Reinforcement_Learning
-
Learning Timeline-Preserving Speech-to-Speech Translation
2026-10-31 06:39:04Zhisheng Zheng, David HarwathAbstract
Speech-to-speech translation (S2ST) increasingly preserves what is said and how it sounds, but not necessarily when speech and silence occur. For dubbing and other temporally grounded applications, matching total duration is not enough: speech and pauses must also occur at corresponding moments. We formulate timeline-preserving S2ST, which aims to preserve the source endpoint and salient internal pauses on a shared absolute timeline. We present TransDubber, an end-to-end autoregressive system that learns this temporal structure directly from aligned target waveforms, without inference-time frame-level timing control or post-hoc temporal correction. To provide this supervision, we construct 642K exactly duration-matched English-Chinese speech pairs by translating and synthesizing target speech on source-defined temporal scaffolds. Training combines a progressive supervised curriculum with verifier-guided reinforcement learning to balance translation quality and temporal alignment. On a 4,353-utterance test set spanning read and spontaneous speech, TransDubber increases the proportion of translations within 2% of the source duration from 25.6% to 61.5% and pause-alignment F1 from 0.118 to 0.550 compared with UniSS, while maintaining competitive translation quality. Our analysis shows that aligned supervision establishes timeline following, while reinforcement learning refines temporal precision and partially offsets the translation-quality cost of strict synchronization. Together, these results demonstrate the effectiveness of our data and training framework for timeline-preserving S2ST. Audio samples, code, datasets, and pretrained models are available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2611.00690
PDF
-
Enhancing Language Model Reasoning with Structured Multi-Level Modeling
2026-10-31 04:33:35Siheng Xiong, Ali Payani, Faramarz FekriAbstract
Inference-time scaling enhances a model's reasoning by extending its chain-of-thought (CoT). However, existing approaches typically rely on a single policy trained with outcome-reward reinforcement learning (RL), which often suffers from long-horizon plan failures where the implicit plan drifts from valid strategies, especially for small LMs with limited capacity. To address this, we propose Multi-Level Reasoning (MLR), which reformulates long-CoT generation as a two-level stochastic process. A high-level planner generates structured step descriptors specifying both the reasoning mode and the semantic subgoal. The low-level executor then produces detailed reasoning conditioned on these descriptors, forming an alternating plan--execute loop. To maintain scalability, we adopt a minimal design where the base model serves as the low-level policy and a lightweight LoRA module implements the high-level policy. For training, we observe that outcome-reward RL provides sparse and delayed feedback for long trajectories (e.g., several thousand tokens), hindering credit assignment. We therefore introduce iterative Step-DPO, a process-level preference optimization scheme that leverages Twisted Sequential Monte Carlo (TSMC) to provide scalable stepwise supervision. This yields more effective training, improved stability, and higher accuracy. Extensive experiments on challenging math, science, and logical reasoning benchmarks show that, under the same reduced data budget (10% SFT and 5% preference relative to the DeepSeek-R1 distillation setup), MLR outperforms both SFT-based distillation and strong RL/preference-optimization baselines across multiple base models and tasks. Moreover, MLR exhibits slower performance degradation on long-horizon reasoning, demonstrating stronger robustness under extended CoT generation.
Abstract (translated)
URL
https://arxiv.org/abs/2611.00616
PDF
-
MEMENTO: Learning Context Management for Long Context Processing Agents
2026-10-30 18:25:08Yunfan Zhang, Taehoon Hwang, Kathleen McKeown, Smaranda MuresanAbstract
LLM agents that operate over long inputs must perform context management: deciding what to retain in a fixed-size context window. A common approach is compaction, where the model replaces its history with a self-generated note. Yet off-the-shelf agentic models, including GPT-5.5 and GLM-5.3, often write ineffective notes, and reinforcement learning (RL) alone rarely discovers useful note-taking behavior. We present MEMENTO, a long-context agent built on Qwen3-8B and trained to manage its context through compaction. We first bootstrap note-taking by fine-tuning on synthetic trajectories annotated with notes generated in hindsight, then reinforce it with RL using a reward that combines answer correctness, note-quality heuristics, and confidence calibration. Although trained only to compact into a fresh window, MEMENTO extends at test time to strategies such as context folding and confidence-based backtracking. On book-level question answering across four benchmarks, with books of up to 2.5M tokens, MEMENTO raises Qwen3-8B's accuracy from 36.9% to 67.8% while never holding more than 20K tokens in context. It outperforms GPT-5.5 agent in the same harness (13.1%) and full book context (56.7%) at less than 1/50 the cost. It also nearly matches a ~100x larger GLM-5.3 agent (69.3%) at 1/9 the cost, and comes within 6.4 points of GLM-5.3 full context at 1/26 the cost.
Abstract (translated)
URL
https://arxiv.org/abs/2611.00244
PDF
-
Latent Reasoning in Continuous Space for Unified Multimodal Models
2026-10-30 17:59:43Byungwoo Jeon, Yoonwoo Jeong, Hyunseok Lee, Minsu Cho, Jinwoo ShinAbstract
Unified Multimodal Models (UMMs) achieve remarkable success on diverse multimodal understanding and generation tasks, yet they still struggle to effectively leverage language-based chain-of-thought reasoning for image generation. As a result, existing reasoning-augmented UMMs often fail to inherit the test-time scaling and fine-grained controllability observed in large language models. We attribute this failure to a fundamental modality mismatch: reasoning is performed in a discrete token space, whereas image generation operates in a continuous space. To bridge this gap, we introduce a Latent Reasoning framework in Continuous space (LARC), which alleviates the token-level bottleneck by reasoning over continuous hidden states. Specifically, the training framework consists of two stages: (i) curriculum supervised fine-tuning (SFT), and (ii) information-gain reinforcement learning (RL). First, the curriculum SFT stage gradually converts token-level reasoning into latent reasoning. Subsequently, the information-gain RL stage self-evolves latent reasoning without ground truth supervision. Experiments across diverse text-to-image generation benchmarks show that LARC consistently improves generation quality, prompt following, and compositional fidelity. Notably, LARC achieves state-of-the-art performance on GenEval with a 7%p gain over BAGEL and demonstrates clear test-time scaling behavior, outperforming token-based generation under both parallel and sequential test-time scaling strategies.
Abstract (translated)
URL
https://arxiv.org/abs/2610.42149
PDF
-
ROOF: Learning Humanoid Fall Recovery under Overhead Constraints
2026-10-30 17:41:32Yidan Lu, Jiayuan Yu, Zongrui Cai, Jingwen Sun, Jinrui Han, Jing Wang, Ping Luo, Peng LuAbstract
A fallen humanoid beneath an overhead obstacle faces a coupled recovery problem. It must create clearance while organizing support for a stable rise, since attempting to stand before making room can further increase obstruction. We introduce a reinforcement learning method with contact-supported geometric escape guidance, which rewards incremental reduction of robot-obstacle overlap without prescribing an escape path. To achieve this, a learned motion prior, together with posture-dependent support and joint-stall costs, is proposed to shape a single policy that learns when to clear the obstacle, how to establish support, and when to complete the rise, all using proprioception alone. In simulation, it recovers in 88.5% of trials beneath plates that can only be lifted, compared with 18.9% without geometric guidance, and in 98.6% of trials beneath free plates with randomized size, mass and placement. On a Unitree G1, the deployed policy recovered in 95 of 150 attempts across seven real-world obstacle scenes, including furniture and multi-object arrangements absent from training. Project page: this https URL
Abstract (translated)
URL
https://arxiv.org/abs/2610.42097
PDF
-
CRoS: Causality Reward on Scrambled CoTs Improves Accuracy and Reasoning Faithfulness
2026-10-30 17:18:35Xiao Yu, Justin Chih-Yao Chen, Zaid Khan, Hyunji Lee, Mohit BansalAbstract
Reinforcement learning with verifiable rewards (RLVR) has become the standard method for training language models to reason. However, RLVR typically relies solely on outcome correctness, which does not guarantee that the CoT causally contributes to the final answer. Without this connection, outcome rewards may fail to reinforce high-quality reasoning. Existing causality metrics assess CoT causality by perturbing the CoT, such as deleting reasoning steps or injecting errors, and measuring changes in the final answer. However, these perturbations inevitably alter information in each step. Consequently, high causality scores may reflect sensitivity to information changes introduced by perturbation rather than true causality. Such confounding effects further induce undesirable reasoning behaviors when these metrics are used as training rewards, including generating less informative CoTs and reducing exploration and self-correction. To address this problem, we propose CRoS (Causality Reward on Scrambled CoTs), a novel CoT causality metric that perturbs the order of reasoning steps without altering content, thereby preserving information within each step. On Reasoning Gym with Gemma-3-4B, CRoS outperforms existing causality and outcome rewards in out-of-domain accuracy, CoT quality, and CoT faithfulness. Specifically, CRoS achieves 46.8% accuracy on five unseen logic and games datasets, outperforming the strongest baseline (43.8%). It also achieves better CoT quality, consistently outperforming baselines in CoT-Pass@K from K=1 to 128, averaging 43.4% vs. 41.4%. For CoT faithfulness, CRoS achieves a hint acknowledgment score of 34.0% vs. 20.2%.
Abstract (translated)
URL
https://arxiv.org/abs/2610.42054
PDF
-
Optimizing Stochastic Policy Geometry for Few-Step Flow Reinforcement Learning
2026-10-30 16:05:17Zhuguanyu Wu, Congjia Chen, Ruihao Gong, Yang Yong, Shiqiao Gu, Yi Xu, Xianglong LiuAbstract
Few-step flow models generate samples through a handful of large denoising transitions. Applying GRPO to such models requires introducing stochasticity into the denoising transitions, and when a single transition spans a wide range of noise levels, the choice of the resulting stochastic policy becomes a major factor in optimization. Recent constructions constrain the policy to preserve the target flow coefficients, but this constraint admits a family of policies and offers no criterion for choosing among them. We introduce Geo-FSRL (Geometry-Optimized Few-Step Reinforcement Learning), built on a selection principle: at a fixed conditioning state and timestep pair, choose the admissible policy that minimizes the conditional KL divergence induced by any given nonzero velocity-output update. Within a coefficient-preserving family of isotropic Gaussian transitions, this criterion reduces to minimizing a single scalar geometry factor that determines the conditional KL for every velocity-output update. The same factor governs velocity-space Fisher information and conditional transition log-likelihood-ratio variance. We derive the unique closed-form optimizer within this family, shared across all nonzero update magnitudes and directions, with transition coefficients determined by both the source and target noise levels. Because the minimized geometry factor still varies across timesteps, we further adopt gradient-scale matching from prior work and derive closed-form policy-gradient and KL weights that normalize explicit score scales and reference-KL curvature. Geo-FSRL trains on the original few-step schedule and retains the deterministic solver at inference. Our method achieves higher final reward scores than Flow-GRPO and Flow-CPS on both image generation and video generation models under the 4-step setting. Code is available at this https URL
Abstract (translated)
URL
https://arxiv.org/abs/2610.41949
PDF
-
Online Learning of Heterogeneous Locomotion Dynamics under Reinforcement Learning Policies for Precise Loco-Manipulation
2026-10-30 15:34:35Tianlin Zhang, Weipeng Xia, Lingwei Zhang, Yiyang Shao, Zhongyu Li, Yun-Hui LiuAbstract
How to reuse a pretrained locomotion policy for precise loco-manipulation is still an open problem. We propose an online method to learn the closed-loop dynamics under a frozen locomotion policy. The learned model predicts floating-base motion and improves loco-manipulation accuracy. However, unobserved latent conditions of the policy introduce heterogeneous responses, meaning that the same observed state will lead to different motions. Direct learning without accounting for this heterogeneity introduces bias and fluctuations into dynamics estimates, degrading floating-base prediction and end-effector tracking. To address this problem, a contaminated Gaussian model is proposed to approximate the effects of latent conditions. The model uses two Gaussian components to approximate predictable and unpredictable responses under the same observed state. Then, the contaminated Gaussian model is combined with a Gaussian process to construct an online learner using random Fourier features (RFFs). The learner estimates each response's probability of belonging to the predictable component and uses it to weight online updates, capturing predictable responses while reducing bias and fluctuations caused by heterogeneous observations. With consistent and unbiased dynamics estimates, model predictive control (MPC) predicts floating-base motion accurately and enables precise loco-manipulation. A finite-sample error bound is established to ensure uniform convergence in online learning. Simulation and hardware experiments demonstrate consistent end-effector tracking across different manipulator configurations and tasks, with errors of 0.01 m.
Abstract (translated)
URL
https://arxiv.org/abs/2610.41892
PDF
-
Multimodal In-Context Learning with Explicit Rule Induction
2026-10-30 13:57:30Yuquan Li, Xinyang Jiang, Yuhao Xue, Cairong ZhaoAbstract
A central challenge in multimodal in-context learning (MICL) arises from tasks that are ill-defined without context and require uncovering the underlying rules from demonstrations. Existing methods predominantly treat MICL as direct input-output mapping, overlooking the importance of explicitly inducing and reasoning over such rules, limiting both performance and interpretability. We propose ERIM, Explicit Rule-Induction for Multimodal In-Context Learning, a unified framework that enhances MICL by explicitly inducing the latent rules governing demonstration samples. Leveraging the reasoning ability of multi-modal large language model (MLLM), ERIM constructs rule-centric MICL datasets, introduces explicit supervision for rule induction, and fine-tunes MLLM to perform explicit rule-induction via a two-stage training strategy that combines mixed cold-start supervised fine-tuning with reinforcement learning. Extensive experiments show consistent performance improvements across diverse MICL settings and demonstrate that correctly inducing underlying rules directly leads to stronger and more stable performance.
Abstract (translated)
URL
https://arxiv.org/abs/2610.41754
PDF
-
ResMerge: Residual Policy Learning and Merging for Continual Adaptation of Pre-trained Robot Policies
2026-10-30 12:33:47Kefei Zhu, Lingyun Xu, Yue Xin, Xiaoqi Li, Caixin Guo, Xincheng Du, Yuanpei Chen, Yaodong Yang, Hao DongAbstract
Continual adaptation to new tasks is essential for robots deployed in the real world, but adapting pre-trained policies remains challenging due to parameter growth and the need for continual demonstration collection. Parameter-Efficient Continual Fine-Tuning (PECFT) isolates task-specific updates, but adapter-per-task designs require demonstrations and grow with the task set. We propose ResMerge, a two-stage framework that learns mergeable residual policies atop a frozen pre-trained policy: residual reinforcement learning (RL) acquires task-specific corrections without additional expert demonstrations during adaptation, and parameter-space merging consolidates compatible residuals to reduce stored parameters. We introduce Residual-Field Consistency (RFC), a simple, bounded, and interpretable metric that assesses compatibility in residual action-field space by comparing correction direction and magnitude. Experiments on LIBERO across two backbones and on a real-world Franka robot show improved continual learning performance over strong PECFT baselines, while selective merging reduces the residual-parameter footprint. Project website: this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.41663
PDF
-
Risk-Sensitive Mission Planning for Multi-Target On-Orbit Inspection via Distributional Reinforcement Learning
Abstract
Multi-target on-orbit servicing missions require planning tools that can adapt to evolving operational conditions while accounting for the outcome variability inherent to safety-critical spaceflight. This paper presents an adaptive planning approach for multi-target servicing campaigns in low Earth orbit and applies it to inspection missions flown by a low-thrust servicer. The approach is based on Distributional Reinforcement Learning, which learns the full distribution of mission returns and thereby supports explicit risk-sensitive decision-making at each planning step. Specifically, a Quantile-Regression Deep Q-Network (QR-DQN) agent selects which target to inspect next by jointly considering the expectation and the variance of the predicted return through a mean-variance criterion. The mission environment models circular orbits with a spread in inclination and uses Edelbaum's combined-manoeuvre low-thrust transfer estimates. The observation comprises the orbital elements, the visit history, the observed risk state of each target and the remaining mission-time budget. The risk state of each target changes stochastically during the campaign, making the outcome of an inspection uncertain and creating operationally meaningful distinctions between risk-neutral and risk-averse planning strategies. Because the mission-time budget generally admits only a subset of the candidate targets, the planner must also select which targets to inspect. Numerical experiments on scenarios with five target satellites show that one risk-aversion weight moves the policy across a range of mean return and return variance, over an unchanged environment and reward. Risk-averse agents reduce the variance of the episodic return by approximately one half relative to risk-neutral agents and lower the probability of a mission loss, at a cost in mean return. To validate the learned policies, the efficient frontier, which gives the highest mean return attainable at each level of return variance, is computed exactly by enumerating the admissible visit orders. At equal variance, the learned policies lie close to this frontier in mean return, and the risk-averse policies have a lower probability of a mission loss than the frontier policies.
Abstract (translated)
URL
https://arxiv.org/abs/2610.41647
PDF
-
Chance-Constrained Inspection Viewpoint Sequencing for On-Orbit Servicing via Safe Reinforcement Learning
2026-10-30 12:15:31Chlo\'e Carer (LGI), Adam Abdin (LGI)Abstract
Autonomous inspection of a target spacecraft is typically the initial step in on-orbit servicing. Planning close-proximity observation viewpoints involves a complex combinatorial problem constrained by coverage, fuel, and safety considerations. This paper models the viewpoint selection as a Constrained Markov Decision Process (CMDP) and applies Proximal Policy Optimization with Lagrangian relaxation to solve it. The system combines a high-level planner, which sequences camera viewpoints on an observation sphere around the target, with a low-level model that assesses each transfer using the Clohessy--Wiltshire (CW) equations for relative motion. The deterministic constraints on single-impulse reachability and $\Delta v$ cap are enforced directly on the action set. Safety margins are affected by navigation and manoeuvre errors, making the actual clearance stochastic. To address this, a chance constraint on the realised trajectory is implemented, with a Lagrangian multiplier governed by PID control to adapt the penalty during training. The approach is tested on a Galileo-class navigation satellite in medium Earth orbit, modelled as a point cloud where visibility from each viewpoint considers field-of-view and line-of-sight occlusion. Across various risk budgets, the trained policy maintains the keep-out violation rate within the specified limit, achieving coverage close to its maximum and staying within the mission $\Delta v$ budget. Compared to the usual practice of applying a fixed margin to the keep-out radius and planning deterministically, the chance-constrained policy attains less than half the violation rate at comparable coverage. This makes the collision risk an explicit design parameter, eliminating the need for re-tuning per case. The learned policy selects a viewpoint without the repeated Monte Carlo risk estimates required by a greedy, chance-constrained planner at every decision point.
Abstract (translated)
URL
https://arxiv.org/abs/2610.41639
PDF
-
GRIT: Gradient Masking for Visually Misgrounded Tokens in Text-Rich Reasoning
2026-10-30 12:05:54Chanseul Cho, Noori Bae, Dongheon Lee, Youngmin RoAbstract
Reinforcement learning with verifiable rewards (RLVR) has recently been extended to vision-language models (VLMs), yet its effectiveness remains limited for text-rich reasoning tasks. We highlight a key factor contributing to this limitation: models frequently arrive at correct final answers despite misperceiving visual information during intermediate steps. We define this phenomenon as Correct-but-Visually-Misgrounded Reasoning (CVMR). Because standard RLVR rewards only final-answer correctness, it fails to differentiate between properly grounded and misgrounded reasoning, reinforcing both equally. Through token-level analysis, we reveal that CVMR tokens exhibit distinct attention patterns that differ systematically from well-grounded ones. Based on this observation, we propose GRIT, a training framework that incorporates visual grounding into RLVR to mitigate the impact of CVMR. Furthermore, to address the lack of text-rich reasoning benchmarks that allow for systematic evaluation across text length and reasoning depth, we introduce GRIT-Bench. Experiments demonstrate that GRIT significantly improves both reasoning accuracy and grounding fidelity over existing RLVR methods.
Abstract (translated)
URL
https://arxiv.org/abs/2610.41629
PDF
-
ReBRAC-v2: The Return of the King
2026-10-30 11:58:18Denis Tarasov, Robert K. KatzschmannAbstract
Recent offline reinforcement learning methods increasingly rely on expressive generative policies and specialized value guidance. We ask how far systematic modernization of a conventional behavior-regularized actor-critic can go while preserving algorithmic simplicity. ReBRAC-v2 directly trains an exact-likelihood normalizing-flow actor with likelihood, MSE, and MAE behavior regularization, classification-based residual critics, staged optimization, and multi-sample inference. We develop one shared configuration through roughly 600 Bayesian proposals on six OGBench tasks, then adapt only two behavior-regularization coefficients using a 16-point grid for the main comparisons. Across ten common OGBench categories, ReBRAC-v2 averages 74.8 versus 52.3 for the next-best method and ranks first in eight categories. Without structural changes, it also obtains the strongest compared averages on D4RL AntMaze (90.2) and Adroit (33.6). Motivated by these results, we extend evaluation to all 235 state-based single-task problems across the 47 dataset variants in the original OGBench suite. To our knowledge, this is the first complete evaluation in this setting; no compared baseline reports results across the full suite. Per-task scores and configurations establish ReBRAC-v2 as a reference baseline for future work beyond the common task subset. The complete cloning objective retains the highest average after coefficient retuning of its alternatives, while further ablations characterize training, capacity, and inference choices. These results demonstrate the strength of systematic engineering within a minimalist offline RL foundation.
Abstract (translated)
URL
https://arxiv.org/abs/2608.01205
PDF
-
What Should LLMs Forget: Reinforcement Unlearning of Knowledge Associations
2026-10-30 11:55:35Wutong Xu, Yun Qu, Haiyan Feng, Qi Wang, Xiangyang JiAbstract
Large language models (LLMs) acquire extensive factual knowledge during pre-training, which may include sensitive, private, or copyrighted information, motivating the development of unlearning methods that selectively remove specific knowledge while preserving general capabilities. However, existing approaches typically optimize entire responses without explicitly identifying the knowledge to be forgotten, resulting in coarse and uncontrolled forgetting. To address this, we revisit the forgetting target of LLM unlearning and introduce Knowledge Association (KA), which characterizes the association between a query context and its target knowledge and is instantiated by the corresponding conditional predictive distribution, as the fundamental target of forgetting. Based on KA, we propose Knowledge Association Reinforcement Unlearning (KARU), a unified reinforcement learning framework that suppresses forgotten knowledge associations while preserving retained ones. Specifically, KARU derives complementary mechanisms from the KA-based formulation: token-level reward construction for finer-grained forgetting supervision, distribution-level regularization for precise knowledge suppression, and proximity-aware retain sampling to mitigate collateral degradation. Experiments across diverse LLMs on representative benchmarks demonstrate that KARU consistently improves forgetting effectiveness over existing baselines while maintaining comparable retention performance and general utility.
Abstract (translated)
URL
https://arxiv.org/abs/2610.41616
PDF
-
KEEPER: Learning Control-Sufficient Textual Memory for Long-Horizon LLM Agents
2026-10-30 09:36:06Jinkyeong Choi, Chaebin Jeong, Junsung Jeon, Donghyeon ParkAbstract
Recursive textual memory can carry earlier errors into later updates, yet task performance alone does not establish memory reliability. We define self-consistency bias as the persistence of incorrect claims already present in the incoming memory. We present KEEPER, a comparative analysis of four auxiliary objectives along information-content and update-sensitivity axes within a shared recursive interface, examining how supervision targets relate to agent performance. Among evaluated conditions, reward-related prediction achieve the highest task performance before and after offline reinforcement learning, outperforming joint supervision. A claim-level analysis of one baseline trajectory documents error persistence despite corrective observations. Together, these analyses motivate evaluating error persistence and valid-information retention alongside task outcomes.
Abstract (translated)
URL
https://arxiv.org/abs/2610.41482
PDF
-
From Representation to Readout: Mechanistic Analysis of Membership Signals in Language Models
2026-10-30 08:47:07Wenxi Dai, Jingyu Hu, Yanting Yang, Mengnan DuAbstract
Membership inference aims to determine whether a particular example was included in a model's training data. Such membership signals are often broadly described as memorization, while the underlying mechanisms can involve both how information is represented internally and how it is accessed by the model to produce behaviors. We therefore present a mechanistic study of membership signals in large language models (LLMs). We introduce Decodable Information Score, Used Information Score, and Readout Accessibility Gap (DUG), a set of complementary measures that separately quantify membership information decodable from internal representations and the extent to which it is exposed through the model's readout. Across supervised fine-tuning (SFT) and reinforcement learning (RL)-based membership inference methods, membership-specific effects appear in both the amount of decodable information and readout under SFT, while under RL-based membership inference methods they appear primarily in readout. Activation patching further localizes this membership-specific effect to intermediate layers. To examine whether these findings extend to a more general RL setting, we further study reinforcement learning with verifiable rewards (RLVR) contamination, where the training reward is independent of the reference solution. In this setting, we find that behavioral changes can emerge without a corresponding increase in likelihood-based membership inference signals.
Abstract (translated)
URL
https://arxiv.org/abs/2610.41445
PDF
-
Pinching Antennas for ISAC: Waveguide Architectures, Solutions, and Future Directions
2026-10-30 07:45:16Qian Gao, Ruikang ZhongAbstract
Integrated sensing and communication (ISAC) is a core design principle for sixth-generation (6G) wireless systems, yet fixed antenna geometry limits its performance. Pinching antenna systems (PASS) guide electromagnetic waves along dielectric waveguides and radiate them through position-adaptive antennas, allowing communication links and sensing observations to benefit from spatial reconfiguration. This article reviews PASS-enabled ISAC through single-waveguide, multi-waveguide, and segmented-waveguide architectures, comparing their feed structures, spatial degrees of freedom, operating protocols, and uplink/downlink support. We organize solution pathways around physics-consistent modeling, joint spatial-signal optimization, dynamic channel acquisition, and stable real-time control. A segmented waveguide-enabled pinching-antenna array (SWAN) case study demonstrates joint segment selection, antenna po?sitioning, and transmit beamforming using segment-hysteresis reinforcement learning. The results illustrate how waveguide loss and per-segment aperture gain create communication-sensing tradeoffs. We conclude with research directions in joint transmit?receive operation, measurement-calibrated digital twins, and trustworthy control.
Abstract (translated)
URL
https://arxiv.org/abs/2610.41380
PDF
-
Joint-Health-Aware Reinforcement Learning for Robust Robot Control Under Actuator Degradation
2026-10-30 07:05:58Haifa Zhang, Yijing Wang, Zhiqiang ZuoAbstract
Robots deployed in unstructured environments are susceptible to actuator-authority degradation, which reduces the effective control authority of individual actuators and can cause reinforcement learning policies trained under nominal dynamics to fail. Existing robustness approaches rely on discrete fault labels, broad domain randomization, or global latent variables, often without explicitly modeling continuous per-joint residual actuation capability. We propose a joint-health-aware reinforcement learning framework for robust robot control under simulated actuator degradation. Our framework encodes actuator condition in a continuous joint-health vector and models degradation as multiplicative attenuation of executed actions. A dedicated HealthNet estimator infers per-joint health from recent observations and actions, allowing the policy to redistribute control effort across healthy and degraded joints. We evaluate the method on Walker, Go2, Cassie, and Panda-based ManiSkill manipulation tasks under diverse degradation masks and severity levels. The method outperforms nominal and degradation-trained no-health baselines on the main evaluated metrics. Relative to the nominal baseline, task-level locomotion returns improve by up to 250.1\% and manipulation success rates by up to 15.2 percentage points; in the high-degradation Cassie group, return increases from 3.94 to 40.50 (+928.0\%). Ablations support the contribution of per-joint health estimation, action-degradation modeling, and health-conditioned control.
Abstract (translated)
URL
https://arxiv.org/abs/2610.41348
PDF
-
HandMimicX: Learning Human-Like Dexterous Manipulation via an Object-Centric Policy from Egocentric Videos
2026-10-30 06:51:27Zihan Gao, Yufei Liu, Yuhong Zhang, Zhen Yu, Xinhao Huang, Zhinan You, Kai W. Ho, Zipeng Ye, Peng Jiao, Haoqian WangAbstract
Learning dexterous manipulation from human videos remains an open challenge, particularly in the context of transferring a single demonstration into a spatially generalizable robotic skill and maintaining physically plausible human-like interactions. Unlike prior works that emphasize hand-motion imitation, we introduce an object-centric framework for acquiring dexterous skills from egocentric human RGB-D videos. Within our framework, we formulate the reinforcement learning (RL) objective in terms of object motion to decouple the underlying skill from the specific hand trajectory and impose constraints on hand-object interaction states to promote more anatomically natural hand configurations. Extensive experiments in simulation and on real robots demonstrate that our method enables efficient learning from human videos and generalizable skill transfer across novel spatial configurations.
Abstract (translated)
URL
https://arxiv.org/abs/2610.41336
PDF
