Combinatorics
Distributions of Mesh Patterns of Short Lengths on Separable Permutations
Alice L.L. Gao, Sergey Kitaev, Ya-Xing Li et al. (+1 more)
This paper contributes to the long line of research on the distribution of mesh patterns in permutations. We extend these studies to separable permutations and carry out a comprehensive analysis of mesh patterns of length at most~2. For mesh patterns of length~1, we determine the distributions for all six equivalence classes. In addition, we obtain the joint distribution for the patterns in the class containing the well-known permutation statistic known as the strict fixed point. Furthermore, computer experiments suggest that at most 124 pairs of mesh patterns of type 12 and 21 with identical shading are equidistributed. Using
symmetry operations, we partition these pairs into 38 equivalence classes with respect to distribution. By explicitly determining 24 of these distributions (in many cases, in fact, joint equidistributions of the respective pairs), we reduce the number of equivalence classes to~31, which turns out to be the true number of equivalence classes. Enumerating 14 of these classes is left as an open problem.
Read the full abstract ▾
All authors Alice L.L. Gao, Sergey Kitaev, Ya-Xing Li, Yun Li
Cryptography and Security
Adversarial RL for Port-Scan Evasion: Attacker Feature Visibility in Edge-Deployed IDS
Logan Andrew North, Priya Sanjay Kaluskar, Shasi Kumar Ramachandran Prabhu et al. (+2 more)
Machine learning-based intrusion detection systems (IDS) are increasingly used in resource-constrained Internet of Things (IoT) environments, yet their robustness is often evaluated against static attacks rather than adversaries that adapt to detection feedback. This paper investigates adaptive port-scan evasion against ML-based IDS models deployed on a Raspberry Pi 3B+. We implement a live Zeek-based IDS pipeline with XGBoost, a multi-layer perceptron, and a 1D convolutional neural network trained on TON_IoT telemetry, and use a Deep Q-Network (DQN) adversary to learn evasive combinations of probe timing, TCP flags, and payload size under black-box, gray-box, and white-box feature-visibility settings. Although the deployed IDS models detect conventional port scans at 91.1–99.8%, DQN final-50-episode evasion rates range from 61.9% to 98.3% across feature-visibility settings. Greater feature visibility does not monotonically improve evasion, and its effect is model-dependent: against XGBoost, the black-box
agent achieves 92.9% evasion, compared with 61.9% and 76.9% for gray-box and white-box
agents, respectively, whereas 1D-CNN is most vulnerable under white-box access at 98.1%. Because standard DQN can overestimate action values, we additionally spot-check representative conditions using Double DQN. The gray-box condition remains unstable in this check, providing no evidence that overestimation bias alone explains the observed instability. These results show that limited feature knowledge can still enable effective adaptive evasion against static edge-deployed IDS models, motivating more robust defenses for IoT edge environments.
Read the full abstract ▾
All authors Logan Andrew North, Priya Sanjay Kaluskar, Shasi Kumar Ramachandran Prabhu, Peilong Li, Suman Saha
Robotics
Trajectory Planning without Trajectory Data: A Manifold-Guided Approach
Silong Yong, Anji Liu, Cunxi Dai et al. (+5 more)
A common way for trajectory planning is to leverage generative models trained on large collections of expert trajectories. At inference time, the model generates executable trajectories by conditioning on task goal constraints. However, trajectory-based methods rely on costly supervision, scale poorly with sequence length, and often generalize poorly to unseen constraints such as novel start-goal pairs. We propose an alternative to learn the underlying state-space
manifold and use the geometry of the
manifold for trajectory planning. This approach requires only state observations and enables generalization to unseen constraints by con- structing trajectories on the learned
manifold of the state space. Experiments on Maze2D and robotic motion-planning
benchmarks show that Ariadne constructs feasible paths from state-only supervision and generalizes to unseen start-goal combinations. On high-dimensional dual-arm planning, it remains competitive with trajectory-supervised and classical planners, while requiring no trajectory data for training.
Read the full abstract ▾
All authors Silong Yong, Anji Liu, Cunxi Dai, Carl Busart, Guanya Shi, Yilun Du, Katia Sycara, Yaqi Xie
Robotics
CIRRA: Dual-Level Continual Instruction Reconciliation with Ongoing Execution for Embodied Robot Agents in Interactive Household Tasks
Ci Zhang, Enfu Nan, Arman Akbari et al. (+6 more)
Household
robots must accommodate new user instructions while executing ongoing tasks. Existing
agents often regenerate or extensively revise the remaining task sequence, introducing plan ambiguity, logical inconsistency, and redundant execution. We formulate continual instruction reconciliation and propose CIRRA (Continual Instruction Reconciliation for
Robot Agents), a dual-level framework combining LLM-based semantic
reasoning with rule-constrained structural integration. CIRRA first grounds incoming instructions to unique executable skills and resolves underspecified actions and execution locations. It then preserves the ongoing subtask sequence as an execution backbone and generates integration candidates by inserting incoming subtasks into location-matched segments. The semantic reasoner evaluates only modified segments to identify dependencies and conflicts and select the most logically coherent local integration. This structure-preserving process maintains
alignment with ongoing execution, mitigates ambiguity and inconsistency, and reuses shared subtasks to reduce redundant execution. We also introduce CHIRP (Continual Household Instruction Reconciliation and Planning), a text-based
benchmark of 120 episodes across eight household environments and six categories of everyday activities. On CHIRP, CIRRA achieves 74.2% decision agreement, exceeding the strongest replanning baseline by 30 percentage points; every correct fusion decision yields a correctly placed, conflict-free schedule. On a Unitree G1
humanoid, CIRRA interrupts ongoing skills at the correct moment in every trial and significantly outperforms all baselines on every metric.
Read the full abstract ▾
All authors Ci Zhang, Enfu Nan, Arman Akbari, Lin Zhao, Li Wang, Chen Wang, Weiwei Chen, Yanzhi Wang, Geng Yuan
Information Theory
Reconstruction of Geometric and Structural Aspects of Undeciphered Messages by Information-theoretic Methods
Hector Zenil and Abicumaran Uthamacumaran
In previous work, we established sufficient conditions for recovering geometry and
topology from non-random information, demonstrating reconstruction with the Arecibo message. Undeciphered historical records present a related problem: one-way communication without access to their makers' intentions or encoding conventions. Here we extend this framework to the Phaistos Disc, Andean khipu, Rongorongo, Indus inscriptions and the Voynich manuscript, using Egyptian layouts and Arecibo as controls. Algorithmic information dynamics (AID) guides structural perturbations, combining classical information measures, predictive coding, compression and algorithmic-probability-based estimates. Phaistos retains 0.714 bits of excess adjacent-sign mutual information after positional controls; its authentic
segmentation lies within a broad information basin, and cross-face boundary prediction achieves AUCs of 0.76 and 0.86. Repetition explains its principal recurrence, while the tested spiral
embeddings provide no evidence of additional cross-winding structure. Across several corpora, comparative transfer persists beyond exact shared local pairs. Khipu
knot forms distinguish authentic attachments after controlling for degree, depth, fibre and twist (adjusted $p=0.009$); constrained assignment recovers 8.75% of concealed parents against 7.87% expected by chance. Row-
alignment tests yield no comparable evidence after correction. Calibrated BDM recovers Arecibo's 23-column width (search-corrected $p=0.005$), while executable controls detect spatial dependence and eliminate it through interventions on the generator. These findings connect information-based structural reconstruction with interventional
reasoning, distinguishing recoverable organisation from semantic decipherment.
Read the full abstract ▾
High Energy Physics (Theory)
Gravitational scattering amplitudes in collinear and high-energy limits
Lorenzo Pietrini
In this thesis we study the high-energy and collinear behaviour of gravitational scattering amplitudes and their relation to classical scattering and radiation observables. Multi-Regge kinematics, characterised by a strong rapidity ordering, provides the factorised building blocks governing the leading logarithmic structure. Relaxing this ordering to next-to-multi-Regge kinematics allows two neighbouring particles to have comparable rapidities and provides the real emission building blocks entering at next-to-leading logarithmic accuracy. We extract the next-to-multi-Regge impact factor from tree-level MHV amplitudes for pure gravitons and derive its gravitational splitting functions. We then use BCFW recursion relations to reconstruct the five-point tree amplitude for two massive scalars scattering with the emission of one graviton. Its high-energy limit yields the massive scalar–graviton impact factor and, through the KMOC formalism, a representation of the leading high-energy collinear waveform. Finally, by sewing the relevant vertices across unitarity cuts, we construct the elastic \(H\) kernel, its radiative extension and a classical next-to-multi-Regge kernel. The latter reproduces the standard \(H\) kernel in the multi-Regge limit and the universal Weinberg current in the soft limit.
Read the full abstract ▾
Differential Geometry
Harmonic torsion of algebraic generalized Ricci solitons and the structure of solvable extensions
Huibin Chen, Zhiqi Chen and Fuhai Zhu
We prove harmonicity for nonshrinking algebraic generalized
Ricci solitons and for all algebraic generalized
Ricci solitons on solvable Lie
algebras. In the solvable setting, we characterize expanding
solitons by normal extensions of generalized nilsolitons, and derive a sharp rank bound.
Read the full abstract ▾
Computation and Language
LRCC: Generalizing Low-Rank Compression with Conditional Computation
Thomas Vaitses Fontanari, Maximo Eduardo Rulli, Federico Alvetreti et al. (+2 more)
Low-rank compression reduces the cost of pretrained
language models by replacing linear transformations with low-rank factorizations. However, conventional methods use a fixed rank allocation during inference, assigning the same amount of compute regardless of the input
token. We introduce Low-Rank Conditional Computation (LRCC), which adds
token-dependent computation to pretrained models by training one lightweight router per
Transformer block to select among a small set of nested low-rank paths. During training, the low-rank factors remain frozen, and only the routers are optimized. We evaluate LRCC on Llama and Qwen models for
language modeling and zero-shot downstream tasks. Within the same average active-parameter budget, LRCC improves the predictive performance over static low-rank compression, including a 7.6 percentage-point gain in average downstream accuracy on Llama-2-7B over static methods. At matched batch-size-1 decoding latency, LRCC improves both perplexity and downstream accuracy on Llama-3.2-1B and remains competitive on Llama-2-7B, without specialized kernels. Finally, we assess the usefulness of assigning a
token-wise path by analyzing the routers' path choices.
Read the full abstract ▾
All authors Thomas Vaitses Fontanari, Maximo Eduardo Rulli, Federico Alvetreti, Donatella Genovese, Simone Scardapane
Group Theory
Infinitely many Nielsen classes in mapping class groups and free-group automorphism groups
Wenchang Yang
We formulate a root-conjugation criterion for producing generating pairs and detecting Nielsen inequivalence by a
polynomial symmetric-trace invariant. The method simultaneously treats mapping class groups and
automorphism groups of free groups. We prove that $\mathrm{Mod}(\Sigma_g)$, $g\ge2$, and $\mathrm{Aut}(F_n)$, $\mathrm{SAut}(F_n)$, $\mathrm{Out}(F_n)$ and $\mathrm{SOut}(F_n)$, $n\ge3$, have countably infinitely many Nielsen classes of generating pairs. A sign parameter unifies the full and special
automorphism-group constructions, with common generation arguments and trace
polynomials. The same homology representations give the corresponding results for $\mathrm{Sp}_{2g}(\mathbb{Z})$, $g\ge2$, and $\mathrm{SL}_n(\mathbb{Z})$ and $\mathrm{GL}_n(\mathbb{Z})$, $n\ge3$. This answers Hirose–Monden's low-genus question and Kapovich's Question 8.1.
Read the full abstract ▾
Populations and Evolution
Dynamical Insights into the Current Control Strategies for Chikungunya
Bo Zheng, Xingzhi Chen, Jianglong Xiao et al. (+3 more)
This paper addresses the challenge that, under China's current mosquito-control policy for chikungunya—clearing stagnant water, killing adult mosquitoes, and preventing bites—epidemics can still recur and continue to rise. By constructing a vector–host dynamical model that incorporates asymptomatic infections and a screening rate, we derive approximate analytical expressions for the epidemic peak value and peak time, and reveal the intrinsic link between short-term transients and long-term outcomes. Simulations across three scenarios—human-seeded, mosquito-seeded, and joint human–mosquito-seeded—show that (i) even when the vector population is effectively suppressed, asymptomatic carriers can still sustain transmission; (ii) the effect of the screening rate on the peak time is non-monotonic, and there exists a critical threshold that maximizes the delay of the epidemic; and (iii) moderate screening can both suppress the first wave and avoid leaving an excessively large susceptible pool that would amplify subsequent waves. Accordingly, we upgrade the original policy to a Twelve-character strategy for prevention, mitigation, and control—clearing stagnant water, killing adult mosquitoes, preventing bites, and screening cases early—providing theoretical support for chikungunya and other mosquito-borne diseases.
Read the full abstract ▾
All authors Bo Zheng, Xingzhi Chen, Jianglong Xiao, Kai Wang, Jianshe Yu, Huaiping Zhu
Machine Learning
Climbing the Design Ladder: Sequential Knowledge Distillation for Early-Stage Circuit Timing Prediction
Reza Moravej, Fahad Rahman Amik, Zhanguang Zhang et al. (+2 more)
Integrated
circuit design involves multiple design stages: logic synthesis, floorplanning, placement, and routing, with each stage taking hours to weeks to complete. Discovering timing violations late in this flow forces costly iterations back to earlier stages, wasting computational resources and delaying product launches. While predicting post-routing timing from early-stage data could prevent these failures, existing machine learning approaches struggle with the massive abstraction gap between post-synthesis logical descriptions and post-routing physical layouts. We propose STEP-KD (Sequential Timing Evaluation via Progressive Knowledge
Distillation), which leverages intermediate design stages as “stepping stones” for progressive knowledge transfer rather than attempting direct prediction. STEP-KD trains teacher models at the post-routing, post-placement, and post-floorplan stages, then sequentially distills their knowledge to a post-synthesis student model through representation
alignment. Experiments on diverse
circuits demonstrate that STEP-KD reduces timing prediction error compared to direct
distillation and supervised baselines, and in most settings compared to the industry-standard Static Timing Analysis (STA) tool. STEP-KD reduces the weighted mean absolute percentage error of Total Negative Slack prediction to 19.78%, compared with 74.84% for STA. Our proposed method is step forward to identify timing problems earlier, avoiding expensive late-stage redesigns.
Read the full abstract ▾
All authors Reza Moravej, Fahad Rahman Amik, Zhanguang Zhang, Didier Chételat, Yingxue Zhang
Robotics
HexaGripper: A Single-Actuator, Winch-Deployed Gripper for Autonomous Aerial Parcel Collection
Nimantha Adikaram, Mahen Abeyratne, Lakmina Chandrajith et al. (+3 more)
Autonomous aerial parcel collection remains constrained by package-transfer operations that require manual loading, landing, or dedicated ground infrastructure. This letter presents HexaGripper, a single-actuator, winch-deployed six-plate gripper for autonomous collection of cuboid parcels. The proposed mechanism provides synchronized grasping with a wide capture region and tolerance to positional misalignment during pickup. The system integrates
vision-based
alignment, range sensing, winch deployment, and state-based control to enable autonomous collection while maintaining
UAV separation from the pickup surface. Experimental evaluation covered static grasping, capture-workspace assessment, and end-to-end outdoor aerial collection. Static experiments achieved 100% pickup success (15/15 trials) across three parcel geometries, while workspace experiments achieved successful pickup at all 28 tested positions up to a 150 mm radial offset. End-to-end outdoor aerial collection achieved an 80% success rate (4/5 trials). These results demonstrate the feasibility of mechanically synchronized, winch-deployed grasping for landing-free autonomous aerial parcel collection.
Read the full abstract ▾
All authors Nimantha Adikaram, Mahen Abeyratne, Lakmina Chandrajith, A. H. T. E. De Silva, Isira Naotunna, Asanka Perera
Cryptography and Security
Safeguarding LLMs via Model-Agnostic Latent Safety Signals from Dark Knowledge
Wonjun Lee, Kyungsik Yang, Gaeun Ji et al. (+5 more)
LLMs have advanced rapidly, raising growing concerns about their safety. Recent work has proposed approaches to detect and defend against attacks including defenses at decoding stage that leverage models' hidden states. However, existing decoding-stage defenses suffer from two limitations. First, they introduce a trade-off between safety and over-refusal, where strengthening safety degrades the model's helpfulness on benign queries. Second, many of these methods rely on internal hidden states and are thus restricted to specific architectures, incurring substantial overhead and limited generalization across models. To address these limitations, we introduce LADE (Latent Safety Signals for Defense), which leverages latent safety signals extracted by contrasting harmful and benign queries from dark knowledge (i.e., information carried by the output probability distribution beyond its argmax) in the first-
token output probability distribution. Our key insight is that, beyond surface-level refusal
tokens, the dark knowledge in the first-
token distribution contains latent safety signals, defined as
tokens whose probabilities differ sharply between harmful and benign queries. We show that these signals consistently align across LLMs, forming a model-agnostic direction that emerges from safety
alignment. LADE consists of three components: (1) Extracting Latent Safety Signals from Dark Knowledge, which selects top-k safety-discriminative
tokens from the first-
token probability distribution; (2) Tokenizer Mapping, which maps these
tokens across different tokenizers to enable model-agnostic application; and (3) kNN-based Discrimination, which classifies queries via a k-Nearest Neighbors search over the mapped
tokens. Across diverse LLMs and
benchmarks, LADE is robust against a wide range of jailbreak attacks and lowers attack success rates while maintaining a competitive safety-utility trade-off.
Read the full abstract ▾
All authors Wonjun Lee, Kyungsik Yang, Gaeun Ji, Vaidehi Patil, Haon Park, Bumsub Ham, Mohit Bansal, Suhyun Kim
Cryptography and Security
BVI: Lightweight, Data-Centric Blockchain-Based Verification of Identity Claims
Harshith Pothapala, Gagandeep Singh, Samudi Amarasinghe et al. (+2 more)
A person who answers an unexpected call claiming to come from a bank has no way to check the claim. Australian text messaging has labelled a message as unverified when the sender identifier is not registered since 1 July 2026, but a voice call still arrives with nothing behind it, and voice cloning has removed the last cue recipients relied on. We present BVI, which answers one question for the recipient: did the calling party prove it holds a credential a registered organisation issued for this call? BVI keeps the organisational record, its authorised channels and its revocation state on a public ledger in a directly queryable form, and puts all decision logic in the handset, which performs eleven checks, pays no transaction fee and holds no full-chain state. We define ten attack classes plus the case in which revocation cannot be resolved, compare them in a 10-by-4 coverage
matrix spanning BBCA, the content digest, the detector and composed BVI, and run 27 automated scenario tests against isolated Hardhat fixture states of the BVI contract; all 27 pass. For media substitution and synthetic
speech, the contract tests validate commitment and gating properties rather than claiming detector accuracy. The mandatory per-session anchor costs about 91.5k gas and is invariant in call duration and hop count; each participating intermediary additionally contributes one optional attestation write. In a 20,000-session-per-
cell path simulation, at one quarter carrier participation BVI detects 20.6 per cent of randomly located in-path rewrites versus 0.1 per cent for the every-hop comparison, while identity and content evidence remain available even when path evidence is indeterminate. We also quantify the throughput ceiling of the anchoring design.
Read the full abstract ▾
All authors Harshith Pothapala, Gagandeep Singh, Samudi Amarasinghe, Priyanka Singh, Xue Li
Symplectic Geometry
Obstructions in Symplectic Embedding Problems for Four-Dimensional Convex Toric Domains
Theodore Coyne
In Beyond ECH Capacities, Hutchings used the ECH cobordism map to produce obstructions for
embedding one convex toric domain into another. We generalize the methods there to obstruct
symplectic embeddings of a disjoint union of convex toric domains into another convex toric domain. We also find additional obstructions coming from intersection positivity and use similar methods to obstruct the existence of isotopies between two given
symplectic embeddings.
Read the full abstract ▾
Machine Learning
Targeted search shows that random-device testing underestimates worst-case error in a simulated wave-based neural operator
Samrendra Roy, Jason Yoo, Souvik Chakraborty et al. (+1 more)
Wave-based processors promise fast, energy-efficient
Fourier layers for neural operators. They are usually validated on randomly sampled devices, but using them requires knowing how large their error can become under fabrication and
alignment variation. In a stylised numerical case study, a hybrid
Fourier neural operator runs its four spectral layers on simulated coherent 4f processors with 32 toleranced knobs, whose half-widths are representative rather than calibrated. For 120 models (four tasks, six training methods, five seeds), we compared the worst of N random in-spec devices with a searched one. On a deterministic simulator with one frozen draw of the random static errors, the searched device's held-out error was 1.08-3.10 times the maximum over 200 Monte Carlo devices and 1.06-2.71 times that over 1000. With 20 fresh static draws, it still exceeded the maximum over 200 random devices in 116 of 120 models. Under uniform sampling, the probability of drawing such a device is at most 0.37% per model (two-sided 95% Clopper-Pearson), which says nothing about how large its error is. The gap persisted with uniform or Sobol' sampling at the search's budget, shared knobs, a second crosstalk model, box scales of 0.25-2 and a pixel-level device model. Models trained only with random static errors reached 3.7-39.9 times their nominal error on searched devices, and fine-tuning on random and gradient-searched devices gave the lowest searched error of the six in all 20 task-seed pairs. For two heat-exchanger quantities, a search targeted at each exceeded the worst of 1000 random devices in all 39 models, and hence the Wilks 95/95 limit (worst of 59). For the mean pressure of 11 models, no random device exceeded a 1% error threshold, but the searched device did. Random testing estimates how often errors exceed a threshold; worst-device search gives a lower bound on how large they can be.
Read the full abstract ▾
All authors Samrendra Roy, Jason Yoo, Souvik Chakraborty, Syed Bahauddin Alam
Complex Variables
Finite holomorphic pullbacks, Segre numbers, and generic Lê numbers
Z. Jelonek, V. H. Jorge Perez and R. N. Araújo Dos Santos
We study numerical comparisons for hypersurface singularities under finite holomorphic maps between smooth germs. We retain Jelonek's topological proof of the Milnor-number inequality in the isolated case and give an algebraic proof using a cyclic factorization, Brieskorn modules, and trace. For a reduced divisor-theoretic pullback, we prove lexicographic monotonicity of Segre numbers. Componentwise monotonicity follows when the two singular loci have the same dimension and the target Jacobian ideal is equimultiple. For one-dimensional singular loci, we also obtain componentwise comparison under an equality condition on the first nonzero Segre number or a nonramification condition. The arguments use finite-flat pullback of Segre cycles and
Hilbert–Samuel multiplicity. Through the identification with generic Lê numbers, the same results hold for these invariants. We distinguish these statements from comparisons in arbitrary prepolar coordinates and formulate the remaining componentwise and ramified cases as
conjectures.
Read the full abstract ▾
Robotics
Task-Space Imitation Guidance for Efficient Reinforcement Learning
Salar Asayesh, Hossein Darani, Todd Cao et al. (+2 more)
We introduce Task-Space Imitation Guidance for Efficient Reinforcement Learning (TIGER), a reward-construction and pretraining framework for sparse-reward tabletop robotic manipulation. TIGER treats an action-chunked imitation policy not as an executable controller or action prior, but as a local task-space progress
estimator: predicted action chunks are converted, using controller-aware action-to-motion mapping, into short-horizon end-effector references, and the RL
agent receives dense progress rewards toward these references while the sparse environment reward remains the dominant objective. During pretraining, TIGER uses imitation-guided look-ahead signals to relax conservative value penalties for actions predicted to make task-space progress, reducing off-
manifold exploration during early online RL. Across simulation and real-
robot experiments, TIGER improves early sample efficiency and reduces measured safety violations while matching or improving final success rates relative to prior RL and IL-RL baselines on the evaluated tasks.
Videos and an overview of this work are available at https://sanctuary.ai/news/tiger/.
Read the full abstract ▾
All authors Salar Asayesh, Hossein Darani, Todd Cao, Evgeny Andriash, Mani Ranjbar
Probability
Stability of Szarek's inequality with best constant
Xinyuan Xie
Let $\varepsilon_1,\ldots,\varepsilon_n$ be independent Rademacher random variables. We settle the best constant $c$ such that \[ \mathbb{E}\Bigl|\sum_{j=1}^n a_j\varepsilon_j\Bigr| \ge \frac{1}{\sqrt{2}} +c\Bigl|a-\frac{e_1+e_2}{\sqrt{2}}\Bigr| \] holds for every $n\ge 2$ and every unit vector $a\in\mathbb{R}^n$ with $a_1\ge\cdots\ge a_n\ge 0$. We prove that the optimal constant is $c=(2-\sqrt{2})^{3/2}/8$, with equality attained at $a=\frac{1}{2}(1,1,1,1,0,\ldots,0)$ for $n\ge 4$. This completes a line of research by De-Diakonikolas-Servedio, Eskenazis-Nayar-Tkocz and Fang-Wang.
Read the full abstract ▾
Robotics
ReDex: Repairing Sim-to-Real Dexterous Policies by Finger-Level Compliant Interaction
Jinzhou Li, Hadi Tabatabaee, Kelin Yu et al. (+6 more)
Dexterous manipulation policies trained in simulation often fail to transfer to the real world because of errors in contact timing and force regulation. Yet these policies can retain useful multi-finger coordination for task progression. We propose ReDex, a framework for adapting a simulation-trained base policy to the real world by correcting local contact failures and incorporating tactile feedback. Starting from a proprioception-only base policy, ReDex allows a human operator to physically correct contact failures at selected fingers under compliant control during real-world rollouts, while the frozen base policy continues to control the remaining fingers. These rollouts combine base policy execution, human-corrected finger motion, and fingertip force observations. We reconstruct force-informed targets from these rollouts to train a standalone force-conditioned policy via behavior cloning. This design reduces human correction effort, enables learning of contact regulation from real-world interaction, and introduces force feedback into a proprioception-only policy without tactile simulation or complex full-hand teleoperation. We evaluate ReDex on two challenging, contact-rich dexterous manipulation tasks on real hardware. Compared with sim-to-real transferred base policies, ReDex increases Object Flipping success rate from 14% to 86% across two objects and average Screwdriver Rotation progress from 26.0% to 95.3% across three objects.
Read the full abstract ▾
All authors Jinzhou Li, Hadi Tabatabaee, Kelin Yu, Yuyin Sun, Cheng-Hao Kuo, Roberto Martín-Martín, Nima Fazeli, X. Alice Wu, Xianyi Cheng
Audio and Speech Processing
Region-Aware Masking for Accent-Robust Cross-Lingual Text-to-Speech
Haoqi Li, Shivam Mehta, Ravi Teja Gadde et al. (+1 more)
Accent leakage remains a critical challenge in cross-lingual zero-shot text-to-
speech (TTS), where models inadvertently transfer both the speaker's timbre and source-
language accent into the target-
language output. In mask-reconstruction TTS this is amplified by a train–inference mismatch: training reconstructs from same-
language context, while inference conditions on cross-lingual context. We close this gap by concatenating utterances from two
languages and placing the reconstruction mask relative to the
language boundary, so training presents the cross-lingual prompting pattern the model encounters at inference. This requires no
language IDs, accent labels, parallel same-speaker recordings, or architectural changes—only the mask geometry differs. In a listening study with native speakers, region-aware masking reduces perceived accent from 4.3 to 0.5 on a 0-5 scale against the unadapted baseline, and by 18-51% in seen regimes and 35-55% on unseen source
languages against bilingual adaptation alone, with no measurable loss in intelligibility or naturalness. Comparing mask geometries shows that placement, not the amount masked, governs the balance between accent suppression and speaker preservation: masks confined to the reconstruction region suppress accent most but retain the reference speaker least reliably, whereas two-region masking achieves both. Mask geometry is thus a simple, effective lever for accent robustness.
Read the full abstract ▾
All authors Haoqi Li, Shivam Mehta, Ravi Teja Gadde, Yinghong Lan
Human-Computer Interaction
PAIR: Perceptual Affective Inference and Regulation in a Real-Time Multimodal Conversational Agent
Kexin Quan, Zijian Ding, Jiaye Yong et al. (+3 more)
Sustained emotional support requires generative
agents to connect momentary
emotion inference and regulation with continuity across encounters. We present PAIR (Perceptual Affective Inference and Regulation), a real-time
multimodal agent that reconstructs how an event is appraised into an emotional state. Appraisal scaffolds produce a valence-arousal-dominance estimate and select regulation guidance, delivered through conversation with coordinated
speech, color, and avatar cues. Rolling
memory carries context across sessions, and the scaffold re-runs after guidance. In a 14-day deployment with 19 participants, 1,093 sessions paired initial and post-guidance estimates with unanchored self-reports. Initial valence reached MAE 1.20 on the 9-point SAM scale (r=.68), dominance reached MAE 1.30, and arousal showed weak agreement even after coarsening. Self-reported emotional change varied with initial state, with the largest valence increases in sessions that began at negative valence. Perceived understanding was associated with greater valence increase and showed little correspondence with numerical prediction error. Over two weeks, helpfulness increased while input shortened; interviews traced personalization and companionship to relevant recall, context updates, and familiar dialogue. These findings connect inference accuracy to conversational and temporal patterns of support through per-event, first-person evaluation.
Read the full abstract ▾
All authors Kexin Quan, Zijian Ding, Jiaye Yong, Qinshi Zhang, Dong Wang, Jessie Chin
Machine Learning
Activation Denoising: A Robustness View on Parallel vs Sequential LLM Quantization
Yan Scholten, Rachel Lawrence, James Hensman et al. (+3 more)
Post-training quantization is a powerful tool for compressing large
language models. The most scalable methods quantize every layer in parallel, but quantization errors then compound through the residual stream, as no layer corrects for the errors of the layers before it. Sequential quantization accounts for this error compounding by re-calibrating each layer on the already-quantized outputs of its predecessors, yielding stronger results but at the cost of a serial schedule that becomes a bottleneck at scale. As a solution, we propose parallel quantization with activation denoising, which recovers much of the sequential benefit while keeping quantization fully parallel. Rather than re-calibrating layer-by-layer, we take a robustness perspective and model the upstream error as noise, regularizing to be robust to it through a preprocessing step followed by metric-weighted rounding. Applied at every layer, this regularization forms a depth-compounding smoothness penalty that dampens how strongly quantization errors amplify through the model. Unlike orthogonal rotations commonly used in quantization, which must preserve the model's function, we multiply the weights by a more general linear transformation. We find that the two are complementary and their effects compound. Empirically, our robustness regularization recovers a significant part of sequential quantization's benefit in a single parallel pass, at a fraction of its time. Overall, by treating compounding quantization errors as a robustness problem, we offer a principled foundation for more efficient and accurate LLM quantization at scale.
Read the full abstract ▾
All authors Yan Scholten, Rachel Lawrence, James Hensman, Stephan Günnemann, Alicia Curth, Riccardo Grazzi
Artificial Intelligence
Grounding What Shapes the Plan: Rethinking Groundedness for Physical Intelligence in Autonomous Driving
Minkyoung Cho, Zewei Zhou, Wenhao Ding et al. (+11 more)
Driving models increasingly ground
reasoning in causal relations, spatial structure, perceptual evidence, and predicted futures. These advances make
reasoning more faithful to the driving scene, but leave a fundamental question unresolved: what should groundedness mean when the model ultimately outputs an action? Correctly grounded
reasoning does not, by itself, ensure desirable driving outcomes. We introduce GroundAct, which starts from a simple premise: driving unfolds through physical entities and their interactions. Entities therefore become the unit of grounding; a lightweight reference
token keeps each selected entity's continuous state addressable through symbolic
reasoning; and only the referenced entities' interactions with the evolving proposal correct the plan. The result is an explicit path from what
reasoning grounds to what the plan does, which we call grounded planning. To assess its practical value, we evaluate GroundAct in both open- and closed-loop settings. GroundAct shows strong open-loop planning across normal, out-of-distribution, and safety-critical scenarios, with closed-loop results extending this evidence to driving in simulation.
Read the full abstract ▾
All authors Minkyoung Cho, Zewei Zhou, Wenhao Ding, Shuhan Tan, Boyi Li, Yuxiao Chen, Yan Wang, Zheng Lian, Min-Hung Chen, Chaowei Xiao, Zhuoqing Mao, Boris Ivanovic, Marco Pavone, Yulong Cao
Number Theory
Further results on the paramodular Hecke algebra
Jennifer Johnson-Leung, Joshua Parker and Brooks Roberts
In this paper we further examine the structure of the graded paramodular Hecke
algebra $\mathcal H$. We define a commutative subring $\mathcal{H}^\alpha$ of $\mathcal{H}$ as the elements fixed by a certain
automorphism $\alpha$, and we show that the elements $T(q^k)$, defined as the sum of the double cosets of degree $k$, are contained in $\mathcal{H}^\alpha$. We prove that the formal power series in the indeterminate $t$ with coefficients $T(q^k)$ is an explicit rational function in $t$ with coefficients from $\mathcal{H}^\alpha$. We also determine the structure of $\mathcal{H}^\alpha$ and its relation to $\mathcal{H}$.
Read the full abstract ▾
Computation and Language
Not What a Child Expressed: Auditing the Sign-to-Text Safety Interface in Child-Facing AI
Muhammad Rafiullah Memon, Viet Vo, Wanlun Ma et al. (+1 more)
Automatic sign
language translation (SLT) has entered consumer products, turning American Sign
Language into English text for dictation, messaging, and queries put to a conversational assistant. Child-facing AI and platform trust-and-safety tooling decide on text, using filters on minor accounts and grooming classifiers that score chat messages. A signing child who uses SLT therefore reaches these safeguards through a translation. We found no publicly documented system in which the two have been jointly evaluated, and the leading deployed SLT model was neither trained nor formally evaluated on signers under 18. Errors that alter negation, participant roles, secrecy, urgency or help-seeking could change a safety decision without disturbing fluency. This paper proposes a Deaf-informed pre-deployment audit of that boundary, with a failure taxonomy, a sanitised scenario schema, four comparison conditions, and four outcome measures. Auslan is the planned first case study.
Read the full abstract ▾
All authors Muhammad Rafiullah Memon, Viet Vo, Wanlun Ma, Yang Xiang
Machine Learning
Harmful SFT Leaves a Continuous Trace in LLM Checkpoint Updates
Ziqun Bao, Xinyu Zhang, Yuchen Shao et al. (+1 more)
Safety
auditing of post-trained large
language models typically relies on model behavior, requiring model execution and depending on the coverage of available evaluations. This work asks a different question: Do the target behaviors optimized during supervised fine-tuning (SFT) leave readable evidence directly in checkpoint updates? We find that harmful-compliance SFT induces a continuous, objective-dependent ordering in checkpoint-update space. Using a reference geometry defined by pure harmful-compliance, safety-targeted, and benign-utility SFT, we find that a checkpoint-level coordinate s_H tracks controlled harmful-objective composition with Spearman correlations of 0.986-0.992 across four 7-8B backbones, with the same ordering persisting at larger model scales. Matched compliance-versus-refusal controls show that this checkpoint trace reflects the SFT objective rather than harmful-input exposure, while additional controls rule out simple explanations based on harmful-example count or generic training intensity. Building on this structure, we introduce TRACE, a weights-only
auditing method that localizes an unknown checkpoint update relative to frozen harmful and non-harmful reference prototypes and converts this geometry into a continuous harmful-objective score. TRACE requires neither model queries nor access to the unknown SFT data, and can be evaluated directly from checkpoint updates. Across distribution shifts, unseen data, different SFT configurations, partial checkpoint access, and LoRA/full-parameter fine-tuning, the trace remains stable and is positively associated with independently measured attack success rates. TRACE remains informative even at low harmful-objective proportions, providing a complementary
auditing signal when behavioral evaluation is unavailable or incomplete. Code is available at https://anonymous.4open.science/r/Code4TRACE-54D3.
Read the full abstract ▾
All authors Ziqun Bao, Xinyu Zhang, Yuchen Shao, Chengcheng Wan
Chemical Physics
What Rate Theories Compute: Chemical kinetics from Arrhenius to machine-learned potentials
Rodney S. Ruoff
Chemical rate theories have advanced by changing how a reaction is represented and which molecular quantities are calculated. Several advances also supplied controlled corrections to earlier theories. I connect this history, from Arrhenius to machine-learned potentials, to tests of the assumptions behind a calculated rate. Original sources clarify Marcelin's treatment of incomplete transmission and reactive-population depletion, and Christiansen's descriptions of orientation and collisional deactivation. Five numerical comparisons distinguish tests against experiment from tests using the same molecular model and from calibration. For hydrogen desorption from platinum, a published barrier adjustment improves absolute rate agreement but increases the spread of calculated-to-experimental ratios across temperatures; the source supplies no rate uncertainties. For triosephosphate isomerase, changing the prior on microscopic rates shifts the median inferred intermediate energy from 7.3 to 17.2 kJ/mol with the same inputs, likelihood, and bounds. This sensitivity calculation does not determine a preferred physical energy. I also examine how later molecular information can change the interpretation of older measurements. Hydrogen-oxygen chain branching provides a published reconciliation involving revised thermochemistry and dynamics. For pyrophosphate hydrolysis, conditional speciation identifies a potentially important complex containing two magnesium ions whose hydrolysis rate is not supplied by the recent calculations. Proposed tests use independent species populations, a later optical calibration of Criegee intermediates, and controlled temperature histories and local recession measurements in diamond dissolution.
Read the full abstract ▾
Distributed Computing
NCCL M2N: A Layout- and Topology-Aware Collective for Distributed Tensor Resharding
Kaushik Kandadi, Youngeun Kwon, Sreeram Potluri et al. (+6 more)
Distributed training and rollout generation often use different tensor layouts, requiring model weights to be resharded across distinct process groups. This M-to-N redistribution is not directly expressed by standard collectives. Flat direct sends duplicate traffic across destination replicas, while gather-then-broadcast concentrates network injection at one root and transfers data that destinations do not need. For DeepSeek-V3 on 256 GPUs, legacy all-gather plus broadcast accounts for 29.4% of the reported reinforcement-learning step time. We present NCCL M2N, a layout- and
topology-aware collective primitive for distributed tensor resharding. Given source and destination meshes and placements, it derives the required transfer regions and a global communication schedule. Its hierarchical route balances source contributions across eligible destination ranks, forwards one copy between destination NVLink domains, and completes local replication over NVLink. Network transfer and local replication overlap, avoiding replica-multiplied source egress. An aggregate data-movement model captures the limits of both stages. We evaluate NCCL M2N on up to 256 GB200 GPUs in an NVL72 cluster with NDR InfiniBand. A single FFN-MoE layer transfer achieves up to 7.9x speedup over flat direct sends (9.8 ms versus 77.3 ms). In a separate 256-GPU DeepSeek-V3 NeMo-RL experiment, NCCL M2N reduces reported weight-sync time from 5.78 s to 2.77 s, a 2.09x speedup over legacy all-gather plus broadcast, and reduces step time by 12.7%.
Read the full abstract ▾
All authors Kaushik Kandadi, Youngeun Kwon, Sreeram Potluri, Ching-Hsiang Chu, Ke Wen, Pouya Kousha, Sangkug Lym, Nitin Nitin, Manjunath Gorentla Venkata
Robotics
ProCut: Probabilistic Cutting Topology for Autonomous Electrosurgical Tissue Dissection
Xiao Liang, Fei Liu, Florian Richter et al. (+2 more)
Accurately modeling and tracking the deformation of soft tissue is critical for a wide range of interventional and
surgical procedures. However, current methods struggle in scenarios involving topological changes, such as cutting and dissection, due to the inherent non-linearity and discontinuity introduced by explicit changes in connectivity. In this work, we present a novel, fully differentiable framework that enables robust estimation and modeling of topological changes during deformable tracking. Our method introduces a continuous, sigmoid-based formulation to smooth the otherwise discrete event of tissue cutting, making it amenable to gradient-based optimization within a differentiable Position-Based Dynamics (PBD) simulation. To account for uncertainty and improve robustness in the presence of noisy visual data, we incorporate Stein Variational Gradient Descent (SVGD) for particle-based probabilistic inference, generating multiple hypotheses for topological state estimation. Building on this foundation, we develop an autonomous dissection
algorithm for thin-shell tissues that leverages topological updates to guide closed-loop cutting trajectory control. We evaluate our approach in both simulated and real-world electrosurgical environments, demonstrating significant improvements in topological estimation accuracy and dissection precision over existing methods. Our results highlight the potential of this framework to advance automation in soft-tissue
surgical procedures by enabling reliable perception and control in the presence of complex structural changes.
Read the full abstract ▾
All authors Xiao Liang, Fei Liu, Florian Richter, Genie Rubaiyat, Michael Yip