in Single-Cell Representation Learning
Yunhak Oh, Yoonho Lee, Junseok Lee et al. (+9 more)
Single-
cell RNA-seq representation learning is fundamentally label-free:
cell identities, states, and contexts are not fixed training targets, so what constitutes signal or nuisance is analysis-dependent. A single representation must therefore preserve biological identity and state, remain robust to nuisance context, and retain the gene-level variation needed for expression analysis, three demands we call the representation trilemma. To tackle this problem, we introduce scTrilemma, a latent-bottleneck VAE that routes expression-derived variation to the
embedding, the decoder, or the prior rather than forcing all of it through one
embedding. It gates gene
tokens by expression, routes the
cell representation through the decoder, and conditions the prior on unlabeled pseudo-bulk context, under a single reconstruction objective and without target annotations or auxiliary representation losses. In release-based zero-shot evaluation on successive CZ CELLxGENE Census releases, scTrilemma leads all three demands at once and preserves biological-state, differential-expression, and pathway structure across multiple disease settings. Latent interventions further show that context can be removed at almost no cost to the other demands, leaving identity against fidelity as the remaining tension. Code is publicly available at https://github.com/yunhak0/scTrilemma.
Read the full abstract ▾
All authors Yunhak Oh, Yoonho Lee, Junseok Lee, Namkyeong Lee, Sang-Yeon Hwang, Yinhua Piao, Hyomin Kim, Seonghwan Kim, Jaechang Lim, Woo Youn Kim, Sungsoo Ahn, Chanyoung Park
Computer Vision
FrameMorrow: Future-guided Frame Selection with Prospective Tokens for Long-Horizon Video Generation
Bo Yin, Xiaobin Hu, Jiaqi Zhao et al. (+1 more)
Long-horizon
video generation requires models to effectively leverage an increasingly long generation history. As the generated history grows, retaining all previous content becomes increasingly expensive and redundant, making effective historical selection essential. Existing approaches often determine historical relevance based on the current content. However, information relevant to the present is not necessarily useful for future generation, while seemingly less relevant history may become important later. Our key insight is that historical information should be selected according to its relevance to future information needs. Capturing these needs does not require generating the full future; instead, a compact representation of what becomes important next is sufficient to guide historical selection. Building on this insight, we propose FrameMorrow, a prospective frame selector that predicts a small set of prospective
tokens representing future information needs and uses them to identify relevant information from history. FrameMorrow selects explicit historical frames rather than model-specific internal states, enabling plug-and-play integration across diverse generators, including closed-source models, with little additional inference cost. We evaluate FrameMorrow across five
benchmarks and 11 generative models spanning long-
video generation, interactive generation, and action-conditioned world models. Extensive experiments demonstrate consistent improvements in long-range consistency, visual quality, and action
alignment across diverse generation settings.
Read the full abstract ▾
All authors Bo Yin, Xiaobin Hu, Jiaqi Zhao, Shuicheng Yan
Game Theory · Cross-listed from quant-ph
Average-and Last-Iterate Lower Bounds for Optimistic Matrix Mirror-Prox in Quantum Zero-Sum Games
Yiheng Su, Emmanouil-Vasileios Vlatakis-Gkaragkounis and Pucheng Xiong
Optimistic
matrix mirror-prox (OMMP) computes $\epsilon$-approximate Nash
equilibria in
quantum zero-sum games with an $O(1/\varepsilon)$ average-iterate guarantee [arXiv:2311.10859]. We investigate whether this dependence on accuracy is tight and whether
geometric last-iterate convergence can be guaranteed. We study these questions through explicit games with one
qubit per player. First, we prove an $\Omega(1/\varepsilon)$ lower bound for the uniform-average output that includes the maximally mixed initial state, independently of the regularizer and step size. Second, we construct a fixed game on which optimistic gradient descent-ascent (OGDA), initialized at the maximally mixed state, has last-iterate Frobenius distance to
equilibrium $\Theta(1/t)$ and duality gap $\Theta(1/t^3)$ for every sufficiently small fixed step size. A separate fixed game exhibits arbitrarily long delays in reducing the initial error by a constant factor across a family of initial states. Finally, we give a fixed game with a unique, strictly complementary
equilibrium on which optimistic
matrix multiplicative weights updates (OMMWU) converge only polynomially from the maximally mixed state for every fixed positive step size. The last-iterate Frobenius distance and
quantum relative
entropy from the
equilibrium to the iterates decay as $\Theta(1/t)$, while the duality gap decays as $\Theta(1/t^2)$.
Read the full abstract ▾
Data Structures and Algorithms
Optimal VC Dimension of Contrastive Learning with Margin
Dionysis Arvanitakis, Vaggos Chatziafratis, Yiyuan Luo et al. (+1 more)
Contrastive learning is a successful paradigm for learning $d$-dimensional
geometric representations from a collection of “anchor–positive–negative” triplets $(i,j^{+},k^{-})$, indicating that “item $i$ is closer to $j$ than to $k$.” Despite its success, understanding why contrastive learning leads to representations of high generalization quality—beyond the often pessimistic predictions from PAC-learning—remains a central question. Recently, \citet*{alon2024optimal} proved that, for PAC-learning $d$-dimensional Euclidean representations of $n$-point
datasets, $\Theta(\min(nd, n^2))$ triplets are necessary and sufficient, while they posed as an open question whether their VC dimension bounds for the more realistic setting of contrastive learning with a margin can be improved. For a margin parameter $\alpha >0$, a triplet $(i,j^{+},k^{-})_{\alpha}$ is satisfied by the
embedding $\phi:[n]\rightarrow \mathbb{R}^{d}$, if $\|\phi(i)-\phi(k)\|_2>(1+\alpha)\cdot\|\phi(i)-\phi(j)\|_2$. In this work, we resolve their question by proving that the VC dimension of contrastive learning under any margin $\alpha\in(0,1)$ is in fact $O(n/\alpha^2)$, improving on the previous bound of $O(n\log(n)/\alpha^2)$. We also establish that the bounds are optimal up to constant factors, by providing a matching lower bound of $\Omega(\frac{n}{\alpha^2})$ (the previously known lower bound was $\Omega(\frac{n}{\alpha})$), for $\alpha\geq \max(n^{-1/2},d^{-1/2})$.
Read the full abstract ▾
All authors Dionysis Arvanitakis, Vaggos Chatziafratis, Yiyuan Luo, Konstantin Makarychev
Machine Learning
ReSCENE: Server-Side Replay for Structural Mitigation of Catastrophic Forgetting in Federated Continual Learning
Sungmin Kang, Zhengzhong Tu and Sunwoo Lee
Federated continual learning must integrate new tasks over time without losing earlier-task knowledge. Most existing methods attach an anti-forgetting mechanism to the client-trained, server-aggregated loop of
federated learning, which holds back new learning to preserve earlier knowledge and burdens resource-constrained clients. We propose ReSCENE, which structurally mitigates catastrophic forgetting by having each client upload a small condensed surrogate of its local data while the server keeps the surrogates of past tasks and trains the global model on them together with the current task surrogates. For efficient server
memory, we introduce temporal herding, which selects the more recent surrogates from the pool accumulated over a task into a compressed buffer. Our study provides a theoretical analysis showing that this buffer can represent the original task data more closely than full accumulation of all surrogates. Across CIFAR-10, CIFAR-100, and TinyImageNet, ReSCENE achieves the strongest accuracy over seven baselines, by up to $31.1$ points of average accuracy, while requiring as little as $0.11\times$ of the client computation and up to $179\times$ less upload than the model-update baselines. ReSCENE further demonstrates its effectiveness when scaled to larger client populations and larger models while remaining efficient, which makes it a practical method for
federated continual learning.
Read the full abstract ▾