TACROSS is a low‑cost, scalable system that enables robots to learn from human touch by aligning tactile streams at the level of contact events rather than raw sensor values. It combines a $10.86 piezoresistive glove with 285 sensing points and a temporal Transformer that maps heterogeneous signals into a shared 256‑dimensional latent space. The approach uses robot demonstrations for action supervision while human demonstrations aid tactile representation learning, achieving a 3.5‑fold efficiency improvement and a 95.7% reduction in demonstration equipment cost across four manipulation tasks.
By Bo Chen, Huanzhang Hu, Junyang Ma, Bo Yue, Fangdi Yu, Haijier Chen, Xianxin Lai, Shuyu Pan, Zhen Yang, Xiaoquan Sun, Wenze Cui, Zhongliang Jiang, Shaopeng Liu, Jiayu Chen
The paper introduces Differentiable Systematic Resampling (DSR), a temperature-controlled relaxation of systematic resampling that maintains the CDF-ordered, banded structure while allowing full gradient flow. DSR converges to exact systematic resampling as temperature approaches zero and the authors prove a pointwise exponential convergence rate for the induced bias. Compared to optimal-transport-based differentiable resampling, DSR avoids iterative solvers and has substantially lower computational overhead, achieving comparable or superior filtering and dynamics learning performance on stochastic dynamical systems and real-world handwriting data.
By Fredrik Cumlin, Saikat Chatterjee
Generative Adversarial Loops (GAL) is a framework that alternates between a discriminator generating adversarial data to expose weaknesses in current AI systems and a generator discovering algorithms to overcome those weaknesses. Applied to tasks such as KV compression, sparse video generation, sparse attention, and context extension, GAL’s discriminator identifies shortcomings in state‑of‑the‑art techniques, while the generator produces new algorithms that improve performance on both adversarial and established benchmarks. The study demonstrates significant gains, for example boosting CompactorPress on KV compression from 0.35 to 0.97 on the discriminator dataset and improving Dual Chunk Attention from 0.20 to 0.90.
By Kislay Aditya Oj, Nidhi Jain, Sri Surya Varma Datla, Priyanka Jayaswal, Kumar Krishna Agrawal, Aditya Desai
ProtoSemImage proposes representing class prototypes as image-valued archetypes rather than vectors, using a four‑channel HSV space that encodes linguistic factors. The model learns a deformable row alignment between a document image and its archetype bank, enabling spatial template matching that highlights where and how an input diverges from its prototype. Experiments show that this image representation outperforms vector prototypes on a ten‑class task, while diagnostic tests reveal that the matching component, not the color compression, limits performance.
By Mohammad Zare, Pirooz Shamsinejadbabaki
The paper audits the reliability of large language models used as judges in NLP evaluation. It stresses that verdicts can vary across identical replications, change with presentation order, and that even the most deterministic model only agrees with ground truth 51% of the time. The authors introduce the trustworthy verdict rate (T) to quantify reproducibility, order‑invariance, and accuracy, and show that holistic rubric scoring improves trustworthiness more than any single prompting strategy.
By Vineet Kumar, Darshita Rathore, Anindya Moitra
LeWAM is a bidirectional transformer that predicts forward, backward, inverse dynamics and policy, trained end‑to‑end on a decoder‑free JEPA latent. It outperforms a forward‑only JEPA world model by better aligning latent representations with robot and object states while ignoring visual distractors. In closed‑loop tests, LeWAM matches a flow‑matching policy of the same size and improves MPC planning by sampling actions in the policy head’s noise space rather than raw actions.
By Shashank Hegde, Alexander Popov, Elie Aljalbout, Nikolai Smolyanskiy
The paper introduces an observational estimator to quantify how much peer‑review decisions would change if a paper were reviewed by a different set of reviewers, using public review data from ICLR 2017‑2025. The estimator decomposes scores into paper quality and reviewer noise via a Bayesian ordered‑probit model, maps scores to decisions with a logistic model, and simulates independent committees to estimate disagreement rates, finding 23‑30% disagreement at committee size two and 18‑24% at size four. Calibration against NeurIPS 2021 data shows close agreement, and longitudinal analysis reveals no robust trend in reviewer noise over the period, though specific years (2020, 2021) exhibit higher flip rates due to scale compression and low signal‑to‑noise.
whyItMatters":"The study provides a scalable, data‑driven method to assess the reliability of conference accept/reject decisions, offering insights into reviewer noise and potential improvements in review processes."
By Feilian Huang
The paper addresses policy optimization in online episodic tabular MDPs with adversarial losses and bandit feedback. By employing regularized Q‑functions, the authors eliminate the extra horizon factor present in previous policy‑optimization regret bounds, achieving high‑probability regret of ≥O(√{HS(H+A)T}) for known transitions and ≥O(HS√{AT}) for unknown transitions. These results improve horizon dependence and match the best-known bounds, with extensions to adversarial linear‑mixture MDPs.
By Mingyi Li, Taira Tsuchiya
The paper introduces PSCMIA, a power side‑channel membership inference attack that can determine whether a data sample was used to train an embedded machine learning model by analyzing power traces, without needing prediction probabilities or labels. The authors evaluate PSCMIA on MNIST, FMNIST, CIFAR10, and CINIC10 datasets using fully connected and convolutional neural networks on STM32F3 and XMEGA platforms, achieving ROC‑AUC values up to 0.907 for fully connected models and close performance to probability‑vector attacks for CNNs. PSCMIA outperforms label‑only attacks in 11 of 16 configurations, showing that physical execution can leak membership information even when conventional outputs are suppressed.
By Sahan Sanjaya, Prabhat Mishra
AliO: Output Alignment Matters in Long-Term Time Series Forecasting proposes a new method, AliO, to improve output alignment in LTSF models by reducing discrepancies in prediction outputs for the same timestamps across both time and frequency domains. The authors introduce a Time Alignment Metric (TAM) to quantify alignment, contrasting with traditional MSE metrics that only measure distance to ground truth. Experiments demonstrate that AliO can increase TAM by up to 58.2% while maintaining or improving forecasting performance by up to 27.5%.
By Kwangryeol Park, Jaeho Kim, Seulki Lee
arXiv:2610. 11584v1 Announce Type: cross Abstract: To test conditional independence of $X$ and $Y$ given a text or an image $Z$, one conditions on an embedding $\psi(Z)$ in place of $Z$.
By Nikolaj Thams, Anton Rask Lundborg
The paper introduces TriTrust-PBRL (TTP), a framework for preference-based reinforcement learning that learns a shared reward model and expert-specific trust parameters from multi-expert feedback. Trust parameters evolve to be positive (trust), near zero (ignore), or negative (flip), allowing the model to invert adversarial preferences instead of discarding them. Experiments on manipulation and locomotion tasks show TTP achieves near-oracle performance under adversarial corruption, outperforming existing PBRL methods.
By Seyed Amir Hosseini, Maryam Abdolali, Amirhosein Tavakkoli, Fardin Ayar, Ehsan Javanmardi, Manabu Tsukada, Mahdi Javanmardi
PSI‑SINDy introduces a statistical inference framework that quantifies the reliability of dynamical terms selected by the Sparse Identification of Nonlinear Dynamics (SINDy) method. It addresses selection bias arising from using the same noisy trajectory for both selection and inference by employing data thinning to create four independent views for selection and inference. The approach accounts for measurement error and shared noise, and its theoretical validity is established under stated conditions with numerical experiments on simulated and experimental data.
By Ashraful Islam, Shuichi Nishino, Tomohiro Shiraishi, Ichiro Takeuchi
DiscoVL introduces a disentangled cross‑modal representation learning framework for vision‑language models, combining orthogonal adversarial regularization with a multi‑branch low‑rank residual aligner to enhance bidirectional visual‑textual interaction. The method decomposes representations into subspaces, enabling cross‑modal feedback at each layer and preventing centroid collapse through an orthogonal adversarial triplet loss. Across 15 benchmarks, DiscoVL consistently outperforms state‑of‑the‑art approaches in base‑to‑novel generalization, cross‑dataset evaluation, and few‑shot learning.
By Mengping Dong, Jinbao Li, Fei Li
IntactWorld introduces a Joint World Modeling Architecture that preserves uncompressed Intact Features to better capture real‑world logic in video generation. By predicting clean intermediate features instead of flow velocity in a high‑dimensional space, it avoids manifold gaps and reduces computational overhead through a Full‑to‑Compact Training Paradigm that replaces raw features with refined CLS tokens. The approach cuts spatial memory usage by 11.4% and inference latency by 43.8%, achieving a 2.46‑point improvement on the VBench 2.0 benchmark.
By Boming Tan, Xiangdong Zhang, Yan Xia, Qi Zhu, Deyi Ji, Xue Yang, Shaofeng Zhang
TAP3D is a new system that reconstructs dense 3D human point clouds from low‑cost thermal array sensors, avoiding the high cost, sparsity, and privacy issues of LiDAR, radar, and depth cameras. It uses a physics‑informed design with a forward thermal model, multi‑primitive estimation for self‑supervised depth recovery, and geometric perspective fusion to suppress interference and separate multiple people. The system, built on a single commodity sensor and evaluated on a 160K‑sample dataset, achieves high accuracy in downstream tasks such as fall detection, indoor tracking, and human mesh recovery.
By Xie Zhang, Chengxiao Li, Xuan Liu, Chenshu Wu
The paper presents a lightweight 6D pose tracking method that operates on relative pose constraints instead of point-based optimization, using uncertainty derived from geometric alignment to weight these constraints. By avoiding direct inclusion of noisy point measurements, the approach achieves fast and robust long-term tracking with computational costs far lower than reconstruction-based trackers. Experiments on four real-world benchmarks show comparable accuracy to state-of-the-art methods while maintaining real-time performance.
By Xiaojie Zhang, Tom Fischer, Viktor Larsson, Eddy Ilg
AgentGarten is a framework that links simulators and game engines with a shared neural renderer to create real‑time interactive virtual worlds. It uses a pretrained video model adapted to geometry conditions, refined with Adversarial Forcing, to produce realistic visual observations while maintaining consistent state and rules. The system enables agents to learn efficiently—achieving comparable performance in only four training rounds versus millions in traditional reinforcement learning—by distilling experience into playbooks that successive agents can inherit and improve upon.
By Jiawei Chi, Shangchen Miao, Zhiyuan Shi, Kailu Wu, Hanyang Wang, Weiliang Chen, Qiyu Dai, Jinshan Ren, Jun Gao, Mingsheng Long, Yueqi Duan, Jiangran Lyu, Jialong Wu, Fangfu Liu
The paper investigates typed decision models used as guardrails in agent systems, evaluating seven open‑weight models on tasks such as prompt‑injection, jailbreak, and toxic‑content screening. Accuracy for allow‑or‑block decisions ranges from 36% to 72% above chance, with models either over‑allowing or over‑blocking. The authors demonstrate that simple textual manipulations—like adding misleading names or server log lines—can dramatically increase fail‑open rates, and that all tested defenses can be bypassed, suggesting these models are unsuitable as the sole decision component.
By Seyedarmin Azizi, Erfan Baghaei Potraghloo, Massoud Pedram
The paper introduces Proof-of-Use (PoU), a reinforcement learning framework designed to prevent tool‑call hacking in deep research agents. PoU enforces evidence grounding by requiring agents to cite normalized evidence identifiers and uses a multi‑objective reward system that includes progressive process rewards, an answer‑support alignment reward, and a curriculum‑style adaptive reward mixing. Experiments demonstrate that PoU effectively mitigates tool‑call hacking and promotes robust, adaptive tool usage even under domain and tool shifts.
By Shengjie Ma, Chenlong Deng, Jiaxin Mao, Jiadeng Huang, Teng Wang, Junjie Wu, Changwang Zhang, Jun wang