Robotics
Learning Reflexive Behavior for Contact-Rich Manipulation
Quan Nguyen, Yunho Kim and Joonho Lee
During contact-rich manipulation, interactions between a
robot and its environment carry information about local geometry: a surface prevents penetration, a bore guides a peg. A controller that exploits these interactions can comply with environmental constraints while preserving task intent.
Robot-earning systems commonly use position, hybrid force-position, or Cartesian impedance control. Their prescribed tracking objectives, stiffness, or force-control directions may not match local constraints and may degrade performance. We learn a proprioceptive reflex policy in simulation on three simple interaction primitives: a spring, a plane, and a rail. The policy maps task-space commands to joint-position targets using state history, without direct force or geometrical measurements. Once trained, it serves as a frozen execution layer beneath higher-level controllers. We evaluate it in dual-arm box lifting, peg insertion, and surface following. In box lifting, the reflex kept the force below the threshold while the baseline failed. In rough-surface following it stayed below the 10 N reference, on par with tuned hybrid force-position control. In 0.02 mm peg insertion It reduced mean estimated contact force to less than half that of the baseline while increasing hardware success rates from at most 22 % to 36-58 %. By separating contact response from command generation, the reflex policy provides motion planners, learned policies, and teleoperators with robust contact-rich execution.
Read the full abstract ▾
Artificial Intelligence
ROUTEAUDIT: Interaction-Aware Identification for Budgeted Multi-Verifier Routing
Miaobo Hu, Shuhao Hu, Xiaobo Guo et al. (+4 more)
Adaptive multi-verifier systems are commonly compared through endpoint quality-cost gaps, even when the verifier catalog, availability, accounting, information filtration, or scorer changes with the policy. We formulate verifier routing as a contract-conditioned identification problem. The contract records request support, verifier catalog, realized availability, resource accounting, online filtration, and post-trace scoring; a matched route contrast changes only the policy coordinate. ROUTEAUDIT adds three measurable objects to this contract. A contract
lattice averages coordinate increments over every admissible bridge order and reports the resulting attribution together with its path sensitivity. A policy-independent response tape identifies paired sequential contrasts when adaptive policies reveal different observations. For incomplete matching, request-level bounds use whichever potential outcome remains observed and give a sharp finite-population interval. The protocol commits paid observations and ledger events before the oracle join and returns an attribution certificate for each comparison. On two held-out raw-tail caches, matched static SF+SA equals the cascade, assigning the apparent gains of 0.1797 and 0.1250 over full static to the verifier-set edge. On 1,319 held-out task requests, the learned and RLVR studies report quality 0.9522 and 0.9553 versus 0.9484 for matched static; the RLVR-static paired difference is +0.0068 with a request-paired interval $[0.0015,0.0122]$ and a training-seed-by-request hierarchical interval $[0.0006,0.0131]$. Controlled attribution recovery yields route mean absolute error 0.0011 and endpoint reconstruction error 0.0004. Factorial, bridge-order, and
stochastic-provider studies evaluate the certificate interface; RLVR supplies a learned-policy stress test under the same identification contract.
Read the full abstract ▾
All authors Miaobo Hu, Shuhao Hu, Xiaobo Guo, Xin Wang, Bokun Wang, Tianshu Fu, Daren Zha
Cryptography and Security
From TS-SUF-2 to TS-SUF-4: Practical Security Enhancements for FROST2 Threshold Signatures
Will Wang, Syh-Yuan Tan, Ryan Chow et al. (+2 more)
Threshold signature schemes play a vital role in securing digital assets within blockchain and distributed systems. FROST2 stands out as a practical threshold Schnorr signature scheme, noted for its efficiency and compatibility with standard verification processes. However, under the one-more discrete logarithm assumption, with static corruption and centralized key generation settings, FROST2 has been shown by Bellare et al. (in CRYPTO 2022) to achieve only TS-SUF-2 security, which is a consequence of its vulnerability to TS-UF-3 attacks. In this paper, we address this security limitation by presenting an enhanced variant of FROST2, namely, FROST2+ which achieves the TS-SUF-4 security level under the same computational assumptions as the original FROST2. FROST2+ strengthens FROST2 by integrating additional pre-processing
token verifications that help mitigate TS-UF-3 and TS-UF-4 vulnerabilities while maintaining practical efficiency. We show that FROST2+ can achieve TS-SUF-4 security not only under the same conditions as the original FROST2 analysis, but also when initialized with a distributed key generation protocol such as PedPoP. Our
benchmark using ZCash's FROST library shows that the performance of FROST2+ is comparable to FROST2 and about 64-79% faster than FROST when precomputation is enabled.
Read the full abstract ▾
All authors Will Wang, Syh-Yuan Tan, Ryan Chow, Chanson Chan, Martin Zhao
Robotics
SARI: Phase-Split Sim-Real Co-Training for Contact-Rich Manipulation
Xingxin He, Yuxuan Jiang, Haonan Zhang et al. (+5 more)
Vision-
language-action (VLA) models often require costly real-world demonstrations to adapt to contact-rich manipulation tasks, particularly when generalization across object placements is needed. We propose SARI (Simulated Approach, Real Interaction), a phase-split sim-and-real co-training framework built on a simple insight: spatial coverage and contact physics should be acquired from the domains best suited to them. Specifically, free-space approaches require spatial diversity but tolerate modest simulation gaps, making them ideal for synthetic generation; conversely, contact interactions demand accurate physics but vary little across object placements, allowing a few real demonstrations to generalize across the workspace. SARI generates diverse simulated approaches in a photorealistic digital twin while collecting real contact interactions at only a few placements. Post-trained on these phase-segmented demonstrations, a single policy seamlessly stitches simulated approaches with real contact interactions using visual appearance
alignment and a shared camera-relative action representation–without explicit phase labels or hand-coded switches. Across five real-world contact-rich manipulation tasks, SARI reduces real-data collection time by 34.3% and achieves 27.5% success at unseen placements, where all full-task sim-real baselines fail completely (0%).
Read the full abstract ▾
All authors Xingxin He, Yuxuan Jiang, Haonan Zhang, Chuhan Cui, Kaile Li, Zhongxing Zheng, Caihao Xu, Ziqi Wang
Robotics
LOCUS: Landmark-Oriented Container Discrimination Using Spatial Graphs
Taylor Bergeron, Shibani Senthilbabu and Kevin Leahy
As
robots are increasingly deployed in unstructured, real-world environments, the ability to reason about complex spatial and semantic relationships among objects remains a fundamental challenge in enabling robust and generalizable manipulation and
navigation. For example, deciding where to search for an object that is not in plain sight depends on where it is physically plausible as well as semantically likely. Popular methods such as cosine similarity with CLIP struggle to disambiguate between spatially and semantically similar objects that could contain a target object. We propose Landmark-Oriented Container Discrimination Using Spatial Graphs (LOCUS). To jointly reason about spatial information and semantics, we train a GNN to update CLIP
embeddings on a full environment scene graph by passing
embedding information between nodes based on proximity. CLIP
embeddings, augmented by semantic knowledge from a fusion of household ontologies provide a robust semantic signal. We evaluate in simulation on a noiseless scene graph from simulator metadata, making the approach detection-agnostic. Our approach outperforms random, CLIP, Tidybot, and an LLM planner in the majority of room classes and configurations in simulation. To show our approach is robust to scene graph node placement and label noise, we demonstrate a physical mobile manipulator running in an exploration pipeline start-to-finish including scene graph labels from Detic.
Read the full abstract ▾
Robotics
ManiPhysicsBench: Physics-Based Assessment of Object Preservation in VLA Manipulation
Sangwu Park, Yeonjun In, Wonjoong Kim et al. (+3 more)
Vision-
language-action (VLA) models aim to perform diverse manipulation tasks, but task success in existing rigid-body
benchmarks does not indicate whether they preserve objects. We introduce ManiPhysicsZoo, which consolidates literature-supported material properties, 3D meshes, and supporting references into reusable object assets. Using these assets, a solver-based assessment computes grasp-specific damage thresholds from object geometry, material properties, and recorded grasp conditions and compares them with recorded contact forces to assess potential deformation and fracture. Building on these components, ManiPhysicsBench evaluates object preservation in LIBERO and SimplerEnv across three physics axes and three difficulty levels. Public VLA checkpoints show a substantial gap between task success and safe success, defined as task completion while preserving the object. Their gripper commands concentrate near full opening and closure, with largely similar aggregate distributions across objects, consistent with binary gripper supervision. We examine how object-specific continuous gripper labels change model behavior by retraining a VLA model. The retrained model shows more object-dependent gripping and higher safe success, but lower task success and limited generalization of object-preserving behavior.
Read the full abstract ▾
All authors Sangwu Park, Yeonjun In, Wonjoong Kim, Sungwon Kim, Sein Kim, Chanyoung Park
Artificial Intelligence
VIGOR: Zero-Shot Visual Generalization via Latent-Space Consistency in Model-Based Reinforcement Learning
Mingyu Park, Samyeul Noh, Hyun Myung et al. (+1 more)
Model-based reinforcement learning (MBRL) achieves strong sample efficiency by planning within learned latent dynamics, yet its performance degrades substantially under unseen visual distractions such as background variations, lighting changes, or camera shifts. Unlike model-free RL, where encoder perturbations affect only single-step predictions, MBRL suffers from a two-level vulnerability: visual distractions first push encoder outputs out of distribution, and these errors then compound through recursive latent rollouts over the planning horizon. We propose visual generalization via latent-space consistency in model-based RL (VIGOR), a framework that enables zero-shot generalization to unseen visual distractions while retaining the sample efficiency of its MBRL backbone. VIGOR integrates three interdependent components: (i) asymmetric weak-to-strong augmentation, which pairs weak-only and weak-to-strong latent views within a single batch; (ii) dynamics-level consistency, which enforces augmentation-invariant transition predictions through direct latent regression; and (iii) encoder-level stabilization, which prevents encoder drift under the cross-augmentation supervision imposed by dynamics-level consistency. Evaluations on the DeepMind Control Suite (DMC) and Robosuite show that VIGOR outperforms state-of-the-art model-free and model-based baselines, surpassing the second-best baseline by 3.4% on DMC and 43.6% on Robosuite. Ablations further show that VIGOR's robustness is augmentation-agnostic: replacing the default augmentation with alternatives from distinct perturbation families preserves strong generalization, confirming that latent-space consistency, not the augmentation choice, drives robustness.
Read the full abstract ▾
All authors Mingyu Park, Samyeul Noh, Hyun Myung, Donghwan Lee
Artificial Intelligence
BitNest: Bit-Nested Speculative Decoding for Memory-Efficient LLM Inference Acceleration
Chence Yang, Ningxi Cheng, Arash Akbari et al. (+9 more)
Speculative decoding accelerates autoregressive generation by using a lightweight draft to propose multiple
tokens for parallel verification. However, existing methods often require an additional draft model or weight representation, introducing non-negligible
memory overhead on resource-constrained devices. Self-speculative approaches reduce this overhead, yet still face trade-offs between draft quality, target quality, and storage efficiency. We propose BitNest, a bit-nested speculative decoding framework that embeds a low-precision draft directly into the higher-precision target representation. Instead of deriving a draft from a predefined target, BitNest first constructs a strong low-precision base and then recovers the higher-precision target through residual refinement, enabling both models to share a single physical weight representation. BitNest further extends this progressive-precision design to the KV cache for long-context inference. Across multiple 7B–8B edge-friendly LLMs and diverse workloads, BitNest achieves an average speculative acceptance rate of 95.2% while closely preserving higher-precision model quality, and delivers 1.48–1.61x end-to-end speedup over FP16 autoregressive decoding. On the LLaMA models supported by all representative self-speculative baselines, BitNest also achieves consistently competitive or higher decoding speedup.
Read the full abstract ▾
All authors Chence Yang, Ningxi Cheng, Arash Akbari, Qitao Tan, Qingchan Zhu, Ci Zhang, Changdi Yang, Yanzhi Wang, Wei Niu, Jinhui Wang, Jin Lu, Geng Yuan
Computer Vision
FUSEye: Training-Light Fisheye Detection with Overlapping Views and Zero-Initialized Adapters
Wenya Su, Kai Luo, Di Wen et al. (+5 more)
Fisheye cameras give mobile
robots a single-sensor, low-cost view of their surroundings, yet the COCO-pretrained detectors that practitioners routinely reuse fail on them: strong radial distortion warps local image structure, while boundary compression shrinks objects to near-invisible sizes. Full fine-tuning closes much of the gap but requires abundant fisheye labels and compute. We present FUSEye, a training-light framework that turns a frozen-backbone COCO-pretrained extra-large YOLO26 detector (YOLO26-x) into a fisheye detector. FUSEye adds roughly 227k new parameters while updating the inserted modules and the pretrained detection head. It addresses the transfer gap at three causally linked levels. At the input level, overlapping grid view generation and box remapping (GridViews) enlarge compressed boundary regions. At the feature level, zero-initialized residual adapters (Z-Adapters) correct distortion-induced feature misalignment. At the decision level, learned cross-projection agreement fusion (AgreeFusion) promotes low-confidence detections only when they are supported by consistent evidence across multiple views. On the WoodScape surround-view fisheye
benchmark, FUSEye raises YOLO26-x from 0.148 to 0.266 mAP50 and retains 84.3% fully fine-tuned accuracy. Moreover, randomly using only 25% of the labeled training images, FUSEye achieves 0.2597 mAP50, retaining 97.6% of its full-label performance. FUSEye also consistently improves YOLOv8-11 detectors, showing that the recipe is architecture-agnostic. Source code will be available at https://github.com/Su-wenya/FUSEye.
Read the full abstract ▾
All authors Wenya Su, Kai Luo, Di Wen, Ruiping Liu, Yufan Chen, Junwei Zheng, Kunyu Peng, Kailun Yang
Machine Learning
Muon Learns Facts Better: Understanding the Role of Spectral Orthogonalization
Xuheng Li, Qiwei Di, Yuan Cao et al. (+1 more)
The
Muon optimizer applies spectral orthogonalization to
matrix-valued updates and has shown strong performance in large-scale neural network training, yet the mechanisms of this transformation in feature learning remain poorly understood. In this work, we investigate this question through a tractable factual-recall model, where a fact maps each subject-relation pair to an answer, and a linear
transformer learns the subject- and relation-dependent information required to recover this mapping. The
transformer is optimized with gradient flow (GF), spectral GF, or Sign GF, which are continuous-time limits of gradient descent,
Muon, and Adam, respectively. Prior studies (Nichani et al., 2025) have shown that when the number of subjects exceeds the number of relations, GF learns relation-dependent information before subject-dependent information, producing a feature-separation phase during training. We characterize this separation with the learning times when the subject- and relation-dependent components of the prediction reach a target accuracy. With $S$ subjects and $R$ relations, GF has a learning-time ratio of $\widetilde{\Theta}(\sqrt{S/R})$, whereas Spectral GF reduces this ratio to $\widetilde{\Theta}(1)$. In addition, for fixed $S$ and $R$, the subject- and relation-dependent errors decay as $1/(T\log T)$ in training time $T$ under GF, but as $\exp(-\mathrm{poly}(T))$ under spectral GF. Finally, we show that GF and spectral GF are equivariant under orthogonal transformations of the
token embeddings, whereas Sign GF is not: Different orthonormal
embeddings can potentially produce no feature separation, a large feature-separation phase, or even a reversed learning order. These results provide a mechanistic view of how spectral orthogonalization can fundamentally reshape feature-learning dynamics.
Read the full abstract ▾
All authors Xuheng Li, Qiwei Di, Yuan Cao, Quanquan Gu
Artificial Intelligence
Modeling Shared and Individual Structure for Cross-Subject Continuous Affect Regression from EEG-fNIRS
Xuan Wang, Bing Wang, Shuai Chang et al. (+3 more)
Continuous, second-by-second valence-arousal estimation from physiological signals is typically studied in a subject-dependent setting, where the model sees labeled data from the same person it is later evaluated on. We study the harder zero-shot cross-subject variant on a synchronized
EEG-fNIRS
dataset: predict raw-scale ([1, 255]) valence and arousal trajectories for subjects whose labels the model never observes, given only their unlabeled
EEG/fNIRS recordings while watching the same
video stimuli as a disjoint set of training subjects. We decompose the affect trajectory into a structure shared across subjects who watch the same stimuli and an individual structure estimated for each test subject from a label-free
EEG marker (alpha-band cross-channel synchrony), which rescales the shared trajectory around the scale midpoint. We validate the per-subject calibration mechanism on four independent axes: leave-one-subject-out correlation between the marker and each subject's true optimal gain, a functional-form comparison against non-linear alternatives, a repeated leave-4-out component ablation isolating each part of the pipeline's contribution, and a ceiling analysis bounding the remaining headroom for per-subject scaling. On held-out subjects, the model reaches an overall MAE of 25.96 / 22.80 across two evaluation batches (valence 21.94 / 19.6, arousal 29.98 / 26.0), well below EEGNet and ASAC-Net baselines reported for the same subject-independent split (raw scale score 60.6 and 55.0 respectively). We further report a systematic negative-result search across model architectures, feature representations, and prediction targets that found no signal able to improve on the single alpha-synchrony marker.
Read the full abstract ▾
All authors Xuan Wang, Bing Wang, Shuai Chang, Hao Yuan, Xinbo Qi, Xinyue Zhang
Machine Learning
Efficient Memory Crystallization for Graph Learning under Non-Stationary Distribution Shifts
Yue Hou, Ruomei Liu, Yingke Su et al. (+2 more)
Deep graph learning models deployed in real-world systems often need to cope with non-stationary environments, where the underlying graph distribution drifts continually over time. Prevailing solutions rely on training auxiliary generative modules to synthesize
memory graphs for cross-domain adaptation, which incurs substantial computational overhead and scales poorly under prolonged distribution shifts. We argue that a more economical path exists: rather than generating
memory, one can crystallize it. To this end, we propose Efficient
Memory Crystallization (EMC), a training-free test-time framework that distills each incoming graph domain into a compact, semantically faithful
memory through a closed-form solution to a
memory-oriented distribution-matching objective, thereby eliminating redundant domain information under continual
covariate shifts. To preserve both generalizability and adaptability as the model traverses a long sequence of target domains, EMC further models inter-domain dependencies through state-evolving
memories and admits a theoretically grounded, tighter generalization error bound than direct adaptation. Extensive experiments demonstrate the superior performance of EMC over state-of-the-art baselines on graphs under non-stationary distribution shifts, while reducing average runtime by 87.4% and GPU
memory consumption by 92.4% relative to the recent competitor, making continual graph adaptation practical at scale.
Read the full abstract ▾
All authors Yue Hou, Ruomei Liu, Yingke Su, Junran Wu, Ke Xu
Artificial Intelligence
PAPER2LLM++: Continual Self-Evolution of LLMs from Research Papers
Hongji Pu, Yilun Zhao and Wenpeng Yin
Research on LLMs continually uncovers model limitations, their causes, and potential solutions. Yet these human discoveries remain largely disconnected from model
evolution: an LLM does not automatically learn from new research about its own failures. We introduce PAPER2LLM++, a framework for continual self-
evolution of LLMs from research papers. Rather than treating papers merely as knowledge to retrieve, PAPER2LLM++ uses the growing literature as a stream of evidence and supervision for model improvement. For each incoming paper, it extracts evidence-grounded findings, tests whether the reported limitation persists in the current model, and, when needed, converts the findings into candidate learning signals. A try-evaluate-commit procedure integrates an update only when it improves the targeted behavior without substantially forgetting prior improvements or degrading general capabilities. Across a sequential stream of research-discovered LLM failures, we show that models can progressively incorporate new findings while retaining earlier gains. PAPER2LLM++ thus takes a step toward closing the loop between human discovery and model
evolution, enabling models to continually learn from research about their own limitations and improvements.
Read the full abstract ▾
Artificial Intelligence
Law And Order: Tax Law Autoformalization
Sophia Simeng Han, Yoshiki Takashima, Anjiang Wei et al. (+2 more)
Legal systems are increasingly implemented through software, yet scalable methods for translating legal texts into accurate symbolic representations remain underdeveloped. We study this problem through tax law, where forms and filing instructions define large computational structures involving arithmetic, branching, recursion, and tabular
reasoning. We propose Law&Order, a neuro-symbolic framework for automatically formalizing tax forms and instructions into executable symbolic programs. Our approach establishes two forms of correspondence between law and logic: structural correspondence, which aligns legal and symbolic components such as
cells and schedules, and denotational correspondence, which requires symbolic components to implement the computations specified by their legal counterparts. We combine large
language model synthesis with
cell-level verification and iterative localized error repair using human-written OpenTaxSolver tax returns. We then evaluate the resulting formalizations on independently authored, held-out TaxCalcBench returns, that are never exposed during generation or repair. Although the most advanced LLM achieves only 66% accuracy, Law&Order achieves 100%
cell-level and form-level accuracy on 51 held-out returns, demonstrating the effectiveness of combining LLM-based synthesis with symbolic verification for scalable and verifiable large-scale legal autoformalization compared with using an LLM alone.
Read the full abstract ▾
All authors Sophia Simeng Han, Yoshiki Takashima, Anjiang Wei, Zhaoyu Li, Michael Genesereth
Robotics
Skill2Real: Agentic Skill Learning for Zero-Shot Sim-to-Real Robot Manipulation
Xincheng He, Siyu Ma, Chang Yu et al. (+5 more)
Transferring robotic skills from simulation to reality requires task knowledge that remains usable across differences in perception, dynamics, and embodiment. We introduce Skill2Real, an agentic policy framework that learns executable skills through a shared application programming interface (API). A Proposer-Verifier-Governor (PVG) loop uses privileged simulation evidence to diagnose outcomes and validate updates, while keeping learned skills grounded in public observations and API semantics. The Cerebellum first acquires local manipulation skills; the
Brain then learns task-level composition with the Cerebellum frozen. Both
memories transfer to the real
robot without task-policy fine-tuning or skill-
memory updates. As GPT-5.6 Sol learns skills on LIBERO-90, evaluating each frozen checkpoint with GPT-6 Astra raises LIBERO-Pro Long success from 2.0% to 56.3%, without training on Pro Long. Independent Robosuite training reaches 85.1% and 89.4% mean success with Sol and Opus 5 across seven tasks, respectively. Frozen Sol-trained LIBERO-90 skills achieve 78.75% mean completion across four real-world manipulation tasks with Astra. Removing the Verifier or Governor during LIBERO-90 training lowers final Pro Long success by 17.3 and 13.3 percentage points, respectively. These results support learning and transferring a hierarchy of executable skills through a common
robot interface.
Read the full abstract ▾
All authors Xincheng He, Siyu Ma, Chang Yu, Yunuo Chen, Yanjia Huang, Ying Nian Wu, Yin Yang, Chenfanfu Jiang
Machine Learning · Cross-listed from stat.ML
Hold-Out Scoring for Efficient Gaussian DAG Learning
Donguk Shin, Byeongguk Kang, Inseol Lee et al. (+1 more)
High-dimensional Gaussian DAG learning faces a statistical-computational gap: methods with sharp sample complexity rely on computationally expensive subset search and a supplied indegree bound, whereas
polynomial-time alternatives have less favorable sample complexity. We introduce HOST, an efficient DAG learning
algorithm that replaces subset search with nodewise hold-out scoring and convex regression, without requiring a supplied indegree bound. Our key insight is that recovering a correct ordering does not require uniformly small estimation errors in ordering scores but only one-sided control of those errors. In the ordering step, HOST exploits the fact that score estimation using hold-out samples inflates ordering scores in expectation, which is the favorable direction for candidates that should not yet be selected. Given the ordering, HOST recovers parents by recursively removing indirect effects from total effects between two nodes. Under suitable conditions, HOST exactly recovers a $p$-node DAG of maximum indegree $d$ with sample complexity of order $d\log p$ in
polynomial time. Experiments show that HOST achieves competitive graph recovery while exhibiting favorable runtime scaling.
Read the full abstract ▾
All authors Donguk Shin, Byeongguk Kang, Inseol Lee, Gunwoong Park
Robotics
SimpleTouch: Can Vision-Language-Action Models Master Contact-Rich Manipulation Without Tactile Policy Pretraining?
Chen Yang, Linzhe Shi, Changjie Wu et al. (+7 more)
Tactile sensing provides essential contact information for robotic manipulation, yet incorporating it into pretrained
vision-
language-action (VLA) models remains challenging. A common concern is that simply introducing touch during task-specific fine-tuning may fail to bridge the cross-modal gap, yielding limited gains or even reduced success. Consequently, existing methods often rely on large-scale tactile policy pretraining or separate visuotactile
alignment, adding data requirements and training stages. We introduce SimpleTouch, a simple VLA extension that augments $\pi_{0.5}$ with a tactile expert, to test whether these additional stages are necessary. Leveraging all
tokens from a frozen pretrained tactile encoder, the expert learns from action supervision and multi-horizon prediction of future tactile latents. This single-stage training uses only task demonstrations, without additional tactile policy pretraining or separate
alignment. With 50 demonstrations per task, SimpleTouch achieves the highest success rate among evaluated methods on all six UniVTAC tasks. Its average success rate reaches 77.5%, compared with 45.2% for FTP-$\pi_{0.5}$ and 66.7% for FTP-1, corresponding to gains of 32.3 and 10.8 percentage points, respectively. Across four real-world tasks, it averages 71.3%, exceeding FTP-1 by 8.8 percentage points. These results demonstrate that, given pretrained VLA and tactile representations, additional tactile policy pretraining is not a prerequisite for strong performance on these tasks, offering a simpler route to contact-rich manipulation. Project page: https://simpletouch-
robot.github.io/
Read the full abstract ▾
All authors Chen Yang, Linzhe Shi, Changjie Wu, Hang Zhang, Ronghan Chen, Lingjun Zhang, Xu Hu, Mu Xu, Jiansheng Fan, Chen Wang
Systems and Control
Mission-Centric Requirements Analysis of Model Predictive Control in Spacecraft Rendezvous and Proximity Operations
Nils Maier, Torbjørn Cunis and Tam W. Nguyen
Rendezvous and proximity operations (RPO) missions are commonly designed as a sequence of distinct phases each governed by its own sample time, constraint set, and cost structure, with the translation from mission-level requirements to model predictive control (MPC) design parameters typically performed ad hoc. This report takes a first step toward a systematic, traceable mapping between mission requirements and MPC design choices, using the ADRIOS / ClearSpace-1 active debris removal mission as a case study across three sequential operations. Its central hypothesis is that Economic MPC (EMPC), in which the stage cost reflects propellant consumption directly, is structurally better suited to proximity operations than fixed-point regulation or reference tracking, because it can exploit the natural, fuel-free relative-orbital-motion trajectories admitted by the Clohessy-Wiltshire-Hill (CWH) dynamics instead of fighting them. We show that a pure-fuel stage cost is fundamentally degenerate for this class of problem as the closed-loop optimum is not strictly dissipative with respect to any single target state or orbit, and analyse, operation by operation, which terminal ingredient (a terminal region, a terminal cost, a terminal equality, or a stage-cost regularisation) is required to repair this degeneracy, at what fuel and time cost, and under what formal guarantee. Across all three operations the economic controllers cut fuel consumption by roughly 40-99% relative to standard quadratic-tracking MPC, at the cost of longer manoeuvre times, and we synthesise the results into a cross-scenario table of mission requirements, MPC ingredients, and their residual limitations.
Read the full abstract ▾
Machine Learning
OPD Before RL: Warm-Starting Rubric-Based RL with On-Policy Distillation
Xinpeng Wang, Wei Shi, Yu-Chia Chen et al. (+3 more)
Many useful
language-model tasks cannot be evaluated by exact outcome verification. Rubric-based reinforcement learning (RL) addresses this issue by scoring open-ended responses against explicit criteria. However, because the reward is assigned after the complete response, the training signal does not directly identify which individual decisions contributed to the final score. We propose a two-stage training framework that uses rubrics first as privileged teacher context for dense
token-level supervision, then as rewards for further RL. In the first stage, rubric-privileged on-policy
distillation (RP-OPD), a student without access to the rubric matches a rubric-aware teacher's next-
token distributions at student-generated prefixes. In the second stage, RL directly optimizes the rubric reward and improves beyond the observed
distillation plateau. We evaluate the framework on health and science tasks using open-weight models. Across HealthBench, ResearchQA, and RubricHub Science, we compare post-training methods and vary the amount of SFT or RP-OPD training before RL, finding that our two-stage framework achieves the highest scores among the methods evaluated. RP-OPD + RL shows limited signs of reward hacking on RubricHub Science, whereas the SFT + RL baseline increasingly receives high rewards for claims of rubric compliance without providing the required content. These findings support using rubrics to guide on-policy
distillation before applying rubric-based RL.
Read the full abstract ▾
All authors Xinpeng Wang, Wei Shi, Yu-Chia Chen, Maria Zontak, Yun He, Richard Yuanzhe Pang
Machine Learning
Controlling Polar Exposure to Delay Memorization in Diffusion Models
Xuanchen Wang, Heng Wang and Weidong Cai
Diffusion models can reach useful sample quality before copying training examples, but fast optimization can compress this generalization window by accelerating sample-specific fitting. We investigate this effect through update geometry and propose Quality-Gated De-whitening (QGD), a controller that retains a fast polar-update prefix and progressively restores fixed-gain momentum. Our random-feature analysis separates covariance-controlled,
curvature-equalized and amplitude-controlled memorization clocks. Under aligned spectral assumptions, it establishes a finite-exposure condition under which a fixed-gain tail recovers a delay proportional to
dataset size. QGD implements this principle with a confirmed quality gate, a bounded decay envelope and causal copy feedback. Immediate switching is the conservative limit; gradual control balances delayed copying against continued quality improvement. We pair QGD with Copy-Budgeted Selection (CBS), which applies simultaneous binomial calibration to a frozen checkpoint family, followed by a fresh evaluation of the released checkpoint. On 2,000-image CIFAR-10 subsets, QGD preserves the polar baseline's quality-arrival time while expanding its useful interval by 8.32x and reducing common-checkpoint copying by 75.9%. With identical calibration and independent quality evaluation, QGD achieves FID 75.56 versus 79.37 for SGD with the same selector. Exposure-matched controls, independent detector audits and transfer to flow matching and dance generation support adaptive exposure control as a practical way to improve the quality-copying tradeoff.
Read the full abstract ▾
Computer Vision
TRAC: Trajectory-aware Reuse and Adaptive Correction for Efficient Autoregressive Video Generation
Jiaxing Song, Weiqi Yan, You Huang et al. (+4 more)
Autoregressive (AR)
video generation enables scalable long-
video synthesis by sequentially generating fixed-length chunks, but incurs substantial computational cost from repeated denoising and
attention over growing historical contexts. Recent cache reuse methods exploit temporal redundancy to reduce this cost, yet are mainly designed for single-trajectory generation, making them less suitable for sequentially coupled AR trajectories where approximation errors can accumulate and propagate across chunks. To address this challenge, we propose TRAC, a Trajectory-aware Reuse and Adaptive Correction framework for efficient and robust AR
video generation. TRAC integrates three complementary components: (1) Robust Cumulative Scheduling (RCS), which selects cache reuse schedules by accounting for cumulative rollout errors and their variation across chunks and
prompts; (2) Autoregressive Trajectory-aware Guidance Scheduling (ATGS), which coordinates classifier-free guidance refreshes along the global AR trajectory; and (3) Spectral Structure Correction (SSC), which adaptively restores low-frequency structural information to mitigate long-term error accumulation. By combining these innovations, TRAC substantially improves the efficiency-quality trade-off of AR
video generation. For example, on VBench with SkyReels-V2, it achieves a 6.03x speedup over the vanilla model with only ~0.6% VBench score degradation, while consistently outperforming existing AR acceleration methods in both latency and generation quality. The code is publicly available at https://github.com/yolosjxhhhhhh/trac.
Read the full abstract ▾
All authors Jiaxing Song, Weiqi Yan, You Huang, Mingte Qiu, Huazhong Liu, Xiaofeng Zhu, Yunshan Zhong
Networking
Performance Evaluation of Emerging Networks of Quantum Repeaters: Analysis and Simulation
Kobi Ravid, Javad Ghaderi and Gil Zussman
Emerging experimental
quantum network deployments are based on collaborations between research institutions and rely on telecommunications fiber infrastructure. Currently, such networks consist of mostly Dual Input Repeaters (DIRs) and can be viewed as composed of (mostly) line graphs. In order to evaluate the performance of such networks (e.g., in terms of Entangled Pair Rate, EPR, and average Fidelity) we developed a custom
quantum network simulation platform that takes into account both the
quantum and classical network components. To support the verification of the simulation results, we develop a novel approach for performance analysis of DIRs. We compare the simulation results to the analytical results for DIRs and to prior results for repeaters with more than two inputs. We observe that although the expected
memory utilization cannot be bounded, a small DIR
memory size is sufficient and leads to minimal performance degradation. For line networks with a single repeater and $3$ repeaters, we explore the dependency of incoming and outgoing
memory size requirements on the number of nodes (network size), their connectivity (fiber length) and various
quantum error settings (amplitude damping and phase flip channels). We evaluate the EPR and the average Fidelity for a sub-network of a deployed network with $3$ repeaters, using two alternative paths. We show that as the number of nodes increases or when the fiber lengths between nodes differ significantly, additional node
memory is needed to maintain the same EPR (
qubits are stored for longer duration to allow completion of
entanglement across the network). We also show that the
memory size should be above some minimum threshold to allow EP creation (EPR $>0$) as pair selection and swapping completion propagate across the network.
Read the full abstract ▾
Numerical Analysis
Property-Preserving Data Compression for Incompressible Flows
Andrey Pluzhnik, Ramansh Sharma, Martin Burtscher et al. (+1 more)
We develop a method for lossy compression of incompressible (i.e., divergence-free) velocity fields that preserves zero divergence and, on periodic domains, periodicity. We fit the nodal velocities with property-preserving
matrix-valued kernels and compress their coefficients using standard lossy compressors. Every decompressed coefficient vector defines a field with the same constraints, independently of the compression tolerance. We present several fitting schemes designed around either low-rank representation of or sparsity in the interpolation
matrix. More specifically, we show results for global Matérn interpolation, a two-level Nyström approximation, Nyström–Wendland residual interpolation, multilevel Wendland interpolation and a property-preserving (redundant) kernel frame. We derive nodal error bounds that relate the compressor tolerance to the additional velocity error. Experiments with four compressors on cavity, Taylor–Green, and species-transport flows verify the bounds under their coefficient-error assumptions and compare storage at matched velocity accuracy. The low-rank methods give compact representations when they resolve the velocity field sufficiently accurately; residual, multilevel, and frame interpolation extend the attainable accuracy when they do not. We also measure changes in turbulent velocity statistics. The resulting representations support an accuracy–compression tradeoff while preserving incompressibility and periodicity analytically.
Read the full abstract ▾
All authors Andrey Pluzhnik, Ramansh Sharma, Martin Burtscher, Varun Shankar
Computation and Language
Automatic Evaluation of Mental Health Stigma in Online Communication
Naomi Baes, Jemima Kang, Nick Haslam et al. (+4 more)
Mental health stigma has profoundly harmful impacts but its complexity makes it difficult to evaluate. Stigma may involve explicit derogation, but also subtler forms of blame, fear, paternalistic pity, social distancing, structural exclusion, and discrimination. We introduce a theory-grounded
benchmark for automatic evaluation of mental health stigma in online communication, consisting of naturally occurring online news and social media text annotated with a fine-grained taxonomy of stigma across multiple mental health conditions. Our annotation framework comprises a binary stigma-detection task and a multi-level taxonomy covering (i) stigma mode, (ii) domain, and (iii) specific components of certain forms of stigma. We apply this framework to texts mentioning six mental health conditions and evaluate large
language models alongside stigma-related classifiers for detecting sentiment, toxicity, and hate
speech. Results show that mental health stigma is not well captured by models trained to detect these neighboring constructs, and that LLMs often overpredict stigma unless given explicit operational rules - mirroring the importance of decision rules in human annotation. We release the publicly available part of
benchmark, annotations, prototypical exemplars of stigma and code at: https://github.com/jemimakang/mh_stigma.
Read the full abstract ▾
All authors Naomi Baes, Jemima Kang, Nick Haslam, Chris Groot, Alsa Wu, Luc Raszewski, Yulia Otmakhova
Machine Learning
LatticeSMC: Where to Spend Inference-Time Compute in Chunked Sequence Generators
Xuanchen Wang, Heng Wang and Weidong Cai
Long-form generators for music, motion and
video produce sequences chunk by chunk, with each chunk generated by iterative denoising while rewards are defined over the full sequence. Existing inference-time steering methods typically act on one axis at a time: best-of-N at the end, Feynman-Kac steering across denoising steps, or streaming
pruning across chunks, and are often compared under unmatched compute or different return rules. We introduce budget-matched chunked steering and propose LatticeSMC, a sampler derived from a Feynman-Kac model on the two-dimensional
lattice of chunk index and denoising step. Two telescoping results make its design exact: for chunk-additive rewards, the two axes induce identical weights, so resampling should occur where lookahead is cheapest; for terminal rewards, any prefix score defines an exact intermediate potential, making prefix-evaluable rewards twists with no estimation or extra denoiser calls. LatticeSMC resamples on these potentials at chunk boundaries and, when scoring is free, within chunks, returning either a weighted draw or the best particle. Under matched compute, on music-to-dance
diffusion and 40-second text-to-music generation, it raises beat
alignment from 0.234 to 0.441 (best-of-N: 0.354) and
prompt adherence from 0.470 to 0.560 at 32 particles, while preserving held-out quality. It also retains its advantage on long-range rewards and is preferred by human raters in 60-77 percent of pairwise comparisons. Finally, we show that commitment strength should follow the information in the current potential, while the value of lookahead is predicted by the within-set predictability of future reward.
Read the full abstract ▾
Computation and Language
Improving Atomic-Fact Recall via Focused Views in Unstructured Knowledge Editing
Ding Wu, Ye Zhang, Haoyu Wang et al. (+1 more)
Large
language models (LLMs) increasingly serve as general-purpose interfaces to factual knowledge, but their parameters do not automatically reflect information that changes after pretraining. Knowledge editing (KE) provides a targeted alternative to costly retraining by modifying selected knowledge and preserving unrelated knowledge and general capabilities. Conventional KE uses structured factual triples, whereas unstructured KE (UKE) uses free-form passages containing multiple facts. Nonetheless, existing UKE editors exhibit a failure mode known as context reliance: edited LLMs can often reproduce the editing passage but fail to reliably recall its individual facts without the original passage context. We identify context-induced difficulty underestimation under the standard passage-level editing objective: later facts receive increasingly rich ground-truth context and consequently incur lower initial losses, making them appear easier to learn. In response, we propose FOVEATED, a plug-and-play framework that constructs focused views of each sentence by randomly shifting the Rotary Position
Embedding (RoPE) positions assigned to the keys of its preceding context. The perturbation is applied during editing and removed afterward, leaving the model's native positional encoding unchanged at inference time. We instantiate FOVEATED for both direct-optimization and locate-then-edit editors. We theoretically analyze how FOVEATED counteracts context-induced difficulty underestimation and empirically demonstrate consistent improvements across five KE editors, two LLM backbones, and three
benchmarks.
Read the full abstract ▾
All authors Ding Wu, Ye Zhang, Haoyu Wang, Tianci Liu
Machine Learning
Nearly Optimal Fixed-Confidence Best-Arm Identification with 1-Bit Feedback
Khang Luong, Dinh Thai Son, Hoang Ta et al. (+2 more)
We study fixed-confidence best-arm identification under strict 1-bit feedback constraints. At each round, the learner selects an arm and a query set, and receives only a single bit indicating whether the sampled reward belongs to that set. We consider a distribution-free finite-variance setting with arm-wise localization, where direct empirical mean estimation is no longer available and clipping becomes unavoidable. We first formulate a time-uniform 1-bit mean-estimation primitive based on randomized threshold queries and a clipped tail-integral identity. We then embed this primitive into candidate-challenger best-arm identification
algorithms. A fixed-clipping
algorithm gives a simple anytime $(\epsilon,\delta)$-PAC guarantee, while a phased adaptive-clipping
algorithm matches the clipping level to the current resolution and yields a gap-adaptive sample complexity. We also prove a $K$-arm worst-case information-theoretic lower bound showing that the logarithmic penalty caused by finite-variance 1-bit feedback is intrinsic. This bound matches the leading dependence of the phased
algorithm up to lower-order $\log\log$ factors.
Read the full abstract ▾
All authors Khang Luong, Dinh Thai Son, Hoang Ta, Hung The Tran, Tuan Quang Dam
Computation and Language
AptMQL-Bench: From Text-to-SQL to Text-to-MQL via Access-Pattern Schema Design and Data-Preserving Migration
Hy Nguyen, Nabi Rezvani and Robin Vujanic
Document databases such as MongoDB are core infrastructure for modern applications, and natural-
language interfaces to them—text-to-MQL—would let non-experts query complex, semi-structured data without mastering the query
language. Progress on this task depends on high-quality
benchmarks, which are most practically obtained by converting an existing text-to-SQL
benchmark to the document setting. Unfortunately, existing efforts rely on heuristics for mechanical conversion: the document schema mirrors the relational foreign-key graph, and each query mirrors its source SQL. As a result in our experiments, these approaches fail to migrate 6 of 21 BIRD databases outright, silently drop up to 25.9% of rows on others, and yield schemas whose ground-truth queries run over an order of magnitude slower as the data scales. We instead propose a conversion pipeline, driven by coding
agents with human-in-the-loop verification, that designs each document schema from expected access patterns and rewrites queries to be MongoDB-native. Applying it to BIRD, we build an access-pattern-based text-to-MQL
benchmark (AptMQL-Bench). It includes 21 document-oriented databases, 3,186 natural-
language requests, and their associated MQL queries—whose databases are migrated from SQLite without data loss and scale efficiently. The strongest model, Claude Opus 4.5, achieves only 57.38% accuracy without external knowledge evidence and 70.34% with it. This indicates that realistic text-to-MQL generation remains challenging.
Read the full abstract ▾
Computation and Language
When History Fails to Become Experience: Action Calibration in Language Agents
Jingyu Liu, Zhiwen Wang, Yuxin Jing et al. (+2 more)
Language agents should draw on prior attempts and environmental feedback to improve subsequent decisions within the same task. However, providing additional interaction history can sometimes reduce task success, suggesting that
agents do not consistently use this information effectively. To investigate this limitation, we examine how
agents use history. We find that history improves task completion overall, yet much of this benefit persists even when past actions are shuffled. Disrupting the correspondence between actions and observations causes only a modest decline in task success. We therefore hypothesize that
agents do not reliably connect past actions with their outcomes when deciding how to proceed. To test this hypothesis, we explicitly label each returned observation as the outcome of the preceding action. This simple annotation improves task success and reduces next-action repetition without introducing new environmental information. Building on this insight, we introduce a learned calibrator that explicitly reassesses past actions and selectively records experience to guide subsequent decisions, improving task success beyond outcome labeling alone.
Read the full abstract ▾
All authors Jingyu Liu, Zhiwen Wang, Yuxin Jing, Huanyu Zhou, Yong Liu
Machine Learning
No-Free-Graph: Learning When Multimodal Data Should Be Graphified
Zekai Chen, Kai Hu, YuXin Zeng et al. (+6 more)
Multimodal graph learning has recently emerged as an effective paradigm for in corporating inter-entity relationships into
multimodal representations. Existing studies have made substantial progress on how to construct and optimize graphs, but rarely consider a more fundamental question: whether additional relational structures should be introduced for a given
dataset and task. Through empirical studies across diverse
datasets, tasks, and graph constructors, we reveal that graphification is not consistently beneficial: introducing relational structures can provide substantial improvements in some cases, while offering limited or even negative gains. This observation motivates a new perspective that graph construction should be treated as a selective decision based on its expected utility rather than a default preprocessing step. To address this issue, we propose MAG-SCOUT, a pre-construction graph assessment framework that estimates whether introducing graph structures is beneficial before generating the complete
topology. MAG-SCOUT collects limited relational evidence, analyzes its potential taskspecific contribution, and estimates the expected utility of graphification together with construction cost to make a build-or-skip decision. Extensive experiments across six
multimodal datasets, three downstream tasks, and diverse graph constructors demonstrate that MAG-SCOUT effectively identifies when graph structures should be introduced, saving 33.1% of task-macro graph work while retaining 96.7% of held-out positive-gain mass under the pre-registered floor.
Read the full abstract ▾
All authors Zekai Chen, Kai Hu, YuXin Zeng, Xunkai Li, Xun Wu, Yinlin Zhu, Zhengyu Wu, Xu Wang, Rong-Hua Li