Human-Computer Interaction
Show your work: An exploratory study of student experiences of Turnitin Clarity
J. Roe and M. Perkins
Process-capture platforms promise to make the writing behind an assessed artefact visible, and vendors increasingly
market them as a
fairness measure rather than a detection tool. Their acceptability to the students who must write within them, however, is largely untested. This exploratory qualitative study examines how students' expectations of one such platform, Turnitin Clarity, compared with their experience of using it. Seven students at a UK university, given no onboarding to the platform, took part in pre-use focus groups. Six then completed an unassessed 500-word writing task over five days, before all seven returned for a post-use focus group. Data was analysed using reflexive thematic analysis, with Expectation-Confirmation Theory as an orienting frame. The overall pattern was one of mixed confirmation. Participants' functional expectations were largely met, and the sense of being watched that they had anticipated persisted after use: for some it was offset by perceived
fairness, while for others it heightened self-monitoring. The bounded AI assistant divided them: its limits were welcomed for marking out acceptable use, but some felt it weakened their ownership of the work and worried it would flatten what they produced. Across both phases, participants weighed the costs of observation against perceived gains in
fairness and asked for transparency to run in both directions. Several described already writing defensively in anticipation of accusations of AI misuse. Acceptance of process technologies was reported as being conditional on practice time, two-way transparency, and explicit data governance. Participants also questioned whether a single linear document can represent a writing process they described as messy and
multimodal. Across these accounts, process capture did not sit outside the writing it recorded but reorganised the practice it set out to observe.
Read the full abstract ▾
Machine Learning
Learning Regional Snow Water Equivalent and Snow Height Variations from Sentinel-1 InSAR Acquisitions
Luca Barco, Lorenzo Innocenti, Bianca Bartoli et al. (+3 more)
Managing water resources in mountainous regions depends heavily on reliable Snow Water Equivalent (SWE) and Snow Height (HS) data, yet these variables remain difficult to track at scale. This study evaluates three machine learning architectures (XGBoost, U-Net and SegFormer) for the joint estimation of SWE and HS variations from Sentinel-1 InSAR data over the Italian Alps, using the IT-SNOW reanalysis as reference. SegFormer achieves the best results on both targets, with an MAE of 10.391 cm for HS and 27.113 mm w.e. for SWE and the lowest variability across initializations. A feature sensitivity analysis shows that including all available features does not guarantee the lowest error, with model- and task-specific sensitivities. Spatial metrics (R2, Pearson's r) separate the three architectures far more clearly than mean error (MAE, RMSE) does, and decomposing the error per window attributes most of it to a systematic offset in the estimated mean variation rather than to the spatial pattern.
Read the full abstract ▾
All authors Luca Barco, Lorenzo Innocenti, Bianca Bartoli, Claudio Rossi, Edoardo Arnaudo, Paolo Garza
Machine Learning · Cross-listed from stat.ML
Probabilistic Geodesic Flow Matching on Location-Scale Families
Zeyuan Yu, Zhi Chang and Shiwei Lan
Flow matching (FM) has recently emerged as a promising framework for generative modeling due to its conceptual simplicity and strong empirical performance. In FM, samples are transported along a vector field parameterized by a neural network, inducing a probability path that evolves from a simple noise distribution to the target data distribution, governed by an ordinary differential equation (ODE). However, existing FM approaches predominantly rely on probability paths derived from optimal transport (OT) between Gaussian distributions, which may be suboptimal for capturing complex data with inhomogeneous structures such as heavy tail or sharp contrast. In this work, we generalize FM to the broader class of location-scale families for handling data inhomogeneity and introduce a novel class of probability paths defined as geodesics on the
manifold of probability distributions. We name this approach probabilistic geodesic flow matching to distinguish it from prior geodesic (Riemannian) FM methods defined in input space. We argue that Euclidean OT-based paths are not necessarily optimal in probability space and may limit modeling flexibility. Through synthetic
benchmarks and scientific
datasets at different scales, we demonstrate that the proposed method more effectively captures complex distributions, leading to improved or comparable performance compared with SOTA geometry-motivated generative models.
Read the full abstract ▾
Hardware Architecture
SPIMOE: Exploiting Hybrid Sparsity for Reasoning MoE Inference on Heterogeneous PIM Architectures
Rubing Yang, Cenlin Duan, Yingjie Qi et al. (+3 more)
Long-
reasoning Mixture-of-Experts (MoE) models expose two coupled inference bottlenecks: growing KV caches shift the critical path toward
attention, while sparse expert activation causes load imbalance and low hardware utilization. Although Processing-in-
Memory (PIM) offers a promising way to mitigate data movement overhead, existing PIM-based accelerators typically optimize
attention or FFNs in isolation. We propose SPIMOE, the first co-design framework that exploits hybrid sparsity for efficient MoE inference on heterogeneous PIM architectures. SPIMOE combines adaptive expert routing with block-sparse
attention and physical KV-cache eviction, and disaggregates
attention and FFNs across SRAM-PIM and HBM-PIM. Static expert mapping and dynamic sub-batch scheduling further balance channel loads and overlap the two paths. Evaluations show that SPIMOE achieves up to $8.35\times$ end-to-end speedup over an NVIDIA A100 GPU and $3.33\times$ speedup in MoE FFN execution over PIMoE, while preserving
reasoning accuracy comparable to full-
attention baselines.
Read the full abstract ▾
All authors Rubing Yang, Cenlin Duan, Yingjie Qi, Xiaolin He, Xiao Ma, Jianlei Yang
Machine Learning
Beyond Site Agreement: Re-estimation for Brain Network Generalization
Yingxu Wang, Kunyu Zhang, Yanwu Yang3 et al. (+4 more)
Cross-site out-of-distribution (OOD) generalization in resting-state functional
magnetic resonance imaging (rs-fMRI) often relies on learning task-discriminative representations from full-scan functional connectivity (FC) graphs and promoting invariance across source sites. However, FC graphs are estimated from finite, temporally correlated blood-oxygen-level-dependent (BOLD) sequences. Cross-site agreement therefore does not necessarily imply that predictive evidence remains supported under FC re-estimation within the same scan. In this paper, we propose
Brain Network Re-estimation-Informed OOD Learning (BRIO), a framework that uses within-scan FC re-estimation to guide cross-site
alignment. BRIO maps fullscan graphs and their re-estimates into consistently indexed connectome factors, enabling comparisons of their predictive contributions. It assesses re-estimation support from changes in these contributions relative to within-class subject variability and class separation. For each source-site pair and class, this task-calibrated support from both sites is combined with predictive relevance to form pairwise qualifications, which determine relative factor weights and overall
alignment strength. Leave-one-site-out experiments on four real-world
datasets (ABIDE, REST-metaMDD, SRPBS, and ABCD) show that BRIO consistently outperforms competitive baselines, with relative improvements of up to 3.8% in accuracy. These gains also persist under an alternative
brain parcellation on ABIDE.
Read the full abstract ▾
All authors Yingxu Wang, Kunyu Zhang, Yanwu Yang3, Thomas Wolfers, Yujie Wu, Siyang Gao, Nan Yin
Robotics
Efficient World Action Model Inference with Adaptive Intermediate States
Zhinnan Liu, Haozhi Han, Ruge Zhang et al. (+8 more)
World Action Models (WAMs) enable future-aware control by jointly modeling actions and environment dynamics. However, iterative
diffusion or flow inference incurs substantial denoising latency. Prior inference state offers a natural opportunity for acceleration, yet changing planning contexts, observations, and intermediate representations can quickly render retained state stale. Preserving useful computation therefore requires adapting inference state rather than reusing it as-is. To this end, we present $\mathrm{WAM}{\scriptstyle\mathrm{ACHINE}}$, a training-free framework that accelerates WAM inference by preserving and adapting inference state for efficient and accurate continuation as the control loop evolves. Across closed-loop replans, Trajectory Remapping remaps replan state from the preceding replan to initialize the next replan, reducing redundant trajectory generation. Across denoising steps, Observation Rebinding performs anticipatory inference during action execution and rebinds retained denoising state to the real observation for continuation when consistency checks pass, reducing latency exposed to the control loop. Across
Transformer layers, Residual Rescaling selectively rescales retained layer state and refreshes it through full computation of the middle layers when probe checks fail, reducing repeated
Transformer computation. Evaluations of three representative WAM architectures on LIBERO and RoboTwin 2.0 show that $\mathrm{WAM}{\scriptstyle\mathrm{ACHINE}}$ achieves 1.47-3.05$\times$ speedups in observation-to-action latency and 2.23-3.27$\times$ speedups in GPU inference time per replan, while preserving 96.69-99.54% of native WAM task success.
Read the full abstract ▾
All authors Zhinnan Liu, Haozhi Han, Ruge Zhang, Teng Ma, Tao Ma, Zheng Liu, Yifeng Chen, Yunquan Zhang, Ting Cao, Yunxin Liu, Kun Li
Computer Vision
WorldAttention: An Efficient Attention Architecture for Interactive Video World Models
Zeyu Zhang, Jinyuan Mao, Dakai An et al. (+6 more)
Leveraging the paradigm of autoregressive
diffusion, text-conditioned interactive
video world models aim to simulate temporally coherent environments guided by textual instructions. While enabling low-latency, long-duration generation is pivotal for
embodied AI and simulation-based planning, current frameworks primarily rely on sliding-window mechanisms to bound computational complexity. However, this approach inherently sacrifices historical context, undermining the long-range interactive capabilities. Conversely, maintaining a full-history cache remains computationally prohibitive and
memory-intensive: the quadratic complexity of
attention leads to excessive computational overhead, while the linear growth of the KV cache inevitably leads to GPU
memory saturation. To overcome these limitations, we propose WorldAttention, a system-oriented
attention architecture that achieves high efficiency through the co-design of specialized
attention kernels and hierarchical KV cache management. First, we introduce Hybrid Sparse
Attention (HSA), which integrates linear global
attention supplemented with head-adaptive sparse
attention. Additionally, we design a Hierarchical KV Cache (HKV) that organizes historical KV pairs into semantically indexed pages across multi-tier
memory, enabling fine-grained
retrieval and controlled GPU residency. These two designs are supported by tailored kernels to effectively translate their theoretical efficiency into real-world performance. Extensive experiments on VBench-Long and InterVBench demonstrate that WorldAttention consistently surpasses prior state-of-the-art methods, achieving subject consistency scores of 0.9472 on VBench-Long and 0.9668 on InterVBench, respectively.
Read the full abstract ▾
All authors Zeyu Zhang, Jinyuan Mao, Dakai An, Wangbo Zhao, Hanfeng Lu, Jiasheng Tang, Yinghao Yu, Wei Wang, Bohan Zhuang
Machine Learning
PMOPD: Task Ordering, Cycling, and Parameter-Update Subspace Protection in Multi-Teacher On-Policy Distillation
Youzhi Liu, Ruobing Zheng, Boyuan Tong et al. (+5 more)
Multi-teacher on-policy
distillation (MOPD) has emerged as a popular post-training paradigm for integrating specialized capabilities in frontier
language models. Existing OPD research has primarily focused on optimizing single-task
distillation through objective design,
distillation scope, and teacher signal construction, whereas MOPD must aggregate multiple capabilities in shared parameters and address the resulting capability seesaw, in which improving one domain suppresses capabilities acquired from another. Inspired by the distinctive update geometry of OPD, we find that parameter updates from different tasks rapidly concentrate in their respective low-dimensional subspaces during MOPD, providing a direct
geometric basis for identifying and controlling cross-task interference. We therefore propose PMOPD (Projection-based Multi-Teacher On-Policy
Distillation), which constructs subspace
memories from the cumulative parameter displacements of different tasks and projects both gradients and optimizer updates to remove components that interfere with protected task directions. We further develop a lightweight conflict probe to characterize task interactions and guide task ordering, together with a cycling strategy that balances subspace estimation and timely task revisitation. Experiments on representative Code, Reason, and Math tasks show that PMOPD improves every evaluated capability over MOPD, raising the average score across the three tasks by 2.54 points on Qwen2.5-7B and 2.09 points on Llama-3.1-8B. These consistent gains establish geometry-aware optimization as an effective and transferable approach to balanced multi-teacher
distillation.
Read the full abstract ▾
All authors Youzhi Liu, Ruobing Zheng, Boyuan Tong, Tianqi Li, Pingqi Li, Hanbo Bi, Yi Yuan, Jingdong Chen
Machine Learning
Shaping Persistent Representations from Independent Interactions
Ji Dai, Quan Fang, Junyu Gao et al. (+4 more)
World models learn environment dynamics from interaction experience. These dynamics depend on the current state and actions, as well as on properties that persist across interactions. Yet standard predictive training can reduce error using local evidence alone, without organizing persistent information into reusable context. We introduce SPRII, a training principle that uses relations between interactions as weak supervision for persistent context while retaining the learner's native objective. For example, different trajectories of the same system share persistent properties even when their states and actions differ. SPRII uses such relations to guide context learning without numerical property labels. Two composable components encourage contexts from related interactions to agree (Align) and use one interaction's context to predict another's future (Cross). Our analysis distinguishes three linked questions: what persistent information is accessible in the learned context (Formation), how that context influences a fixed predictor (Use), and whether it reduces task error (Value). Success at one stage does not guarantee success at the next. Controlled experiments show that more reliable relations improve representation organization, but adding a shared-property constraint can reduce access to a property that remains shared. Context substitutions change predictions at fixed model weights, while the benefit from history depends on prediction horizon and readout. Evaluations span thirteen settings, including controlled physical systems, public dynamics tasks, robotic and tactile data, and partner interaction, across multiple learner families. Relative to the corresponding baselines, SPRII yields average gains of over 10% in downstream task performance and over 15% in persistent-property readout. The project page is available at https://persistent-learning-review.netlify.app/interactive.html.
Read the full abstract ▾
All authors Ji Dai, Quan Fang, Junyu Gao, Rongfeng Guo, Haoyan Rong, YipingHuang, Yongxi Li
Artificial Intelligence
After the Fix: Transfer of Corrected Agent Experience
Yanfei Zhang and Xu Lin
Does repairing an episode make its experience a better
memory for the next task? We transfer the same failed source before and after accepted repair to a fixed target, alongside independent execution. Our 3,300 runs cover 100 ThinkingBox pairs and the same 100 APEX pairs with and without source-state inheritance, under eleven conditions. ThinkingBox's Full/Skill/Hybrid correction gains are 44/29/32 percentage points, with corrected performance 25/22/18 points above independence; inference weakens at the task-family level. Yet 12 of Full's 15-point larger correction gap over Skill come from worse uncorrected performance, not better corrected
memory. Moreover, 22 of Full's 46 upward transitions restore observed baseline success. Neither APEX regime establishes comparable aggregate correction benefits. Action evidence connects workflow gains with reusable obligations and convention conflicts with source-local choices. Text APEX's accepted execution reaches 52% versus its summary's 40%, without robust global/group-level superiority or an estab- lished advantage over independence. Smaller handoffs reduce input but increase calls. The value of repairing experience is therefore distinct from the value of reusing it:
memory updates require both a previous-version reference and a fresh-start reference.
Read the full abstract ▾
Machine Learning
When local gains fail to transfer: Frozen Earth-observation embeddings across wildfires
Philipp Stark, Alexandros Sopasakis and Ola Hall
Frozen Earth-observation
embeddings are judged almost entirely by spatially blocked cross-validation inside one study region. We show that this number does not predict accuracy in a new region; we show why; and we show the one setting in which such a model does keep working, using a protocol that needs only a linear probe and labels one already has. The testbed is wildfire, with Copernicus burned-area maps of six fires in Greece and Spain and descriptors from the year before each fire, comparing TESSERA and AlphaEarth with ESA WorldCover classes and annual Sentinel-2 index summaries. Inside a fire, the
embeddings identify the burned land 0.05 to 0.13 ROC AUC better than the index summaries, and repeated fold allocations, spatial buffers, a block bootstrap, and gradient-boosted trees leave that margin unchanged. On a fire in another region, they lose 0.15 to 0.18 AUC, and the index summaries lose 0.06, so the three end within a few hundredths of each other. The representation is not the cause. Eight labelled blocks from the new region restore the
embedding advantage and give a higher AUC than 59,000 labelled pixels from other regions, and the weight vector fitted in one region is nearly orthogonal to the vector fitted in the others, so the part that carries across regions is small and low-dimensional.
Forecasting within a region is a different matter. Fitted on a fire that burned in 2023 and applied to a fire twelve kilometres away that burned in 2024, where nothing used postdates the target fire, TESSERA reaches 0.772 AUC and loses 0.04 against a classifier fitted inside the 2024 fire, while classifiers fitted in other regions lose 0.09 to 0.18. A region with one mapped fire can therefore forecast susceptibility for later fires there; a region without one cannot borrow a model from elsewhere, and every evaluation of a frozen
embedding should report a held-out region.
Read the full abstract ▾
Data Structures and Algorithms
A Sharper Explicit Bound on the Subtour-LP Integrality Gap for Metric TSP
Zhao Song
Karlin, Klein, and Oveis Gharan introduced a randomized better-than-$3/2$ approximation
algorithm for metric TSP [KKO21] and subsequently established the corresponding improvement in the integrality gap of the subtour-elimination LP [KKO22], with an explicit constant $\varepsilon>1.00000\cdot10^{-36}$. Gurvits, Klein, and Leake subsequently improved the certified saving to $2.18000\cdot10^{-34}$ [GKL24]. In this paper, we obtain a randomized
polynomial-time $(3/2-\varepsilon)$-approximation for every fixed $0<\varepsilon<\varepsilon_\star$, where $\varepsilon_\star>2.78621\cdot10^{-18}$, and consequently the subtour-elimination LP has integrality gap at most $3/2-\varepsilon_\star$. The classical worst-case integrality-gap lower bound is $4/3$ [Wil90].
Read the full abstract ▾
Machine Learning
The Low-Rank Structure of VLA Reinforcement Learning
Minjae Oh, Yoonah Park, Jongwon Lim et al. (+1 more)
Reinforcement learning (RL) is increasingly used to post-train
vision-
language-action (VLA) models, yet how RL reshapes these policies remains poorly understood. We find that RL across widely used flow-based VLA models, including $\pi_{0.5}$ and GR00T~N1.5/N1.6, on LIBERO, ManiSkill, MetaWorld, and CALVIN induces substantially lower-rank parameter updates that are highly concentrated in the action expert's Timestep Modules, a small and previously overlooked component. Through systematic module-replacement experiments, we further show that these modules capture a disproportionate share of the performance gains from RL. We then characterize what is encoded in these Timestep Modules. First, we show that RL specializes them to the discrete denoising timesteps used during rollouts, and that this discrete-timestep training underlies the low-rank updates. Second, we find that among their outputs, the shift vector changes most distinctly under RL, and through probing, we show that shift update directions strongly predict task success (ROC-AUC up to $99.6\%$). Third, we find that the geometry of shift updates reflects task relationships, as their pairwise similarity correlates with cross-task transfer patterns. Building on these findings, we show that steering along shift update directions further improves RL-trained policies without additional RL training. Overall, we provide a systematic understanding of how RL reshapes VLA policies by studying how learned signals are encoded in parameter space, offering insights into more efficient and interpretable VLA post-training.
Read the full abstract ▾
All authors Minjae Oh, Yoonah Park, Jongwon Lim, Yohan Jo
Computer Vision
Summarize Before Grounding: Query-Guided Chunk Condensation for Long-Video Temporal Grounding
Nanxing Hu, Xiaoyue Duan, Qiwei Yan et al. (+3 more)
Video temporal grounding (VTG) aims to localize the
video interval corresponding to a
language query. Recent large
vision-
language models (LVLMs) show great potential in solving such a multi-modal
reasoning task. However, long
videos often contain large amounts of redundant information that disturbs LVLMs to mine query-relevant evidence. Instead of dense frame sampling which incurs prohibitive training
memory, previous reinforcement learning with verifiable rewards (RLVR) works typically utilize sparse sampling, which makes training feasible but may miss critical evidence. In this paper, we propose a “summarize before grounding” framework (named “SumGround”) for long-
video temporal grounding. The key of SumGround is to perform query-guided chunk condensation to aggregate and retrieve query-relevant evidence. Specifically, we split the
video into several chunks and perform two-level chunk condensation. First, we introduce query-guided latent summaries, which is represented as KV states of query-guided
prompts, to compress redundant visual
tokens into compact query-relevant chunk summaries. Furthermore, we design an associative summary
retrieval scheme to rank and select chunk summaries that are most likely to contain the event interval. Both query-guided latent summary and associative summary
retrieval schemes are enabled by RLVR. To reduce
memory consumption, we propose a length-aware gradient gating module to selectively stop gradient back-propagated to visual
tokens. Extensive experiments demonstrate that SumGround performs favorably against previous state-of-the-art methods across multiple downstream
datasets, with remarkable gains on long
videos.
Read the full abstract ▾
All authors Nanxing Hu, Xiaoyue Duan, Qiwei Yan, Kailin Lyu, Jinchao Zhang, Guoliang Kang
Cryptography and Security
AuxMark: Defending Against Unauthorized Agent Distillation via Auxiliary Behavioral Watermarking
Yiqing Feng, Haozhe Feng, Shunan Shang et al. (+4 more)
Large
language model
agents can acquire complex capabilities through multi-step interaction and tool use, but their trajectories can also be illegally collected to dis- till student
agents. However, existing watermarking methods either do not fit the structured and interactive nature of
agent environments or lack reliable effective- ness across tasks and model architectures. We introduce AuxMark, a behavioral watermarking framework for tracing unauthorized
agent distillation. AuxMark dynamically inserts safe, non-essential auxiliary action into teacher trajectories, and stores the associated contexts as private evidence cards. To audit a suspicious student model, AuxMark constructs paired real and fake probes from these cards and applies a card-level sign test. This black-box protocol supports both model- level detection and trace-level attribution. Across three
agent benchmarks, two teacher
agents, and four student architectures, AuxMark detects all 24 distilled models with zero false positives on 48 clean models. It also preserves task utility and remains effective against data flooding, paraphrasing, truncation, and adaptive cleaning attacks. Our code will be released at this URL.
Read the full abstract ▾
All authors Yiqing Feng, Haozhe Feng, Shunan Shang, Xiaoyu Zhang, Jian Lou, Haodong Zhao, Mingxun Zhou
Computer Vision
Temporal Modelling for Burn Scars on Sentinel-3
Luca Barco, Edoardo Arnaudo, Andrea Bragagnolo et al. (+2 more)
Rapid and accurate burn scar delineation from satellite imagery is essential for post-fire damage assessment. Sentinel-3 OLCI, with daily revisit and 21 spectral bands, suits rapid mapping, yet most pipelines treat acquisitions independently, leaving the pre/post-fire change signal unexploited. We present a
dataset of 246 wildfire activations (2016-2025) from the Copernicus Emergency Management Service, with Sentinel-3 OLCI temporally paired acquisitions. We
benchmark spatial and temporal (ConvLSTM-augmented) variants of three backbones (U-Net, SegFormer, ConvNeXt-UPerNet) under two input modes and spectral configurations. Temporal modeling improves
segmentation only when pre-fire frames are included, and a 5-band subset matches the full 21-band OLCI configuration.
Read the full abstract ▾
All authors Luca Barco, Edoardo Arnaudo, Andrea Bragagnolo, Claudio Rossi, Paolo Garza
Robotics
Aerial GRIPPER: A Gradient-based Real-time Inverse-game Predictor and Planner
Zeshuai Chen, Meng Wang, Jindou Jia et al. (+2 more)
Accurate capture of non-cooperative targets is critical. In an attempt to tackle this intractable challenge, an aerial gripper system integrated with a Gradient-based Real-time Inverse-game Predictor and PlannER (GRIPPER) framework is proposed. The interaction is formulated as a general-sum pursuit-evasion game under incomplete information. Specifically, underlying cost parameters of the target are inferred online, and the open-loop Nash
equilibrium (OLNE) strategy is iteratively refined within a receding-horizon loop. To ensure high-frequency execution, a computationally friendly gradient-based inverse-game solver is developed. Without explicit computation of the Hessian inverse, the optimized solution is updated (> 50 Hz) based on implicit differentiation and fast Hessian-vector products. Meanwhile, an anti-disturbance controller is developed to overcome disturbances of uncertain payload and gripper actuation, enabling precise tracking of the planned trajectory and accurate grasping of the target. Simulations and real-world experiments illustrate the superior computational efficiency and task performance of GRIPPER. The task of capturing and delivering a non-cooperative target is accomplished, highlighting the robustness, adaptability, and real-time performance of the framework in highly
adversarial scenarios.
Read the full abstract ▾
All authors Zeshuai Chen, Meng Wang, Jindou Jia, Xiang Yu, Lei Guo
Machine Learning
Deep Weighted Bellman Residual Minimization for $Q^*$ Estimation
Lican Kang, Jerry Zhijian Yang, Cheng Yuan et al. (+1 more)
Off-policy evaluation is a foundational component of offline reinforcement learning, aiming to assess and optimize policy performance using pre-collected
datasets. However, such
datasets often suffer from pronounced challenges, including distribution shift, $Q$-value overestimation, and low sample utilization efficiency. To address these issues, this paper introduces a weighted Bellman residual minimization framework that incorporates density ratio weighting by effectively integrating expert demonstrations with behavioral data. The proposed weighting scheme departs from the conventional completeness assumption commonly imposed in the theoretical analysis of deep reinforcement learning. We establish a sharp convergence rate for density ratio estimation and derive the convergence rate for the excess risk of resulting deep $Q^*$
estimator. Extensive empirical evaluations demonstrate that, compared to existing methods, our method achieves significant improvements in numerical performance and policy generalization, providing specific guidance for the rational utilization of expert demonstrations.
Read the full abstract ▾
All authors Lican Kang, Jerry Zhijian Yang, Cheng Yuan, Chen Zhong
Artificial Intelligence
TULIP: Targeted LLM Unlearning at Layers Identified Per-input
Yejin Kim, William F. Shen, Seokwon Jung et al. (+2 more)
Representation-level unlearning modifies the intermediate hidden states of LLMs. Although knowledge is distributed across layers, existing methods operate at a single fixed layer for the entire forget set. We ask whether such a fixed layer is sufficient for unlearning. To answer this, we design a hijacking experiment that grafts hidden states of the target model into an oracle model. The oracle cannot produce the forget answer on its own, yet it produces the answer from the grafted state. This indicates the answer is already formed at an intermediate layer and read out afterward. Moreover, the layer where formation ends varies widely across inputs. Motivated by these findings, we propose Targeted Unlearning at Layers Identified Per-input (TULIP). For each input, TULIP uses the logit lens to locate the formation-readout boundary and removes the hidden state's
alignment with the forget answer's unembedding vector at that layer. TULIP outperforms output- and representation-level baselines on TOFU, PISTOL, and WMDP across Llama, Qwen, and Zephyr models. It also remains robust to paraphrase and quantization attacks. Beyond standalone use, its per-input layer selection serves as a plug-and-play component that further improves existing methods.
Read the full abstract ▾
All authors Yejin Kim, William F. Shen, Seokwon Jung, Daeun Park, Seong Joon Oh
Computation and Language
The Model Knows When to Stop: Training-Free Early Stopping for Long-Context Reading
Muath Alyobi, Mohamed Eltahir, Almoayyad Abuljdail et al. (+3 more)
Language models often process long inputs sequentially in chunks, but continuing to read after sufficient evidence has been acquired wastes computation. Existing stopping mechanisms either learn sufficiency from internal activations or train an exit gate, while a simpler alternative asks the model whether it has read enough. We introduce Answer-Convergence Stopping (ACS), a training-free stopping rule that measures rather than asks. After each chunk, it probes the frozen model's current answer state and stops when that state is both confident and stable. The rule requires only output-side generation and
token log probabilities, has no trained components, and uses one shared configuration across models and
benchmarks. Because a stopping policy can save computation simply by stopping too early, we evaluate the stopping decision itself using evidence position where available. On the full LongBench-v2 with two frontier models, ACS is the only stopping policy that matches or exceeds full-reading accuracy. Furthermore, across 250 S-NIAH questions, the premature stopping rate for ACS across five models from two families ranges from 0% to 12%, compared to 8.4% to 45.6% for the verbalized gate. Taken together, ACS reveals that by properly utilizing the output signals of frozen models, we can achieve favorable behaviors like adaptive stopping without the need for additional training.
Read the full abstract ▾
All authors Muath Alyobi, Mohamed Eltahir, Almoayyad Abuljdail, Riyadh Almutawa, Tanveer Hussain, Naeemullah Khan
Computer Vision
Reinforcement Learning from Intermediate Renders for Image-to-Code Generation
Omri Kaduri, Kate Feingold, Phillip Isola et al. (+1 more)
Reinforcement learning is increasingly used to post-train
vision-
language models for image-to-code generation, such as generating SVG code from a reference image, by optimizing rewards computed from the final rendered output. However, relying on a single terminal reward provides sparse feedback that is poorly aligned with the contribution of individual
tokens. A generated program may contain operations that accurately reproduce some parts of the target image alongside others that introduce errors, yet all
tokens are trained from the same final outcome. We observe that many intermediate code prefixes are not only executable, but already produce meaningful partial renders that reflect progress toward the target. This property provides a natural source of denser supervision during generation. Based on this observation, we introduce IR4RL, an RL framework with a
token-level render-progress reward that turns changes between intermediate renders into localized feedback for the generated sequence. We evaluate our approach on Image-to-SVG and Image-to-TikZ generation. Across both tasks, our method improves over supervised fine-tuning and standard GRPO, yielding new state-of-the-art open-source models. This shows that intermediate rendering provides a simple and effective source of process supervision for RL post-training of image-to-code models.
Read the full abstract ▾
All authors Omri Kaduri, Kate Feingold, Phillip Isola, Tali Dekel
Distributed Computing
AgentWare: Automating the Lifecycle of Agentic Applications across the Edge-to-Cloud Continuum
Michalis Kasioulis, Moysis Symeonides, George Pallis et al. (+1 more)
Deploying LLM-enabled agentic applications across the Edge-to-Cloud continuum remains challenging due to hardware heterogeneity, deployment complexity, limited observability, and the lack of systematic evaluation methods. Existing solutions address
agent development, observability, or benchmarking separately, offering limited support for the full lifecycle of distributed agentic applications. This paper presents AgentWare, an AgenticOps framework that automates the provisioning, deployment, observability, and evaluation of agentic applications across Edge-to-Cloud infrastructures. AgentWare introduces an end-to-end lifecycle pipeline that automatically prepares heterogeneous execution environments, transforms user-defined
agent implementations into distributed applications, deploys
agent components across the continuum, and performs unified collection of execution traces, infrastructure telemetry, and evaluation metrics. The framework further supports automated semantic evaluation through LLM-as-a-Judge workflows and generates reproducible reports covering correctness, performance, resource utilization, and energy consumption. We demonstrate the applicability of AgentWare through a distributed book assistant
agent deployed across real Edge-to-Cloud infrastructure under multiple deployment and model configurations. The results show that AgentWare enables systematic experimentation and evaluation of distributed agentic applications while significantly reducing the manual effort required for deployment, instrumentation, and analysis.
Read the full abstract ▾
All authors Michalis Kasioulis, Moysis Symeonides, George Pallis, Marios D. Dikaiakos
Machine Learning
Compute Time Scaling with Recursive Models for Combinatorial Optimization
Zhengxi Zhang and Paul Swoboda
We propose Tiny Recursive Models for Combinatorial Optimization (\ours{}), a general neural method for combinatorial optimization that scales both depth (how often we recursively invoke our network) and width (how much we sample in parallel). Both are fundamental for combinatorial optimization: hard instances demand a large amount of compute, while a small network is essential to avoid overfitting and capture the algorithmic essence of optimization. In particular, our method consists of a graph-aware tiny recursive model that iterates on a latent state with adaptive halting and needs only a lightweight problem-specific decoder. Compared with previous heatmap-based general neural solvers, it achieves a better balance between solution quality and inference speed on both the Traveling Salesman Problem~(TSP) and the Maximum Independent Set~(MIS) problem, and remains competitive with hybrid methods that combine neural components with heuristics specific to each problem. With the same backbone architecture for both tasks, \ours{} outperforms every
diffusion-based solver on TSP from 500 to 10,000 cities at a lower inference cost, and on the standard Erdős–Rényi-[700-800] MIS
benchmark it surpasses all neural solvers except those that only work well on MIS. We then explore self-relabeling for self-supervised training. We periodically replace the current set of training labels with the model's own better solutions, as an alternative training signal. Self-relabeling can, while forgoing supervision from near-optimal solutions, still result in on-par quality.
Read the full abstract ▾
Computation and Language
In-game Toxic Detection: Bi-directional Representations with Attention Residuals
Yuanzhe Jia
In-game toxic
language has emerged as a critical concern in the gaming industry and community. While several frameworks and models for online game toxicity analysis have been proposed, detecting toxicity in player chat utterances remains a formidable challenge: stemming not only from the extremely short length of such utterances but also from the heavy reliance on game slang, abbreviations, and domain-specific jargon, which generic
language models are poorly suited to recognize. This paper presents a shared task for in-game toxic
language detection built upon real-world in-game chat data, and proposes the best-preforming model for the toxic
language slot filling: Bi-directional Representations with
Attention Residuals (BRAR). Experimental results demonstrate that BRAR effectively captures the global context and outperforms the existing baselines on slot filling.
Read the full abstract ▾
Numerical Analysis
The paxotopy method for finding isolated roots of a system of nonlinear equations
Sándor Bozóki
We focus on systems of nonlinear equations, where some equations are non-
polynomial. Building on the remarkable developments in solving
polynomial systems during the recent decades, and on a few extensions to specific examples of the transcendental case, a general framework for finding isolated roots is proposed. The name paxotopy is proposed after (1)
Polynomial ApproXimation of the transcendental functions, then (2) solving the approximating
polynomial system by the homOTOPY continuation method, and finally (3) the roots of the
polynomial systems are used as starting points of a Newton's iteration to arrive at the solutions of the original system. These steps combine the advantages of local and global methods.
Read the full abstract ▾
Artificial Intelligence
SpeechCritic: Learning a Diagnostic Speech Judge from Limited Human Preferences
Mingyue Huo, Shivam Mehta, Bhavin Jawade et al. (+2 more)
Human
speech conveys rich perceptual information, such as
emotion and speaker identity, yet most automatic
speech quality judges reduce it to a single naturalness score. We study diagnostic
speech judges: given two candidates, a diagnostic judge decides which is better, along which perceptual dimensions (e.g., timbre,
emotion, timing) they differ, and which audible cues support its decision. Learning such judges is challenging: expert annotation is costly, and simply prompting a frontier audio-
language model to produce labels is unreliable: our probing reveals substantial errors and unstable instruction following. We introduce SpeechCritic, which learns a diagnostic judge in a reference-conditioned cross-lingual setting from only about 300 human-labeled comparisons. Rather than replacing the frontier model, SpeechCritic calibrates it with these labels: for each dimension, it selects the acoustic measurements that agree with human judgments, maps them to A/Tie/B probabilities, and passes these to the model as non-binding hints alongside the audio. Compared with the same model labeling without hints, this raises dimension-level agreement with humans by 6.3 points and cuts the mismatch with human Tie rates by 10.4 points. We then train a 7B judge on this supervision and find that different training signals shape different judge behaviors: SFT establishes the task, OPD transfers the teacher's dimension-level strengths and weaknesses, and RL helps most on clear-cut comparisons where human raters agree. Notably, human listeners also find that RL makes rationales cite more specific, localized acoustic cues, although it never directly rewards rationale text. Finally, we show that the pipeline is
language-pair agnostic by instantiating it on both English-Japanese and English-Spanish. Together, these results demonstrate a path from limited human preferences to a diagnostic
speech judge.
Read the full abstract ▾
All authors Mingyue Huo, Shivam Mehta, Bhavin Jawade, Yinghong Lan, Haoqi Li
Computer Vision
Shaobo Ju, Haiyang Yu, Xuecheng Wu et al. (+5 more)
Temporal
video grounding is a key capability of advanced
Multimodal Large
Language Models (MLLMs) for the thorough understanding of
video events, which is however often limited by repeated actions and visually similar contexts in long
videos. In this paper, we study this issue from the perspective of On-policy
distillation (OPD) and propose a new training regime for MLLMs termed Counterfactual
Attention Policy
Distillation (CAPD). In particular, OPD is a viable solution for MLLMs via providing dense teacher supervision on student-generated trajectories. But its next-
token based teacher-student
distillation is hard to identify the specific
video segments supporting each predicted timestamp, which is critical for temporal grounding. In this case, CAPD measures how masking each temporal group changes the teacher's output distribution. The resulting counterfactual influence calibrates the teacher's
attention and weights
token-level
distillation, allowing the student to learn the temporal evidence that affects boundary prediction. To validate CAPD, we trained it on Qwen3-VL-8B-Instruct using only 2,500 samples for one epoch, and evaluated it on the TimeLens and multiple general
video benchmarks. Experimental results show that CAPD improves average recall by 12.0% relative to GRPO on TimeLens while preserving general
video understanding, achieving comparable accuracy to the base model.
Read the full abstract ▾
All authors Shaobo Ju, Haiyang Yu, Xuecheng Wu, Qiong Wu, Jiacong Wang, Fan Shi, Jun Peng, Yiyi Zhou
Systems and Control
On the Achievable Inertia Constant of Inverter Based Resources
Christos M. Nikolakakos, Hassan Haes Alhelou and Nikos Hatziargyriou
As inverter-based resources (IBRs) displace synchronous generators, the inertia they can actually contribute to the grid becomes a critical planning parameter. Unlike synchronous machines, this contribution is bounded simultaneously by the available energy reserve, the converter power rating combined with voltage ride-through (VRT) obligations, and the inertia-emulation control scheme with its activation delay. This paper derives each bound in closed form and combines them into a unified envelope $\Heff(t,\lambda,V_g)=\min(\HE,\HP,\HC)$, which uses parameters accessible to the system operator to quantify how much inertia a plant can provide at a given loading $\lambda$, grid voltage $V_g$, and time $t$ after a disturbance. The analysis shows that below a loading-dependent critical voltage, VRT reactive-current priority does not leave active-current headroom for inertial power injection; that the converter overload ratio $\kappa$ matters mainly during voltage dips; and that de-loading yields a linear, quantifiable inertia gain, while collocated energy storage (ESS) removes the source-coupling constraint, making grid-following (GFL) and grid-forming (GFM) plants with storage equivalent post-activation, up to the GFL activation-delay discount within short RoCoF measurement windows. Simulations on the IEEE 9-bus system confirm the framework and motivate a two-dimensional inertia capability curve $H(\lambda,V_{g,\min})$ as a grid-code instrument analogous to the P–Q diagram of synchronous generators.
Read the full abstract ▾
Computer Vision
GenNVS: Geometry-enhanced Novel View Synthesis via Disentangled 3D Prior
Yajiao Xiong, Youyu Luan, Xiaoyu Zhou et al. (+1 more)
Single-image novel view synthesis remains challenging because the underlying 3D geometry is highly ambiguous. Recent
diffusion-based approaches produce plausible results, but they often struggle to preserve the
geometric structure and spatial coherence of foreground objects. We present GenNVS, a framework for geometry-enhanced novel view synthesis via a disentangled 3D prior. Specifically, GenNVS models foreground objects and the background with 3D Gaussian Splatting and aligns them through a coarse-to-fine
geometric optimization process to form a unified 3D scene. This scene conditions a
video diffusion model through the proposed Dual-Stream Masking mechanism, which guides synthesis by jointly exploiting rendered validity masks and geometry-aware warping. Experimental results show that GenNVS performs favorably against recent methods in both visual quality and
geometric accuracy, while naturally supporting flexible scene editing.
Read the full abstract ▾
All authors Yajiao Xiong, Youyu Luan, Xiaoyu Zhou, Yongtao Wang
Artificial Intelligence
Calibrated Uncertainty for Informative Path Planning in Aquatic Environmental Monitoring
Samuel Yanes Luis, Alejandro Casado Pérez, Alejandro Mendoza Barrionuevo et al. (+3 more)
Informative Path Planning for scalar field reconstruction uses predictive uncertainty to direct sensing vehicles toward maximally informative locations. Gaussian Processes provide this signal but their stationary isotropic kernels are misspecified for non-homogeneous phenomena such as oil spills, producing miscalibrated estimates that degrade planning. We investigate whether replacing the Gaussian Process with a well-calibrated Deep Ensemble improves path planning outcomes, and whether uncertainty quality interacts with the choice of planning
algorithm. Five strategies ($\epsilon$-Greedy, Value Greedy, Uncertainty Greedy, Monte Carlo Tree Search, and Receding Horizon Orienteering) share a common Deep Ensemble backbone trained on physics-based oil spill simulations. On held-out
stochastic spill scenarios, the Deep Ensemble reduces normalised reconstruction error by $83\%$ relative to the Gaussian Process baseline. Crucially, well-calibrated uncertainty amplifies the importance of the planning strategy: the performance gap between
algorithms is negligible under miscalibrated models but becomes substantial under the ensemble, where multi-step lookahead planners outperform greedy selection by up to $32\%$ in reconstruction error and achieve IoU above $0.85$. Monte Carlo Tree Search is the recommended planner, matching Orienteering in reconstruction quality at an order-of-magnitude lower computational cost.
Read the full abstract ▾
All authors Samuel Yanes Luis, Alejandro Casado Pérez, Alejandro Mendoza Barrionuevo, Dame Seck Diop, Sergio Toral Marín, Daniel Gutiérrez Reina