Computer Vision
Hierarchical Curriculum Learning for Surgical Video Generation: Focusing on Bilateral Axillo-Breast Approach Robotic Thyroidectomy Datasets
Youngbin Kong, Seungho Lee, Jae Kyung Shin et al. (+3 more)
High-fidelity surgical
video generation is increasingly important for surgical education, simulation, and downstream AI training, as conventional simulation pipelines are limited by cost, realism, and scenario diversity. Adapting generic text-to-
video diffusion models to surgical procedures remains difficult, however, due to complex anatomical structures, intricate tool-tissue interactions, the inherently hierarchical nature of surgical workflows, and the scarcity of curated training data outside a few well-studied procedures. We propose a surgical
video generation framework that combines hierarchical procedural annotation with curriculum transfer learning. Surgical procedures are decomposed into three levels (phase, task, and action) and a pretrained text-to-
video diffusion model is progressively adapted from coarse to fine-grained surgical context, supported by a dynamic sampling strategy that handles variable-resolution and variable-length surgical clips. We instantiate the framework on Bilateral Axillo-Breast Approach robotic thyroidectomy, a procedure for which no curated
benchmark currently exists. Relative to the preceding task-level model, the final action-level model reduces FVD by 20.1% and FID by 15.7%, and a matched-budget ablation indicates that these gains arise from the curriculum design rather than from additional training. A user study with six clinicians rates visual realism highly while highlighting remaining gaps in anatomical accuracy and clinical reliability. The proposed framework offers a step toward AI-driven surgical simulation in procedures where curated data are scarce.
Read the full abstract ▾
All authors Youngbin Kong, Seungho Lee, Jae Kyung Shin, Jong-hyuk Ahn, Hyoun-Joong Kong, Kyu Eun Lee
Computer Vision · Cross-listed from eess.IV
Deficit-Driven Stratified Acquisition for Building STRATA-S12: An Open SAR-Optical Corpus for Self-Supervised Learning
Christian Sanchez-Leon, Dongming Chen and Dongqi Wang
Building a co-registered SAR-optical corpus for self-supervised Earth Observation is above all an acquisition problem, yet the main multi-modal
datasets are collected opportunistically, with no per-stratum quota control and no mechanism against the geographic dropout that non-uniform cloud cover leaves behind. We present Deficit-Driven Stratified Acquisition (DDSA), an
algorithm that treats building a co-registered Sentinel-1/Sentinel-2 corpus as a constrained maximum-coverage problem over a hemisphere-corrected (class x season x region) stratification, enforces strict temporal pairing and a multi-stage quality gate, and closes the loop during acquisition with a human-in-the-loop deficit-repair stage. Measured on its own product, the
algorithm yields three results a single-pass acquisition cannot report. Deficit-driven ordering makes a partial run a covering one: it holds every one of the 192 strata populated from the first few percent of the budget, where an abundance-first order leaves most strata empty until the end. Whether a failed attempt can be recovered depends on the temporal persistence of its cause, not the kind of defect:
geometric failures such as nodata are among the most repairable (eta = 41.4%) while cloud is among the least (eta = 18.8%), because a cloudy location is cloudy on most dates of its season. The repair loop supplies 39.5% of the released pairs at no measurable quality cost, with 89.8% surviving manual review. The quality guarantee has a price: 2,928,370 acquisition attempts produced 740,746 released pairs. We release the corpus, STRATA-S12, with STAC/PDS4-aligned FAIR sidecars, and a pre-registered linear-probe check confirms it is fit for self-supervised pre-training. A metadata-level coverage comparison against SSL4EO-S12 and SEN12MS situates the corpus over a shared frame; systematic cross-corpus and cross-method comparison is left to follow-up work.
Read the full abstract ▾
Machine Learning
Dynamic K-Head: Difficulty-Supervised Budget Selection for Continuous Latent Reasoning
Ying Li, Yuqi Chen, Sixuan Li et al. (+1 more)
Chain-of-thought (CoT) improves
reasoning but incurs substantial autoregressive rationale cost. Continuous CoT moves intermediate computation into recurrent hidden states, yet typically uses a fixed number of updates even though the best budget varies across questions and accuracy need not improve monotonically with $K$. We introduce Dynamic K-Head, a question-conditioned, pre-rollout budget selector. It is jointly trained with the reasoner under selected budgets, using difficulty supervision based on scores assigned from the question alone. We also show that latent-update count can misrepresent end-to-end cost because a short latent rollout can shift computation into a longer explicit continuation. We therefore count latent updates, implementation-specific special
tokens, and all decoded text. Instantiated with CoDI on Llama 3.2 1B and GSM8K, Dynamic K-Head reaches 54.44% exact-match accuracy at 12.03 average
reasoning/output
tokens, compared with 52.31% at 15.21
tokens for fixed-$K=6$ CoDI—a 2.12-point gain with 20.9% lower
token cost. Across three out-of-distribution arithmetic
datasets, it reduces cost by 19.3–25.7% while improving accuracy by 0.30–2.22 points. These results demonstrate that difficulty-supervised budget selection can improve both accuracy and efficiency, while stable budget selection remains a central challenge.
Read the full abstract ▾
All authors Ying Li, Yuqi Chen, Sixuan Li, Yunfeng Cai
Numerical Analysis
Least-Squares Finite Element Methods with Weakly Imposed Boundary Conditions: Norm and Error Equivalences, Over-Penalization, and Fully Discontinuous Discretizations
Shun Zhang
Weakly imposed boundary conditions in first-order system least-squares methods go back to Jespersen (1977), but two questions have remained open for decades: the right weights, especially for the Neumann residual, whose natural norm $H^{-1/2}$ suggests $h_F$, and norm and error equivalences, especially for indefinite equations. We answer both for general, possibly indefinite, second-order elliptic equations with non-homogeneous mixed boundary conditions. First, for the weights $h_F^{-1}$ on the Dirichlet and $1$ on the Neumann residual, we prove norm and error equivalences with mesh-independent constants for every discrete pair: the error in a mesh-dependent norm is equivalent to the square root of the functional plus a Dirichlet data term. The least-squares solution converges optimally in $H(\mathrm{div};\Omega)\times H^{1}(\Omega)$, and the functional is a reliable and efficient error
estimator, with a recovered flux also for approximations from other methods, even ones violating the boundary conditions. The key idea is to apply the stability of the boundary value problem to pairs that are discrete only in their Dirichlet traces, whose $H^{1/2}$ norm an inverse inequality bounds by the weighted penalty. Second, these weights are the right ones: weaker powers, including $h_F$ on the Neumann boundary, destroy the norm equivalence, and stronger weights are admissible, since the penalty multiplies zero at a comparison function meeting the projected data. Third, for the fully discontinuous counterpart, a pure penalty method with both jumps weighted by $h_F^{-1}$, the error equivalence holds for every discrete pair, also for exact fluxes with normal traces not square integrable on interior faces.
Read the full abstract ▾
Distributed Computing
A Minimum Exact Disjunctive Basis for Two-Robot Solvability Profiles
Tsukasa Ninomiya, Shota Naito, Naoki Kitamura et al. (+2 more)
We completely characterize the solvability profiles of tasks for two autonomous mobile
robots in the plane under variable disorientation, chirality, and rigid movements. The four standard capability models and the schedulers considered here have a known quotient order Q of thirteen computational classes. A task's solvability profile is the set of classes in which it is solvable, and is necessarily an upset of Q. We prove that every upset is realizable and construct a minimum exact disjunctive basis of thirteen concrete tasks. The basis contains one task for each principal upset. For every antichain of Q, the disjunction of the corresponding tasks has profile exactly equal to the union of their profiles. This exactness is not implied by the individual profiles: an
algorithm may satisfy different disjuncts in different executions. We establish it by constructing, for every
algorithm in each maximal class outside the target union, a single admissible fair execution violating all selected predicates simultaneously. Consequently, the realizable profiles form the entire finite distributive
lattice Up(Q): there are exactly 54 profiles, counted by the antichain
polynomial 1 + 13z + 24z^2 + 16z^3, and each has a canonical disjunctive representation using at most three principal tasks. We also identify six tasks whose solvability signatures recover every inclusion and incomparability in Q, and prove that six is minimum even among arbitrary separating tasks. Their profiles are precisely the principal upsets generated by the join-irreducible elements of Q. In contrast, any task family generating every profile by exact disjunctions must contain all thirteen principal profiles. Thus our exact disjunctive basis has minimum size and is unique at the profile level.
Read the full abstract ▾
All authors Tsukasa Ninomiya, Shota Naito, Naoki Kitamura, Yuichi Sudo, Koichi Wada
Information Retrieval
RALI@iKAT 2026: Retrieval-aware User Profile Denoising via Personalized Conversational Dense Retrieval
Yuchen Hui, Fengran Mo, Jia Ao Sun et al. (+3 more)
Modern conversational information access systems continuously extract user information from conversations to build user profiles for personalized
retrieval. As user profiles accumulate over time, they inevitably become noisy, making effective user profile denoising a fundamental challenge. Existing personalized conversational query reformulation methods rely on the black-box
reasoning capability of LLMs to expand the original query with relevant user profile phrases, producing a verbose query for
retrieval. Such rewrite-then-retrieve pipelines reduce user profile denoising to the explicit selection of profile phrases in the sparse
token space, separating personalization from downstream relevance modeling. Consequently, they often fail to identify user information that is truly beneficial for
retrieval. To enable
retrieval-aware user profile denoising, we propose Personalized Conversational Dense
Retrieval (PCDR), which learns to jointly project the conversation history and user profile into a latent
embedding space dedicated to
retrieval. By inheriting the context denoising capability from conversational dense retrievers, PCDR requires only a handful of personalized relevance annotations for training. We evaluate PCDR on the iKAT 2026 tasks, where it serves as the core
retrieval component of a conversational AI
agent assisting users with complex information needs.
Read the full abstract ▾
All authors Yuchen Hui, Fengran Mo, Jia Ao Sun, Yuxing Tian, Wenhao Xu, Jian-Yun Nie
Artificial Intelligence
Encounter-Driven City-Scale Human Mobility Generation with Large Language Models
Chao Li, Renhe Jiang, Chuan Xiao et al. (+1 more)
Large
language models (LLMs) have shown strong potential for human mobility generation by modeling individual routines, activities, and mobility preferences. However, existing approaches remain largely resident-centric: generating realistic individual trajectories does not necessarily recover the encounters that emerge when multiple residents co-occur at the same place and time. To this end, we study encounter-aware human mobility generation, which jointly preserves individual mobility and population-level interaction structure. We propose EncounterMob, an encounter-driven LLM framework consisting of a coarse-to-fine Encounter Generator and an Iterative Coupling Framework. The Encounter Generator first captures city-level encounter rhythms and then instantiates participant-time-venue encounters, while the Iterative Coupling Framework coordinates these encounters with personal mobility behavior through successive refinement. We further introduce an encounter recovery protocol covering encounter marginal and joint distributions over residents, times, and venues. Experiments on the Japan and NYC
datasets show that EncounterMob outperforms all external baselines on all seven encounter metrics and all six personal mobility metrics. Compared with ELLMob, it reduces the participant-time-venue joint error by 40.4%/41.7% and the mean personal mobility error by 58.8%/32.7% on Japan/NYC, respectively.
Read the full abstract ▾
All authors Chao Li, Renhe Jiang, Chuan Xiao, Jiawei Wang
Graphics
Integrating 3D Posture Neutralization with Statistical Shape Modeling for Head-Neck-Shoulder Ergonomic Design
Jinbo Luo, Hang Ren, Yadie Yang et al. (+1 more)
The design of ergonomic products and workspaces requires a deep understanding of human anatomy and posture. In particular, the head-neck-shoulder region is critical for many applications such as cervical orthoses, helmets, and other head-worn or neck-worn devices. This paper presents a framework that integrates posture neutralization with statistical shape modeling (SSM) for the head-neck-shoulder (HNS) region. We acquire a single three-dimensional (3D) scan of the head-neck-shoulder region from each of 200 Chinese adults in a natural posture for each subject. Every scan is then posture-neutralized before SSM. We fit a parametric head-neck model to each scan to separate cervical pose from anatomy, and reset the cervical pose to a common neutral configuration, so that the resulting model captures anatomical shape variation rather than posture-induced deformation. The resulting shape space yields a standardized template and population-wide modes of variation, providing baselines for parametric ergonomic design. We further discuss how the model supports population coverage analysis and the design of products that accommodate anatomical diversity while maintaining neutral cervical posture.
Read the full abstract ▾
All authors Jinbo Luo, Hang Ren, Yadie Yang, Jie Zhang
Artificial Intelligence
Cowork-Gym: Synthesizing Interactive Work Environments at Scale
Anni Zou, Cheng Chen, Jiaji Deng et al. (+18 more)
Cowork
agents navigate dependencies across tools and files while adapting to changing user requirements and edits to shared workspaces. Scaling such environments requires maintaining consistency among task objectives, executable resources, user behavior, and success criteria. We introduce Cowork-Gym, a framework that synthesizes Cowork environments through a build-execute-revise loop that uses execution evidence and review feedback to validate and repair generated environments. To capture realistic Cowork dynamics, a stateful user simulator responds to the
agent's actions through dialogue and direct edits to the shared workspace. We synthesize 64.9K environments across 14 application scenarios and use them to post-train 9B, 27B, and 35B-A3B Qwen models with supervised fine-tuning, reinforcement learning, and on-policy
distillation. Averaged across six agentic
benchmarks, these models outperform their corresponding base checkpoints by 8.7, 6.4, and 4.1 points, respectively. Ours-27B ranks second overall among the evaluated models and achieves the highest average scores on PawBench and ClawEval, outperforming models with over 100B total parameters on both
benchmarks.
Read the full abstract ▾
All authors Anni Zou, Cheng Chen, Jiaji Deng, Weikang Zhou, Xinji Mai, Yue Wu, Jianing Lin, Lipeng Xie, Lixiong Qin, Qingyue Zhao, Que Shen, Shuchang Tao, Xuchen Pan, Yaliang Li, Yunpeng Zhai, Yushuo Chen, Zhihai Wang, Zhuo Zhang, Zhaoyang Liu, Bolin Ding, Jingren Zhou
Robotics
PrT-Flow: Probability-Tractable Flow Matching for Reinforcement Learning
Congzhong Sun and Ning Tan
Diffusion models and Flow Matching can represent flexible distributions over
robot actions, but many reinforcement learning
algorithms also require the probability of each action. We introduce PrT-Flow (Probability-Tractable Flow Matching), which computes probability density while retaining
multimodal, multi-step action generation. Its Jacobian-Tractable
Transformer (JTT) makes each sampling step invertible and enables efficient computation of its Jacobian determinant. We train these finite steps with Conditional Euler-step Training (CET), which supervises their displacement over one step during sampling rather than their instantaneous velocity. We prove that, under certain assumptions, CET has the same minimizers as fitting the Euler-solver updates of Flow Matching. PrT-Flow achieves 96% success on Robomimic Lift after 300 epochs of imitation learning, matching the
diffusion policy reference, and 96% success on OGBench Cube-Triple after 600k online steps. These results demonstrate that invertible networks with tractable probability densities can learn effective
robot policies and support SAC-style actor-critic training. Our code is available at https://github.com/Sunlight-zero/PrT-Flow .
Read the full abstract ▾
Machine Learning
DeltaTTG: Training Multi-Turn Agents with a Token-to-Go Progress Meter
Xuyan Ye, Xiyan Fu, Shengda Fan et al. (+3 more)
Reinforcement learning with verifiable rewards (RLVR) for multi-turn
agents relies on sparse terminal rewards that say little about individual steps. Within-group step comparisons depend on reliable state matching and sufficiently diverse sampled outcomes, while direct step scoring may require costly external evaluators, human annotations, or task-specific heuristics. We introduce DeltaTTG to learn a reusable progress signal through a shared progress meter, using low-cost supervision from diverse policies' recorded trajectories without task-specific progress rules. Its supervision target,
Token-to-Go (TTG), the number of
tokens remaining to be generated until task completion, serves as an observable proxy for remaining completion effort. During actor training, changes in the frozen meter's estimates redistribute outcome-derived advantages across steps without altering the reward, preserving each trajectory's advantage sign and
token-average scale. On ALFWorld, PaperSearchQA, and BFCLv3, DeltaTTG improves the average score over GRPO by 5.7 and 7.2 points with Qwen3-4B and Llama-3.1-8B-Instruct, respectively, outperforms all compared RL baselines on average, and keeps actor-training GPU-hours close to GRPO. Further experiments show improved sample efficiency and out-of-domain performance, and support the meter's ability to distinguish step quality and guide test-time action selection across actor sizes. The code is available at https://github.com/Xuyan923r/DeltaTTG.
Read the full abstract ▾
All authors Xuyan Ye, Xiyan Fu, Shengda Fan, Jiawei Cui, Yankai Lin, Wei Lu
Artificial Intelligence
RoTA-Bench: Evaluating 3D Spatial Reasoning through Interactive Projection Alignment
Qingchuan Ma, Yuexiao Ma, Xiang Meng et al. (+7 more)
Can
vision-
language models turn 2D observations into 3D understanding that supports precise action? This requires inferring object geometry, anticipating the effects of rotation, and refining actions through visual feedback. We introduce RoTA-Bench to evaluate these abilities through interactive 3D-to-2D projection
alignment. Given a target silhouette, a model observes a rotated object and chooses successive rotations to recover the target projection within a limited action budget. Our automated pipeline constructs silhouette-preserving 3D objects from 2D icons and uses reversible initialization to guarantee solvability, yielding 674 tasks and a stratified 100-task test set. Empirically, we find that (i) a substantial human-model gap persists: GPT-5.6-Sol succeeds on only 17% of tasks, whereas 20 undergraduate participants collectively complete the test set four times with a 100% success rate; (ii) image-space and pose-space progress can diverge: at matched states, the model more often improves silhouette overlap while worsening pose
alignment than humans (19.4% vs. 10.9%); and (iii) fine-grained control is sensitive to interaction history: removing it leaves 96.8% of the model's actions at a coarse 30-degree step size and sharply reduces observed task success. These findings highlight the challenge of converting visual evidence into precise 3D control, beyond recognizing or matching individual images.
Read the full abstract ▾
All authors Qingchuan Ma, Yuexiao Ma, Xiang Meng, Yixuan Zou, Tianyu Xie, Wang Chen, Yuhui Zeng, Yuhang Wu, Xiawu Zheng, Rongrong Ji
Data Structures and Algorithms
Hitting Minors: Stronger Lower Bounds
Jongseo Lee, Roohani Sharma and Sebastian Wiederrecht
For a fixed finite collection of graphs $\mathcal{F}$, the $\mathcal{F}$-Minor-Free Deletion problem asks, given a graph $G$ and an integer $k$, whether there is a set $S\subseteq V(G)$ with $|S|\leq k$ such that $G-S$ contains no graph of $\mathcal{F}$ as a minor. This generalizes Vertex Cover, Feedback Vertex Set, and Vertex Planarization, among many others. Baste, Sau, and Thilikos [JCSS 2020, SICOMP 2023] showed that, assuming the Exponential Time Hypothesis (ETH), there are collections $\mathcal{F}$ for which the problem cannot be solved in time $2^{o(\mathrm{tw}\log\mathrm{tw})}n^{O(1)}$ on $n$-vertex graphs of treewidth $\mathrm{tw}$, and gave a matching
algorithm. We ask whether this super-exponential dependence persists under more restrictive structural parameters. First, we strengthen their lower bound. Assuming ETH, for every fixed $h\geq 6$, $\{P_h\}$-Minor-Free Deletion, where $P_h$ is the path on $h$ vertices, cannot be solved in time $2^{o(t\log t)}n^{O(1)}$, where $t=\mathrm{fvs}+\mathrm{td}$ is the sum of the feedback vertex set number and treedepth of the input graph. These two parameters are incomparable, but both individually upper bound the treewidth. Together with the $2^{O(\mathrm{tw}\log\mathrm{tw})}n^{O(1)}$-time
algorithm of Baste, Sau, and Thilikos [SICOMP 2023], our lower bound is tight. In contrast, we show that asymptotically faster
algorithms are possible when parameterized by the vertex cover number $\mathrm{vc}$. Specifically, for any finite family $\mathcal{F}$, $\mathcal{F}$-Minor-Free Deletion can be solved in time $2^{O(\mathrm{vc})}n^{O(1)}$. Taken together, our results show that the boundary between single-exponential and super-exponential complexity for this problem lies between the vertex cover number and the feedback vertex set number (plus treedepth).
Read the full abstract ▾
Computation and Language
The Image Still Has a Say: Final-Answer Repair for Multimodal Chain-of-Thought
Yulan Pan, Xiaoyu Xu and Zhihong Shen
Although chain-of-thought prompting has improved
multimodal reasoning, it is still difficult to produce correct final answers, as the
reasoning can drift away from the image. Besides, the trace is already fixed when the answer is generated, leaving no room for self-correction. Considering the image is still available at the final-answer step, we think it is reasonable to fix the answer there without rewriting the
reasoning. As such, the problem becomes to correct the final answer using the image under fixed
reasoning. Unlike methods that improve trace generation through training, resampling, or decoding-time grounding, we repair the final-answer readout while keeping the
reasoning trace fixed. The motivation is based on our finding that a wrong option can become prematurely committed in the
reasoning while the correct option still has stronger image support in middle-to-deep layers. Thus, we propose Text-to-Visual Evidence Reallocation (TVER), a training-free method for final-answer repair. Specifically, TVER selects answer-related text and question-matched image patches, and moves bounded
attention from text to patches. Furthermore, the patches are chosen in a middle-to-deep layer window based on question relevance. Our method improves answers across
benchmarks and backbones, with gains in both multiple-choice and open-answer evaluations.
Read the full abstract ▾
Computer Vision
ScenePercept: Scenario-Conditioned Perceptual Assessment of Real-World User-Generated Content Images
Shuhan Xia, Yu Chen, Xiang Wang et al. (+3 more)
The rapid development of mobile imaging and social platforms has led to explosive growth in user-generated content images, making their systematic and comprehensive perceptual assessment increasingly important. Existing image perception
benchmarks are typically task-oriented, curating specific scenarios for quality or aesthetic assessment and applying a uniform perceptual criterion across diverse scenarios. This limits their ability to capture the scene diversity and perceptual complexity of real-world UGC images. To address these limitations, we introduce ScenePercept-Bench, a
benchmark designed to reflect the distribution of real-world UGC images, comprising 23,100 images across 21 categories and 105 fine-grained scenes. To account for the influence of scene context on human perception, we design a hierarchical, scene-aware annotation protocol, covering visual quality, aesthetic perception, and scene semantics, with 15 attributes in total. Each image is annotated with an overall score, 15 attribute-level scores, and structured explanatory
reasoning. Building on this
benchmark, we further introduce Scenario-Conditioned Perceptual
Alignment, a training framework that tackles the heterogeneity of perceptual criteria across scenarios. SCPA jointly optimizes absolute score prediction, preference ranking, and cross-scenario calibration, preserving the model general perceptual assessment ability while encouraging it to explore and adapt perceptual criteria across different scenarios. Extensive experiments demonstrate that SCPA achieves state-of-the-art performance in UGC image perception and generalizes effectively to established IQA and IAA
benchmarks.
Read the full abstract ▾
All authors Shuhan Xia, Yu Chen, Xiang Wang, Shuai Li, Peipie Li, Zekun Li
Human-Computer Interaction
InSight: A Mobile Assistant Helping Visually Impaired People Navigate Unfamiliar Environment
Junwei Zheng, Jiale Wei, Di Wen et al. (+6 more)
Navigating unfamiliar outdoor environments is one of the most demanding everyday tasks for people with visual impairments (PVI). However, existing navigation systems cannot simultaneously satisfy the needs of informative perception and precise localization during navigation. This paper explores the core navigation demands of PVI through a preliminary study. Based on the results of the pre-study, we present the design of InSight, a mobile assistant that combines scene descriptions with precise localization to support PVI navigating unfamiliar outdoor environments. The offline mode of InSight runs entirely on device for real-time navigation, while the online mode streams camera frames to a self-hosted server for arbitrary object detection and accurate localization. Finally, a user study with 21 visually impaired participants validates that InSight could assist users in navigating unfamiliar outdoor environments with increased success rate and confidence compared to mainstream navigation applications like Apple Maps.
Read the full abstract ▾
All authors Junwei Zheng, Jiale Wei, Di Wen, Yufan Chen, Ruiping Liu, Chengzhi Wu, Kunyu Peng, Kailun Yang, Jiaming Zhang
Artificial Intelligence
Can Agents Truly Forget? Explore Machine Unlearning for LLM Agents
Junkai Lin, Ge Xu, Zheng Xu et al. (+2 more)
Large
language model (LLM)
agents have shown strong capabilities in interactive problem solving, tool use, and long-horizon task execution. However, they may also acquire sensitive or private knowledge during training and expose it during deployment. Retraining a model from scratch to remove such knowledge is prohibitively costly, making machine unlearning a more practical approach. Machine unlearning aims to remove targeted undesirable knowledge from trained models without retraining from scratch while preserving general utility. When
language models are deployed as
agents, parameter-level unlearning becomes insufficient: forgotten information may still persist in
memory artifacts or be reacquired via tool calls. In this paper, we formulate the problem of
agent unlearning as removing private information from an LLM-based
agent across three information channels: parametric knowledge, persistent
memory, and tool-call acquisition. To study this problem, we introduce we introduce
Agent Unlearning
Benchmark (AUBench), a controlled
benchmark that extends the fictitious-author setting of TOFU into an
agent environment with persistent
memory, an offline web snapshot, tool-accessible documents, and provenance-tracked interaction trajectories. By evaluating existing parameter-level and
memory-level unlearning methods in this setting, AUBench reveals the gap between model-level forgetting and system-level
agent unlearning, and provides a foundation for developing unlearning methods that operate across the full lifecycle of LLM
agents.
Read the full abstract ▾
All authors Junkai Lin, Ge Xu, Zheng Xu, Junkai Chen, Xiangyuan Lan
Computation and Language
Worth Their Weights? Evaluating Generative Models for Discourse Parsing
Luke Gessler and Amir Zeldes
Rhetorical Structure Theory (RST) parsing has historically been dominated by discriminative models based on pretrained encoder-only
language models. The recent availability of high-quality generative
language models has made it unclear whether RST parsing is better approached as a generative task. In this work, we investigate whether generative
language models are better at parsing RST than traditional discriminative ones. We find that at matched parameter counts, discriminative parsers perform much better than generative ones, though much larger generative models sometimes outperform them. Generative models hold a particular advantage in elementary discourse unit (EDU) segmentation, and we report new state-of-the-art results on the RST-DT
benchmark in end-to-end parsing as well as segmentation.
Read the full abstract ▾
Robotics
Towards a Systematic Study of Embodied System 2 over Full Task Execution Cycles
Yuxi Wei, Ye Fang, Shuai Yang et al. (+3 more)
An embodied
brain, or System 2, must turn an abstract goal into actions while discovering relevant scene conditions and checking whether executed skills achieved their intended effects. Open-loop evaluations cannot test observations shaped by an
agent's decisions, while some closed-loop evaluations provide limited evidence during execution or assume idealized skill outcomes. We introduce SCOPER, a suite for studying observation-grounded planning, execution, and recovery. SCOPER-bench combines high-level goals, ongoing visual observations, a shared rule-based System 1 for low-level actions, and controlled execution failures. Its construction and validation pipeline yields 870 tasks across BEHAVIOR and ProcTHOR, complemented by about 3,500 situated questions tied to the evaluated
agent's execution.
Benchmark results reveal difficulties in retaining scene evidence, monitoring progress, and recovering from unexpected outcomes. To address these difficulties, SCOPER-harness combines Evidence
Memory and Progress Verification with a dynamic task agenda and bounded exploration, without additional model training. Across two evaluated open-source backbones and two simulators, the harness improves task success by 11.1-28.6%; a harnessed 9B model outperforms a directly executed 27B model on both simulators. In an offline next-action evaluation using observations from 200 real-
robot demonstrations, the harness also improves full-call accuracy by 14.7% and 15.3%. SCOPER provides a setting for diagnosing and improving embodied
reasoning throughout a complete task execution cycle.
Read the full abstract ▾
All authors Yuxi Wei, Ye Fang, Shuai Yang, Tong Wu, Tai Wang, Xiaojuan Qi
Computer Vision
Open-o3-Video-v2: Seek, Ground, and Reason with Verifiable Spatio-Temporal Evidence
Jiahao Meng, Zhongyuan Bao, Yue Tan et al. (+7 more)
Reliable
video reasoning requires models to produce correct answers and expose supporting visual evidence. Open-o3-
Video enables verifiable
reasoning by
embedding timestamps and object-level bounding boxes into
reasoning traces, but is restricted to frames from an initial sparse sampler. We introduce Open-o3-
Video-v2, which formulates
video reasoning as a unified agentic evidencegrounded process. The model identifies missing information, acquires additional observations, grounds the moments and objects supporting its
reasoning, and writes this evidence into the trajectory before continuing or answering. To support this behavior, we construct STGR-v2-CoT135K, including 52K multi-turn agentic grounded
reasoning trajectories, and STGR-v2-RL-13K for reinforcement learning. We further propose Clue-Seek GRPO (CS-GRPO), which tracks how tool calls change accumulated evidence, rewards clue coverage and step-wise gains, and penalizes excessive, repetitive, or uninformative
retrieval. On V-
STaR, Open-o3-
Video-v2-4B achieves 40.4% mAM and 56.3% mLGM, outperforming its Qwen3-VL-4B backbone by 8.5% and 12.6%, respectively. It also delivers consistent gains across general
video understanding, long-
video reasoning, and temporal grounding
benchmarks. These results show that active evidence acquisition and verifiable object-level grounding are complementary for reliable
video reasoning. The code and models are released at https://msalab-pku.github.io/projects/Open-o3-
Video-v2.
Read the full abstract ▾
All authors Jiahao Meng, Zhongyuan Bao, Yue Tan, Haiquan Wen, Renrui Zhang, Anna Wang, Jason Li, Yanwei Fu, Yunhai Tong, Ming-Hsuan Yang
Information Theory · Cross-listed from stat.ML
textGrain watermarking is harder to detect: can sum-tests still do it optimally?
Swapnaneel Bhattacharyya and Soham Bonnerjee
Watermarking embeds an imperceptible signal in text from large
language models that is statistically detectable with a secret key. The recent textGrain watermark (Li et. al. (2026b)) calibrates this signal against the model's sampling
entropy through an explicit
entropy budget, combining the stochasticity of Red-Green and the unbiasedness of Gumbel-max watermarks, and its accompanying report proposes a detector that sums pivotal statistics. We study when, and how efficiently, textGrain can be detected after human edits, modeled as a sparse mixture in which a fraction $\varepsilon_n\asymp n^{-p}$ of positions retain the watermark and
token uncertainty decays as $n^{-q}$. First,
entropy calibration comes at a cost: the minimax detection boundary of textGrain is $p+q=1/2$, so its detectable region is strictly smaller than that of Gumbel-max and maximal-coupling watermarks, whose boundary is $2p+q=1$. This cost stems from textGrain's construction rather than from
entropy calibration itself: an unbiased scheme with the same
entropy loss remains detectable where textGrain is not. Second, perhaps surprisingly, this loss makes the sum detector optimal at the boundary when the number of transport columns is fixed, unlike for Gumbel-max. When the number of columns grows and the
entropy budget does not vanish, the detectable region expands while that of the sum detector does not. Third, for a fixed edit fraction, we characterize the optimal exponential rate of type II error decay and show that the sum detector falls strictly short of it at every fixed alternative. Finally, we propose a weighted multiscale binomial scan, valid in finite samples and needing no knowledge of the next-
token distributions,
entropy budget, or edit fraction; it attains every detection boundary above and the optimal exponent.
Read the full abstract ▾
Computation and Language
Decouple to Forget: Semantic Mediation for Sensitive Unlearning in Large Language Models
Jingyue Cong, Andy Song, Yang Yu et al. (+7 more)
Machine unlearning for large
language models seeks to remove specified knowledge while preserving general capability, yet current methods often treat an entire response as the unit of forgetting. This coarse granularity causes unnecessary utility loss when the forget target is only a small set of sensitive facts embedded within otherwise benign explanations. In this paper, we introduce Decouple to Forget (D2F), a targeted unlearning method inspired by semantic mediation that separates sensitive factual content from non-sensitive meaning and surface expression. For each example to be forgotten, D2F extracts a fact-level "mediator" representation from the answer, identifies which parts are sensitive, and removes only those parts while leaving the rest of the structure intact. We then generate counterfactual answers grounded in this mediator that preserve non-sensitive content but exclude sensitive facts, employing preference-based contrastive optimization to reduce the likelihood of information leakage while maintaining helpfulness and fluency. Experiments across various
benchmark datasets show that D2F achieves a better balance between forgetting and retention than strong baseline methods. Our code is available at https://github.com/JingyueCong/D2F.
Read the full abstract ▾
All authors Jingyue Cong, Andy Song, Yang Yu, Tabinda Sarwar, Xinshu Li, Ziqi Xu, Xun Yi, Ke Wang, Bo Han, Estrid He
Robotics
Code2Worlds-2: Physically Plausible Agent Harness for Embodied World Simulation
Haoyu Zhang, Siming Li, Zeyu Zhang et al. (+3 more)
Recent coding large
language models (LLMs) can synthesize dynamic 4D worlds from natural
language, but the resulting content remains a visual artifact. It lacks physical semantics such as the collision geometry, mass, friction, inertia, and joint structure, required to enable it to simulate the physical world, and its dynamics are scripted to look plausible rather than designed to execute. What is needed is an executable world: one that a physics engine can load and step, resolving contact physically. We present Code2Worlds-2, an extension of Code2Worlds that turns 4D world generation into an embodied world simulation. We keep the original dual-stream generation pipeline intact and append two modules. First, a SimReady Scene Compiler that turns a generated visual scene into a simulator-compatible representation: it assigns collision meshes via convex decomposition, estimates physical attributes with a
vision-
language model, infers a lightweight support graph, instantiates the engine's contact, friction, and dynamics constraints, and applies a
gravity settling pass, before exporting the scene as MuJoCo MJCF. Second, a Simulator-in-the-Loop 4D Refiner that implements an automated
agent harness-a compile, simulate, critique and refine loop-that converts visual dynamics into executable rigid and articulated dynamics and evolves the physical settings rather than only the code, replacing the purely visual motion critic with a simulator critic that inspects penetration depth, collision pairs, stability, contact forces, joint limits, and
robot reachability. We further propose SimCode4D, a state-based
benchmark with five task templates for evaluating embodied simulation. Experiments on SimCode4D and across natural, indoor, industrial, urban, and service scenes show that Code2Worlds-2 produces physically plausible, simulator-compatible, and
robot-interactable scenes.
Read the full abstract ▾
All authors Haoyu Zhang, Siming Li, Zeyu Zhang, Yi Zhang, Tat-Seng Chua, Hao Tang
Computational Complexity · Cross-listed from quant-ph
Nearly Optimal Quantum Sample Complexity of Learning Fourier-Sparse Boolean Functions
Zekun Ye
We study the number of uniform
quantum examples needed to exactly learn a Boolean function with at most $k$ nonzero
Fourier coefficients. We give a learner with near-optimal $\widetilde{O}(k)$ sample complexity independent of the input length $n$. The learner uses only separate measurements of individual examples. This improves the previous $O(k^{3/2}\log^2 k)$ upper bound (Arunachalam, Chakraborty, Lee, Paraashar, and de Wolf, 2021). The main ingredient is a candidate set formed by symmetric differences of subsets from independent groups of
Fourier samples. A multilinear majority
polynomial combines unbiased random approximations into an accurate witness whose
Fourier support lies in this set. Granularity then forces the set to contain the entire
Fourier support, including subsets never directly sampled. For comparison, we derive the tight classical sample complexity $\Theta(nk)$ by combining known sparse-recovery and lower-bound results.
Read the full abstract ▾
Systems and Control
Service-Aware Hosting Capacity Assessment of Edge Data Centers with Workload Flexibility
Linhan Fang, Haoxiang Wan, Anurag Srivastava et al. (+1 more)
The growing demand for edge computing, content delivery, and AI services is driving the interconnection of edge data centers (DCs) with distribution networks. Before interconnection, utilities evaluate how much DC capacity can be accommodated without violating feeder current and voltage limits. Fixed peak load representations can overlook service dependent demand patterns, cooling related facility demand, and delay tolerant computing tasks. This paper develops a hosting capacity (HC) assessment model for edge DCs with shiftable workload scheduling. Three representative types are considered: mobile edge computing (MEC), content delivery network (CDN), and AI DCs. Facility demand is modeled by combining fixed base demand, service driven demand, prescribed cooling-overhead coefficient, and a shiftable workload component. Workload execution is optimized under arrival causality, maximum delay, daily energy balance constraints, and the resulting active and reactive loads are embedded in a distribution power flow model. Compared with the baseline without load shifting, the maximum bus level HC gain on the IEEE 33-bus system reaches 4.46% for MEC DCs and 9.89% for AI DCs, while CDN case shows negligible gain under the assumed cache management windows.
Read the full abstract ▾
All authors Linhan Fang, Haoxiang Wan, Anurag Srivastava, Xingpeng Li
Machine Learning
DisaggKD: Efficient Knowledge Distillation through Teacher-Student Disaggregation and a Fused Loss
Ruixuan Tu and Yuyang Dong
Knowledge
distillation (KD) frameworks place teacher and student on the same GPUs, so per-GPU
memory limits the teachers that fit. DisaggKD separates them across nodes: teacher replicas stream hidden states to the student, a KD loss over row windows and vocabulary shards equals the full-vocabulary loss in exact arithmetic without forming the full-vocabulary logits, and a prefetch ring paces producer and trainer. Closed-form
memory and traffic models locate the
memory limits of each layout. On the Qwen3.5-35B-A3B to 9B pair, the disaggregated layout matches the LM loss of the colocated run with the same loss and is faster than that run; our fused loss also lets a colocated run train on as few nodes at faster speed, while the split is
memory efficient when the student spans several nodes. On the larger pairs, colocated runs with a fused loss still run OOM where the split trains, because teacher weights and student states fill the budget.
Read the full abstract ▾
Artificial Intelligence
When Should Enterprise Policy Decisions Be Learned, and When Should They Be Reasoned?
Hyojung Han, Ryangkyung Kang, Youngeun Kim et al. (+1 more)
An enterprise
agent that answers under a written policy must choose an action before it says anything: answer, ask for a missing fact, ask for confirmation, call one or several tools, escalate, or refuse. Holding one 27B Korean enterprise model fixed, we vary whether the decision is a generated JSON object or a single constrained
token, and whether the model may reason first. On 2800 in-distribution items we did not detect an accuracy difference between the two deployed paths (93.46% vs 94.14%), while they differ about tenfold in restart stability (3.00% of actions flip vs 0.29%); they also differ in
reasoning, so this is an operational comparison. On a sealed
benchmark of 300 items whose labels come from a hidden executable policy,
reasoning is worth +17.3 points [+12.3, +23.0] on exact action. With
reasoning off, the format difference was 0.0 points [-4.3, +4.0], a failure to detect an advantage for either interface, not equivalence; with
reasoning on it is unresolved. Against a
token-matched random control, boundary-targeted supervision moves the two covered boundaries by +17.5 and +20.0 points and leaves a held-out boundary unchanged. In a 3-seed training x
reasoning factorial, the sealed-rendering interaction is -4.9 [-8.1, -1.7], consistent with partial substitution. All supervision was Korean. On independently rendered English versions, the model is 0.82 points lower [-2.68, +0.93] with
reasoning on, the same order as re-rendering in Korean; the
reasoning-off gain from targeted supervision is not stable in either
language, so we do not claim transfer. The original text stays private as the confirmatory set. An open-model re-rendering made after these results reproduced the
reasoning effect and the English verdict; the interaction kept its sign but did not replicate under item-clustered intervals. We release the model and that re-rendering with gold labels.
Read the full abstract ▾
All authors Hyojung Han, Ryangkyung Kang, Youngeun Kim, Seung-Hun Jeon
Artificial Intelligence
Beyond Bias Scores: Answerability Confounds in Activation Steering with Gradient-Constrained Direction Design (GCD)
Weitong Li, Donglin Song, Junkai Lin et al. (+1 more)
Bias scores in
language-model evaluations often conflate what a model prefers with whether it answers at all. We identify this confound in BBQ, whose ambiguous score factorizes into answerability and signed preference. Across 11 categories, 28,}824 items, and five models, contrastive steering lowers the signed ambiguous score in 11/11 categories but lowers the signed disambiguated preference score in only 8/11. Across 99 configurations, the answerability channel exceeds half of the observed score change in 17% and accounts for the entire change in 11%. In a six-category disambiguated evaluation, 20.8% of 1,500 items flip to the unknown option, where abstention is incorrect; StereoSet shows no analogous answer-rate shift. The effect reflects selection and near-orthogonality between the contrastive and preference-gradient directions. We introduce Gradient-Constrained Direction Design (GCD), an option-gradient construction with a first-order unknown-logit constraint. Under a matched Qwen-7B protocol, GCD reduces answer-rate distortion 14-fold and yields a 4-fold larger preference change, while ablations show similar gains for alternative and unconstrained option-gradient directions; nulling the unknown gradient alone is not responsible for the gain. We recommend reporting answerability alongside published scores.
Read the full abstract ▾
All authors Weitong Li, Donglin Song, Junkai Lin, Xi Xuan
Computer Vision
MemAct: Streaming Spatial Understanding with Memory and Active Exploration
Yuxi Wei, Wei Huang, Qirui Chen et al. (+2 more)
Spatial understanding is essential for embodied
agents navigating and interacting with the physical world. As observations arrive incrementally,
agents must reason in a streaming manner. Yet streaming understanding must also be closed-loop: task-relevant evidence may require both recalling past observations and actively acquiring new views. Existing streaming approaches largely emphasize processing incoming observations, leaving task-driven active exploration underexplored. We introduce MemAct, a framework for streaming spatial understanding with
memory and action. A shared
vision–
language model incrementally writes structured historical
memory, retrieves records and past frames on demand, and acquires additional evidence through movement and turning. Retrieved evidence and action observations inform subsequent decisions, enabling the
agent to continue exploring or answer within a unified
reasoning loop. We develop the MemAct suite, a data generation pipeline and collection across real and simulated environments, with approximately 1M training examples for spatial
reasoning,
memory writing,
retrieval, and exploration. Its MemAct-bench comprises 20,000 main QA pairs evaluating current-observation understanding, historical evidence use, and active exploration, plus 2,000 separate Timing questions. MemAct combines supervised fine-tuning for
memory and interaction with counterfactual action optimization using cumulative evidence gains, action costs, and terminal answer quality to improve exploration and stopping decisions. Experiments show that MemAct outperforms existing spatial understanding and streaming baselines and approaches frontier
multimodal models on MemAct-bench while retaining streaming inference efficiency.
Read the full abstract ▾
All authors Yuxi Wei, Wei Huang, Qirui Chen, Lu Hou, Xiaojuan Qi
Computer Vision
FrameLite: Decision-Oriented Aesthetic Cropping with a Compact Vision-Language Model
Jianze Li, Kai Liu, Ziqing Zhang et al. (+4 more)
Aesthetic image cropping improves composition by balancing subjects, context, and image boundaries. Large
vision-
language models bring semantic knowledge to this task, but their scale limits lightweight photography assistance. We propose FrameLite, a compact cropping model built on Qwen3.5-0.8B. Our approach is motivated by the observation that a small model can generate better crops than its first answer suggests. We develop three-stage training to turn this potential into stronger direct predictions. Spatial and composition training establishes localization and framing preferences. Quality-Guided Online Supervision (QOS) then learns the highest-quality complete answers among the current policy's generated candidates. Greedy-Referenced Optimization (GRO) further refines the policy using positive and negative quality differences relative to its current greedy answer. Both online stages use annotation-derived feedback, while inference returns one coordinate answer without search or an external scorer. Experiments show that FrameLite outperforms the compared large-VLM croppers across public
benchmarks with a substantially smaller backbone. Controlled studies confirm that selecting high-quality training answers improves the final model beyond online sampling alone. We will release our code and model weights at https://github.com/JianzeLi-114/FrameLite .
Read the full abstract ▾
All authors Jianze Li, Kai Liu, Ziqing Zhang, Weihang Zhang, Yong Guo, Linghe Kong, Yulun Zhang