Artificial Intelligence
MLCommons Jailbreak Benchmark v1.0
Carsten Maple, Cagatay Yucel, Isaac Holeman et al. (+34 more)
Modern AI systems are designed to refuse hazardous requests. A jailbreak is a
prompt crafted to bypass those safeguards and elicit outputs that the system would normally refuse to provide. The MLCommons Jailbreak
Benchmark v1.0 provides an end-to-end methodology for evaluating the robustness of large
language models to single-turn, text-based jailbreak attacks. It combines criteria-driven system and attack selection, paired baseline and
adversarial evaluation, human annotation, automated evaluator calibration, scoring, grading, and risk-calibrated disclosure within a single benchmarking pipeline. The
benchmark evaluates eight open-weight systems using 264 seed
prompts spanning eleven hazard categories and representative attacks drawn from the MLCommons Jailbreak Taxonomy. Responses are assessed using the AILuminate Assessment Standard v1.4, and robustness is measured through the Resilience Gap: the change in safety performance between baseline and
adversarial conditions. Across all evaluated systems and attacks, the unsafe-response rate increased from 11.08% under baseline conditions to 18.65% under jailbreak conditions, producing an average Resilience Gap of 7.57%. Accessible systems showed a larger mean gap, while attack effectiveness varied substantially across attack categories and hazards. The
benchmark also examines evaluator reliability and sources of measurement error. Beyond reporting results, Jailbreak
Benchmark v1.0 establishes a reproducible methodological foundation for comparative jailbreak evaluation and for future expansion across systems, attacks, hazards, and evaluation methods.
Read the full abstract ▾
All authors Carsten Maple, Cagatay Yucel, Isaac Holeman, Chris Knotz, Peter Mattson, James Goel, Jonathan Petit, Sean McGregor, James Ezick, Abhishek Kumar, Alicia Parrish, Murali Emani, Kashyap Iyer, Faiza Khan Khattak, Washington Mbonu, Daniel Machlab, Eileen Long, Shaona Ghosh, Jibin Varghese, Roman Lutz, Andrew Gruen, Bennett Hillenbrand, Prabal Gupta, Mohammed Serrhini, Dhivya Nagasubramanian, Aakash Gupta, Jun Lu, Kurt Bollacker, Chang Liu, Jonathan Petit, Cong Chen, Jean-Philippe Monteuuis, Brent Miller, Apurv Verma, Roman Eng, Armstrong Foundjem, Mohammed Serrhini
Artificial Intelligence
Scaling Trajectories for Complex Tasks through Recursive Self-Rewrite
Zongxia Li, Yucheng Shi, Zhongzhi Li et al. (+7 more)
Successful trajectories on difficult tasks provide valuable supervision for model improvement, but specialized harnesses introduce interventions that may be unavailable during deployment. We propose Recursive Self-Rewrite (RSR), a framework that uses one base model, Qwen-3.8-27B, to discover successful solutions under diverse harnesses and reconstruct them as training trajectories under a general harness. A planner extracts procedures into runbooks, a critic screens for verifier and solution leakage and guides recursive revision, and an executor follows qualified runbooks in fresh sandboxes. Across approximately 3K self-curated terminal tasks, three harnesses jointly solve 759 tasks, 34.3% more than the strongest individual harness in the recorded pool. RSR expands 2,001 successful source trajectories into 11,094 rewritten trajectories for supervised finetuning. Training on these trajectories outperforms both the base model and direct trajectory SFT. Compared with the base model, pass@3 increases from 57.0% to 74.2% on Terminal-Bench 2, from 1.5% to 9.1% on Terminal-Bench 4, from 39.0% to 63.0% on our self-curated Terminal-Bench Hard, and from 3.0% to 6.0% on our Software Terminal-Bench. Process reward on Long-Horizon Terminal-Bench rises from 0.21 to 0.29. These results show how diverse harness-assisted experiences can be reconstructed into reusable capabilities for a model operating under a general harness.
Read the full abstract ▾
All authors Zongxia Li, Yucheng Shi, Zhongzhi Li, Junyao Yang, Ruhan Wang, Chengsong Huang, Fuxiao Liu, Haitao Mi, Jordan Boyd-Graber, LeoweiLiang
Computer Vision
TerrainForge: Physics-Grounded Road Geometry Editing for Counterfactual Autonomous Driving
Yang Chen, Yicheng Zhu, zhenning Li et al. (+2 more)
Road geometry (e.g., crests, sags, and speed humps) and surface conditions (e.g., wet or icy pavement) affect how vehicles move, what drivers and onboard cameras observe, and how much clearance remains between vehicles. Editing these properties in a driving scene therefore requires corresponding changes in vehicle motion. Capturing these differences in a driving
video requires a road edit to propagate to vehicle motion, camera viewpoint, and the clearance between vehicles. We present TerrainForge, a framework for generating road geometry-focused counterfactuals from reconstructed multi-vehicle driving episodes. A unified road model connects scene deformation with four-wheel vehicle dynamics, allowing crests, sags, speed humps, and friction changes to propagate through vehicle motion, camera viewpoint, and inter-vehicle clearance. Vehicle dynamics are evaluated against CarSim, and prescribed road geometry is verified in reconstructed Waymo scenes. Across 18 episodes, leaving surrounding vehicles on their recorded trajectories instead of recomputing their responses produces median peak differences in predicted ego-lead distance of 1.52 m for crests and 1.41 m for sags. We further simulate the ego response to 15,758 road edits across 983 braking episodes, pairing each edit with its safety outcomes relative to an unedited replay. These pairs train a first-stage screening surrogate that takes the original driving context and candidate road-edit parameters as input and predicts the resulting change in the ego's terminal gap. On held-out scenes, this prediction achieves 22-40% lower mean absolute error than predicting no change, so candidates can be screened cheaply before the full multi-vehicle rollout.
Read the full abstract ▾
All authors Yang Chen, Yicheng Zhu, zhenning Li, Tao Li, Zilin Bian
Artificial Intelligence
MetaRubric: Learning to Reward for Rubric-Based Reinforcement Learning
Yuxuan Fan and Jaehong Yoon
Rubric-based reinforcement learning extends reward-driven optimization to open-ended tasks by assigning partial credit to individual response requirements. However, rubric judges can assign a high criterion score even when the information or action it requires is absent from the response, a failure mode we term Vacuous Credit. Such awards persist after the required information is removed and can reverse the sign of a response's GRPO advantage. To address this problem, we introduce MetaRubric, which alternates evidence-aware policy optimization with response-guided rubric adaptation. We construct counterfactual counterparts by changing one task-relevant fact in each
prompt. During policy optimization, credit is assigned only when the response contains sufficient evidence to satisfy the required rubric criterion. After each policy-optimization stage, current policy responses guide revisions to original and counterfactual criteria while preserving the meaning of the original
prompt's initial rubric as interpreted under each
prompt's facts. We also adapt criterion weights at stage boundaries to better address observed policy errors. Across multiple backbones, MetaRubric improves PubMedQA accuracy by 6.00–20.40 percentage points over static-judge GRPO, with further gains on HealthBench-Hard and two
multimodal medical
benchmarks.
Read the full abstract ▾
Sound
What Actually Makes Correlation-Based SSL Distillation Noise-Robust? A Mechanistic Correction
Fabian Ritter-Gutierrez, Nancy F. Chen and Eng Siong Chng
Self-supervised learning (SSL)
speech models are accurate but large. Knowledge
distillation compresses them, but the student loses the teacher's noise robustness. Correlation-based
distillation addresses this with two terms: cross-correlation aligning student and teacher's representations, and self-correlation decorrelating the student's features. Both the original method and De'HuBERT credited the self-correlation term without isolating it. We show the opposite. On LibriSpeech-100
distillation with held-out CHiME-3 noise at 10\,dB, an unbiased full-dimensional probe, a Pearson-variance decomposition, a same-noise causal control, and a per-dimension analysis identify the cross-correlation diagonal as the mechanism that encourages noise invariance, lowering noise-classification accuracy from 76.98% to 55.02%, whereas adding the self-correlation term back leaves it at 55.55%. The self-correlation term instead reorganises the feature space and improves accuracy on the clean downstream tasks, but removes essentially no noise. Across nine
speech and music tasks this yields a concrete design rule for
distillation: weight the cross-correlation term for noise robustness, tune the self-correlation term for better downstream performance, and sample teacher and student noise independently.
Read the full abstract ▾
Machine Learning
Adaptive Spectral-Koopman Dynamics Modeling for Temporal Domain Generalization
Tengxue Zhang, Yu Ke, Yang Shu et al. (+4 more)
Temporal Domain Generalization (TDG) has emerged to address real-world streaming data with distribution shifts over time. However, existing methods are either prone to overfitting to domain-specific noise in the data space or become overly complex and less interpretable in the parameter space. To bridge these gaps, we propose AdaSpecK, a spectral-Koopman framework with adaptive context extraction for TDG. To mitigate noise fitting to irregularly sampled domains, we introduce spectral-regularized Koopman dynamics modeling, which applies spectral-aware filtering in the latent space to extract denoised low-frequency trajectories and learn a Koopman operator to model the system dynamics in a linearized space. To model complex historical environments under non-stationarity, we design a context-informed heterogeneous pattern extraction mechanism. Specifically, we employ a target-conditioned
attention module to attend to distinct past windows, producing a dynamic, target-specific historical summary. By constructing an environmental signature from the current evolutionary pattern, our model adaptively perceives which aspects of the past context are most informative for future prediction via a learned router. Extensive experiments on eight diverse classification and regression
benchmarks demonstrate that AdaSpecK achieves state-of-the-art performance. The code and
datasets are available at \href{}{https://anonymous.4open.science/r/Ada-Spec-K}.
Read the full abstract ▾
All authors Tengxue Zhang, Yu Ke, Yang Shu, Chenchen Sun, Yisheng An, Chenjuan Guo, Bin Yang
Optics
Fast Nanophotonic Inverse Design using Precomputed Numerical Green Functions
Thi Phuong Thao Nguyen, James Wang and Constantine Sideris
Inverse design has been transformative in nanophotonics, providing an automated means of realizing high-performance, non-intuitive devices. However, the primary bottleneck of existing inverse design approaches is their reliance on time-consuming and computationally expensive full-wave electromagnetic simulations. In this work, we extend the Precomputed Numerical Green Function (PNGF) method for the first time to nanophotonic inverse design, accelerating evaluation of the forward problem by multiple orders of magnitude with no loss in accuracy compared to the full-wave solution. After a single, fully parallelizable precomputation step, both the objective function and its gradient can be evaluated through simple calculations whose cost scales linearly with the size of the design region. A low-rank
matrix update technique further reduces the cost of objective function evaluation, yielding sub-millisecond computation times per iteration. Design examples using both gradient-based level-set optimization and tile-flipping direct binary search often achieve more than three orders of magnitude speedup in design time, resulting in an ultrafast photonic inverse design platform that can design new devices from scratch in seconds.
Read the full abstract ▾
High Energy Physics (Phenomenology)
Kinetic Equilibrium between SIMP Dark Matter and Radiation via Internal Bremsstrahlung
Xiaoyong Chu, Ajay Kaladharan and Yassine El Mohtadi
As an alternative to standard dark matter freeze-out via two-body annihilation, strongly interacting massive particles are proposed to regulate their relic abundance through three/four-body self-annihilation. During such freeze-out, dark matter must undergo both number reduction and energy dissipation. The former requires number-reducing processes, and the latter requires an efficient energy-dissipation mechanism. In this work, we propose a novel mechanism where internal Bremsstrahlung processes establish kinetic
equilibrium between dark matter and radiation, and thus dissipate energy. More appealingly, this mechanism can be naturally realized in a class of strong dynamics models with
flavor-universal
quarks and a light
axion. To demonstrate our results in a $Sp(4)_c$ dark-color model, we compute all relevant interaction terms and numerically solve the full Boltzmann equations. The same mechanism can also be applied to vector dark matter models.
Read the full abstract ▾
Computation and Language
Text-Centric Post-Training for Omni-Modal Reasoning
Ziyang Cheng, Yuhao Wang, Hongcheng Liu et al. (+5 more)
Improving joint audio-visual
reasoning in Omni Large
Language Models typically incurs substantial data construction and training costs. Our diagnostics reveal multi-hop
reasoning difficulties despite correct answers to all corresponding single-hop questions and suggest partial decoupling in the local optimization of perception and
reasoning objectives. This motivates post-training with different emphases on these capabilities. Text-only
reasoning training yields gains across data sources, model scales, and families. With the best-performing text-only configuration, supervised fine-tuning followed by reinforcement learning (RL) raises Qwen2.5-Omni-7B's
geometric mean of nine
reasoning scores by 25.83% over the base model, outperforming the complete native audio-visual route with 56.6% fewer GPU-hours. Training on data synthesized entirely by a text-only LLM raises this
geometric mean by 21.01% without audio-visual data in construction or training. However, text-only training degrades perception. We therefore propose a text-centric post-training paradigm: text-only training provides the main
reasoning optimization, and reduced-data native audio-visual RL then refines perception. Refinement uses about 90% fewer input
tokens than full-data audio-visual RL, restores perception above the base level, and retains 93.5% of the best-performing text-only pipeline's
reasoning gain.
Read the full abstract ▾
All authors Ziyang Cheng, Yuhao Wang, Hongcheng Liu, Qimin Wu, Jingru Fan, Chen Qian, Yanfeng Wang, Yu Wang
Mesoscale and Nanoscale Physics
Extracting the anyon charge from shot noise in complex fractional quantum Hall edges
Jinhong Park and Christian Spånslätt
Shot-noise measurements with a
quantum point contact provide a direct probe of the quasiparticle charge in Laughlin fractional
quantum Hall (FQH) states. However, the interpretation of such measurements becomes more subtle for multichannel edges, where the point-contact tunneling noise coexists with noise generated by intermode equilibration and heating. We develop a general framework that incorporates both these contributions and apply it to the paradigmatic $\nu=2/3$ FQH edge. We derive expressions for the drain auto- and cross-correlations in a four-terminal QPC geometry and show that equilibration-induced heating affects the auto- and cross-correlations in parametrically different way than the intrinsic partition noise. This distinction permits us to propose a specific combination of the two correlations which strongly suppresses the heating contribution and fully recovers the tunneling quasiparticle charge. Our results thereby provide a systematic framework for interpreting shot-noise measurements in complex FQH edges and can be further extended to more general counterpropagating edge structures.
Read the full abstract ▾
Cryptography and Security
RMCW: A Deletion-Robust Watermark Based on Reed–Muller Codes for Language Models
Yi Wang, Baicheng Chen, Yu Wang et al. (+3 more)
Large
Language Model (LLM) watermarking provides a lightweight mechanism for identifying text generated by a specific model, but its robustness remains fragile under post-processing attacks. Deletion attacks are particularly challenging because they shift
token positions and break the
alignment between observed
tokens and their original watermark positions. We propose Reed–Muller Code Watermarking (RMCW), an LLM watermarking method based on Reed–Muller codes. In contrast to global codeword recovery, RMCW searches for surviving local algebraic structure, leveraging the Reed–Solomon consistency induced by affine-line restrictions of Reed–Muller codewords. During generation, RMCW injects a Reed–Muller structure into the sequence via a secret-keyed vocabulary partition. During detection, it maps the given text to keyed vocabulary bins and tests local subsequences for low-degree Reed–Solomon consistency using Berlekamp–Welch tests. Experiments on C4 and ELI5
datasets with OPT-1.3B and Llama-3.1-8B-Instruct show that RMCW preserves strong clean-text detectability and outperforms or matches the baseline methods under several deletion and rewriting attacks. Our code is available at https://github.com/BaichengDanny/RMCW.
Read the full abstract ▾
All authors Yi Wang, Baicheng Chen, Yu Wang, Jian Zhao, Yilei Chen, Tianxing He
Machine Learning
Gated Slot Attention-2: Two-Sided Associative Memory Correction in Linear Attention
Ruijie Li, Shengnan Ding, Weimin Zhang et al. (+6 more)
Linear
attention models have emerged as efficient alternatives to standard
attention, but effectively managing their fixed-size recurrent
memory remains challenging. To improve
memory, recent work has explored two distinct directions: delta-rule variants for precise correction of values associated with keys, and slot-based architectures such as Gated Slot
Attention for modeling key and value
memories in two stages. We observe that these directions are complementary–the delta rule provides effective
memory correction, while the two-stage structure provides a natural way to operate on both sides of an association. Building on this insight, we introduce a new Gated Oja Rule for key-side correction and extend it with decoupled erase and write control to obtain Gated Oja Rule-2. We then introduce Gated Slot
Attention-2 (GSA2), which combines Gated Oja Rule-2 for key-side correction with Gated Delta Rule-2 for value-side correction through shared latent slots. We further derive a hardware-efficient chunkwise
algorithm for parallel training. Experiments demonstrate that GSA2 consistently improves over strong linear-
attention baselines across
benchmarks while retaining linear-time sequence modeling and constant-
memory recurrent decoding.
Read the full abstract ▾
All authors Ruijie Li, Shengnan Ding, Weimin Zhang, Derick Tang, Zhanpeng Zeng, Qinsong Zeng, Ming Chen, Jiaxi Hu, Yuxuan Liang
Artificial Intelligence
iS-KV: Online Low-Rank KV Cache Compression via Block-Incremental SVD
Yiren Zhao, Guanghui Song, Tianrui Qin et al. (+3 more)
Long chain-of-thought
reasoning substantially increases KV-cache
memory during autoregressive decoding, as every generated
token introduces new key and value states and causes the cache to grow linearly with decoding length. Existing KV-cache compression methods typically control this growth through
token eviction, but irreversible deletion can remove historical states that later
reasoning may need to revisit. SVD-based low-rank compression provides an alternative by retaining all positions with a more compact representation. However, extending it from a fixed
prompt cache to online decoding is non-trivial. Through our investigation, we find that if the basis is updated for new
tokens while old
tokens keep their coordinates in the old basis, the stored history drifts substantially. Based on this observation, we propose iS-KV, an online low-rank KV-cache compression method for long-horizon
reasoning. iS-KV keeps a recent window exact while incrementally folding older states into bounded-rank representations. As the low-rank basis evolves, it synchronizes historical coordinates with the updated basis to maintain representation consistency. On DeepSeek-R1-Distill-Llama-8B, iS-KV achieves 82.6% accuracy at 4.06-fold persistent-KV compression, close to the original model's 83.6%. On Qwen3-8B, it achieves 89.2% accuracy at 5.64-fold compression. Under matched
memory budgets, iS-KV consistently outperforms
token-eviction baselines.
Read the full abstract ▾
All authors Yiren Zhao, Guanghui Song, Tianrui Qin, Kejiang Ye, Cheng-zhong Xu, Xitong Gao
Software Engineering
VeriPy Source-Preserving Verification and Compatibility Checking for Python Components
Naing Oo Lwin
Keeping a Python program and its formal guarantees aligned is a continuing maintenance problem. Specifications must describe the implementation that actually runs, and updates must preserve the behavior on which existing callers depend. VeriPy brings these obligations into a common workflow for annotated Python components. Developers and
agents express contracts, invariants, and proof hooks as Python comments, then refine checked auxiliary lemmas using source-located diagnostics. Direct encoders produce Dafny or Lean artifacts while retaining admitted executable bodies and explicit models of their dependencies. A relational product checks whether an updated component still admits old inputs and preserves returned values and modeled exceptions. The resulting workflow connects source-level proof development with functional verification and backward compatibility, recording the assumptions under which each guarantee applies. The code is available at https://github.com/astrio-labs/veripy.
Read the full abstract ▾
Robotics
Register-Routed Delayed Fusion: Rewiring Shortcut-Prone Observation Fusion in Visuomotor Imitation
Jieting Long, Weidong Cai and Weiming Zhi
Visuomotor imitation policies combine high-dimensional visual observations with compact signals such as proprioception, and their fusion
topology determines when and through which
tokens these streams interact. In dense
token fusion, visual
tokens may attend directly to compact
tokens from the first encoder layer, allowing action-predictive compact cues to influence spatial visual representations early in their formation. We ask whether controlling this route improves visual responsiveness and policy behavior. We introduce Register-Routed Delayed Fusion (RRDF), which masks direct compact-visual
attention and stages cross-modal interaction through a learned register workspace. Its isolate-collect-route schedule protects an early stream-separated prefix and later permits only register-mediated exchange, while compact conditioning remains available to the native action generator. Across five simulation tasks and three real-
robot tasks, RRDF matches or improves dense ACT under nominal conditions. Appearance-shift evaluations on four simulation tasks and held-out-position evaluations on three real-
robot tasks also favor RRDF. Phase-matched input probes show lower measured state-to-image sensitivity, while ablations indicate that adding registers alone does not reproduce the full performance gain. These results support controlling cross-modal propagation while retaining compact action conditioning.
Read the full abstract ▾
Human-Computer Interaction
Co-Designing AI For Mental Health Support With Young Adults of Color (YOC): Needs, Expectations, and Implications for AI Literacy
Elaine Dabin Jeon, John Bosco S. Bunyi, Hannah Kim et al. (+7 more)
Young adults of color (YOC) face heightened mental health challenges and barriers to care while navigating developmental and life transitions. Situated between youth-oriented safeguards and adult-oriented AI systems, little is known about how they use AI chatbots for mental health and well-being support or how sociocultural contexts shape their expectations, concerns, and design preferences. We conducted a two-day co-design workshop with 13 Asian, Black, and Hispanic/Latino/a young adults aged 18–24. Participants found generic chatbot advice to flatten their lived experiences; rather than making incorrect assumptions, they wanted more opportunities for identity-informed disclosure. Preferences for YOC-centered personalization also revealed gaps in
privacy and AI literacy. Participants negotiated different therapeutic roles for chatbots and sought greater AI accountability and user agency, highlighting blurred boundaries between clinical and non-clinical AI-mediated support. Findings suggest directions for integrating AI literacy with mental health literacy and centering YOC's experiences in the
privacy calculus.
Read the full abstract ▾
All authors Elaine Dabin Jeon, John Bosco S. Bunyi, Hannah Kim, Renkai Ma, Yaman Yu, Michal Luria, Jason Yip, Alexis Hiniker, Katie Davis, Angel Hsing-Chi Hwang
Robotics
Learning Reflexive Behavior for Contact-Rich Manipulation
Quan Nguyen, Yunho Kim and Joonho Lee
During contact-rich manipulation, interactions between a
robot and its environment carry information about local geometry: a surface prevents penetration, a bore guides a peg. A controller that exploits these interactions can comply with environmental constraints while preserving task intent.
Robot-earning systems commonly use position, hybrid force-position, or Cartesian impedance control. Their prescribed tracking objectives, stiffness, or force-control directions may not match local constraints and may degrade performance. We learn a proprioceptive reflex policy in simulation on three simple interaction primitives: a spring, a plane, and a rail. The policy maps task-space commands to joint-position targets using state history, without direct force or geometrical measurements. Once trained, it serves as a frozen execution layer beneath higher-level controllers. We evaluate it in dual-arm box lifting, peg insertion, and surface following. In box lifting, the reflex kept the force below the threshold while the baseline failed. In rough-surface following it stayed below the 10 N reference, on par with tuned hybrid force-position control. In 0.02 mm peg insertion It reduced mean estimated contact force to less than half that of the baseline while increasing hardware success rates from at most 22 % to 36-58 %. By separating contact response from command generation, the reflex policy provides motion planners, learned policies, and teleoperators with robust contact-rich execution.
Read the full abstract ▾
Analysis of PDEs
Boundedness of Solutions to Nonlocal Systems
Serena Dipierro, João Gonçalves da Silva, Giorgio Poggesi et al. (+1 more)
Under mild mass or energy assumptions, we prove uniform $L^\infty$ bounds for all distributional solutions of a multi-dimensional system of nonlocal semilinear equations. The setting comprises Ginzburg-Landau systems and Allen-Cahn equations, and the results obtained are new even for scalar equations.
Read the full abstract ▾
All authors Serena Dipierro, João Gonçalves da Silva, Giorgio Poggesi, Enrico Valdinoci
Probability
New Bounds for the Euclidean TSP Constant
Zhuolun Dong and Junyu Cao
The Beardwood-Halton-Hammersley
theorem characterizes the asymptotic length of the optimal Euclidean traveling salesman tour through independent and uniformly distributed random points $X_1,\ldots,X_n$ in the unit square. It states that there exists a universal constant $\beta$ such that the length of the shortest tour is asymptotic to $\beta \sqrt{n}$ almost surely. The best bounds established to date are $0.6277\leq \beta \leq 0.90367$. In this paper, we improve these bounds to $0.6421\leq\beta\leq0.8810$. Using importance sampling, we further show that $0.6536\leq \beta\leq 0.8749$ holds with probability at least $1-2\times 10^{-4}$. Here the probability is taken with respect to the randomness of the sampling procedure.
Read the full abstract ▾
Artificial Intelligence
ROUTEAUDIT: Interaction-Aware Identification for Budgeted Multi-Verifier Routing
Miaobo Hu, Shuhao Hu, Xiaobo Guo et al. (+4 more)
Adaptive multi-verifier systems are commonly compared through endpoint quality-cost gaps, even when the verifier catalog, availability, accounting, information filtration, or scorer changes with the policy. We formulate verifier routing as a contract-conditioned identification problem. The contract records request support, verifier catalog, realized availability, resource accounting, online filtration, and post-trace scoring; a matched route contrast changes only the policy coordinate. ROUTEAUDIT adds three measurable objects to this contract. A contract
lattice averages coordinate increments over every admissible bridge order and reports the resulting attribution together with its path sensitivity. A policy-independent response tape identifies paired sequential contrasts when adaptive policies reveal different observations. For incomplete matching, request-level bounds use whichever potential outcome remains observed and give a sharp finite-population interval. The protocol commits paid observations and ledger events before the oracle join and returns an attribution certificate for each comparison. On two held-out raw-tail caches, matched static SF+SA equals the cascade, assigning the apparent gains of 0.1797 and 0.1250 over full static to the verifier-set edge. On 1,319 held-out task requests, the learned and RLVR studies report quality 0.9522 and 0.9553 versus 0.9484 for matched static; the RLVR-static paired difference is +0.0068 with a request-paired interval $[0.0015,0.0122]$ and a training-seed-by-request hierarchical interval $[0.0006,0.0131]$. Controlled attribution recovery yields route mean absolute error 0.0011 and endpoint reconstruction error 0.0004. Factorial, bridge-order, and
stochastic-provider studies evaluate the certificate interface; RLVR supplies a learned-policy stress test under the same identification contract.
Read the full abstract ▾
All authors Miaobo Hu, Shuhao Hu, Xiaobo Guo, Xin Wang, Bokun Wang, Tianshu Fu, Daren Zha
Algebraic Geometry
Categorical Dynamics of Abelian Varieties
Yu-Wei Fan
We establish several general results on the categorical dynamics of abelian varieties. (1) We prove the exponential and
polynomial Gromov–Yomdin equalities for every autoequivalence of the derived category of an arbitrary abelian variety. The exponential equality extends earlier results of Kikuta for
elliptic curves and of Yoshioka for abelian surfaces and simple abelian varieties. (2) We prove the categorical
polynomial entropy of every autoequivalence is bounded above by $g^2$, where $g$ is the dimension of the abelian variety. This gives a categorical generalization of the
polynomial log-volume growth of Lin–Oguiso–Zhang and recovers their upper bound as a direct consequence. (3) We identify the shifting number of every autoequivalence of an abelian variety with the pullback of the normalized Barge–Ghys
symplectic translation number on the universal cover of $\text{Sp}(4g,\mathbb{R})$. (4) We prove that the set of reduced shifting numbers is finite if and only if the nef cone is rational polyhedral. Moreover, when this set is infinite, there exists an autoequivalence with transcendental shifting number. In particular, this gives a negative answer to a question of Dimitrov–Haiden–Katzarkov–Kontsevich concerning the algebraicity of categorical
entropy functions.
Read the full abstract ▾
Number Theory
The Wang–Sun Sum over Affine Derangements
Octavio A. Agustín Aquino
Let $n$ be even, let $\zeta$ be a primitive $n$-th root of unity, and let $\Delta_n$ be the set of derangements in the affine group $\overrightarrow{GL}(\mathbb{Z}/n\mathbb{Z})$. We evaluate the Wang–Sun type sum \[ S_n=\sum_{\pi\in\Delta_n}\mathrm{sign}(\pi) \prod_{x\in\mathbb{Z}/n\mathbb{Z}} \frac{1+\zeta^{x-\pi(x)}}{1-\zeta^{x-\pi(x)}}. \] The main step is an arithmetic grouping: for an affine map $\pi(x)=vx+u$, the product depends only on $\sigma=\gcd(1-v,n)$ and on the residue class of $u$ modulo $\sigma$. After summing the translation signs, the full sum becomes a sum over even divisors with explicit local multiplicities. The only remaining analytic blocks are alternating even cotangent power sums; a recent formula of Liu and Xin then gives a closed expression in Bernoulli
polynomials and universal coefficients. Moreover, using results by Cvijović and Klinowski we can evaluate the cotangent power sums using exclusively rational arithmetic. This supplies a general formula for the full affine sum whose initial values were computed using the definition only in an earlier work. The formula also lets us prove some general patterns of the sum: it has integral value for powers of $2$,
prime denominator for $2p$ for
primes $p>3$ and it has alternating signs.
Read the full abstract ▾
Cryptography and Security
From TS-SUF-2 to TS-SUF-4: Practical Security Enhancements for FROST2 Threshold Signatures
Will Wang, Syh-Yuan Tan, Ryan Chow et al. (+2 more)
Threshold signature schemes play a vital role in securing digital assets within blockchain and distributed systems. FROST2 stands out as a practical threshold Schnorr signature scheme, noted for its efficiency and compatibility with standard verification processes. However, under the one-more discrete logarithm assumption, with static corruption and centralized key generation settings, FROST2 has been shown by Bellare et al. (in CRYPTO 2022) to achieve only TS-SUF-2 security, which is a consequence of its vulnerability to TS-UF-3 attacks. In this paper, we address this security limitation by presenting an enhanced variant of FROST2, namely, FROST2+ which achieves the TS-SUF-4 security level under the same computational assumptions as the original FROST2. FROST2+ strengthens FROST2 by integrating additional pre-processing
token verifications that help mitigate TS-UF-3 and TS-UF-4 vulnerabilities while maintaining practical efficiency. We show that FROST2+ can achieve TS-SUF-4 security not only under the same conditions as the original FROST2 analysis, but also when initialized with a distributed key generation protocol such as PedPoP. Our
benchmark using ZCash's FROST library shows that the performance of FROST2+ is comparable to FROST2 and about 64-79% faster than FROST when precomputation is enabled.
Read the full abstract ▾
All authors Will Wang, Syh-Yuan Tan, Ryan Chow, Chanson Chan, Martin Zhao
Robotics
SARI: Phase-Split Sim-Real Co-Training for Contact-Rich Manipulation
Xingxin He, Yuxuan Jiang, Haonan Zhang et al. (+5 more)
Vision-
language-action (VLA) models often require costly real-world demonstrations to adapt to contact-rich manipulation tasks, particularly when generalization across object placements is needed. We propose SARI (Simulated Approach, Real Interaction), a phase-split sim-and-real co-training framework built on a simple insight: spatial coverage and contact physics should be acquired from the domains best suited to them. Specifically, free-space approaches require spatial diversity but tolerate modest simulation gaps, making them ideal for synthetic generation; conversely, contact interactions demand accurate physics but vary little across object placements, allowing a few real demonstrations to generalize across the workspace. SARI generates diverse simulated approaches in a photorealistic digital twin while collecting real contact interactions at only a few placements. Post-trained on these phase-segmented demonstrations, a single policy seamlessly stitches simulated approaches with real contact interactions using visual appearance
alignment and a shared camera-relative action representation–without explicit phase labels or hand-coded switches. Across five real-world contact-rich manipulation tasks, SARI reduces real-data collection time by 34.3% and achieves 27.5% success at unseen placements, where all full-task sim-real baselines fail completely (0%).
Read the full abstract ▾
All authors Xingxin He, Yuxuan Jiang, Haonan Zhang, Chuhan Cui, Kaile Li, Zhongxing Zheng, Caihao Xu, Ziqi Wang
Robotics
LOCUS: Landmark-Oriented Container Discrimination Using Spatial Graphs
Taylor Bergeron, Shibani Senthilbabu and Kevin Leahy
As
robots are increasingly deployed in unstructured, real-world environments, the ability to reason about complex spatial and semantic relationships among objects remains a fundamental challenge in enabling robust and generalizable manipulation and
navigation. For example, deciding where to search for an object that is not in plain sight depends on where it is physically plausible as well as semantically likely. Popular methods such as cosine similarity with CLIP struggle to disambiguate between spatially and semantically similar objects that could contain a target object. We propose Landmark-Oriented Container Discrimination Using Spatial Graphs (LOCUS). To jointly reason about spatial information and semantics, we train a GNN to update CLIP
embeddings on a full environment scene graph by passing
embedding information between nodes based on proximity. CLIP
embeddings, augmented by semantic knowledge from a fusion of household ontologies provide a robust semantic signal. We evaluate in simulation on a noiseless scene graph from simulator metadata, making the approach detection-agnostic. Our approach outperforms random, CLIP, Tidybot, and an LLM planner in the majority of room classes and configurations in simulation. To show our approach is robust to scene graph node placement and label noise, we demonstrate a physical mobile manipulator running in an exploration pipeline start-to-finish including scene graph labels from Detic.
Read the full abstract ▾
Robotics
ManiPhysicsBench: Physics-Based Assessment of Object Preservation in VLA Manipulation
Sangwu Park, Yeonjun In, Wonjoong Kim et al. (+3 more)
Vision-
language-action (VLA) models aim to perform diverse manipulation tasks, but task success in existing rigid-body
benchmarks does not indicate whether they preserve objects. We introduce ManiPhysicsZoo, which consolidates literature-supported material properties, 3D meshes, and supporting references into reusable object assets. Using these assets, a solver-based assessment computes grasp-specific damage thresholds from object geometry, material properties, and recorded grasp conditions and compares them with recorded contact forces to assess potential deformation and fracture. Building on these components, ManiPhysicsBench evaluates object preservation in LIBERO and SimplerEnv across three physics axes and three difficulty levels. Public VLA checkpoints show a substantial gap between task success and safe success, defined as task completion while preserving the object. Their gripper commands concentrate near full opening and closure, with largely similar aggregate distributions across objects, consistent with binary gripper supervision. We examine how object-specific continuous gripper labels change model behavior by retraining a VLA model. The retrained model shows more object-dependent gripping and higher safe success, but lower task success and limited generalization of object-preserving behavior.
Read the full abstract ▾
All authors Sangwu Park, Yeonjun In, Wonjoong Kim, Sungwon Kim, Sein Kim, Chanyoung Park
Artificial Intelligence
VIGOR: Zero-Shot Visual Generalization via Latent-Space Consistency in Model-Based Reinforcement Learning
Mingyu Park, Samyeul Noh, Hyun Myung et al. (+1 more)
Model-based reinforcement learning (MBRL) achieves strong sample efficiency by planning within learned latent dynamics, yet its performance degrades substantially under unseen visual distractions such as background variations, lighting changes, or camera shifts. Unlike model-free RL, where encoder perturbations affect only single-step predictions, MBRL suffers from a two-level vulnerability: visual distractions first push encoder outputs out of distribution, and these errors then compound through recursive latent rollouts over the planning horizon. We propose visual generalization via latent-space consistency in model-based RL (VIGOR), a framework that enables zero-shot generalization to unseen visual distractions while retaining the sample efficiency of its MBRL backbone. VIGOR integrates three interdependent components: (i) asymmetric weak-to-strong augmentation, which pairs weak-only and weak-to-strong latent views within a single batch; (ii) dynamics-level consistency, which enforces augmentation-invariant transition predictions through direct latent regression; and (iii) encoder-level stabilization, which prevents encoder drift under the cross-augmentation supervision imposed by dynamics-level consistency. Evaluations on the DeepMind Control Suite (DMC) and Robosuite show that VIGOR outperforms state-of-the-art model-free and model-based baselines, surpassing the second-best baseline by 3.4% on DMC and 43.6% on Robosuite. Ablations further show that VIGOR's robustness is augmentation-agnostic: replacing the default augmentation with alternatives from distinct perturbation families preserves strong generalization, confirming that latent-space consistency, not the augmentation choice, drives robustness.
Read the full abstract ▾
All authors Mingyu Park, Samyeul Noh, Hyun Myung, Donghwan Lee
Artificial Intelligence
BitNest: Bit-Nested Speculative Decoding for Memory-Efficient LLM Inference Acceleration
Chence Yang, Ningxi Cheng, Arash Akbari et al. (+9 more)
Speculative decoding accelerates autoregressive generation by using a lightweight draft to propose multiple
tokens for parallel verification. However, existing methods often require an additional draft model or weight representation, introducing non-negligible
memory overhead on resource-constrained devices. Self-speculative approaches reduce this overhead, yet still face trade-offs between draft quality, target quality, and storage efficiency. We propose BitNest, a bit-nested speculative decoding framework that embeds a low-precision draft directly into the higher-precision target representation. Instead of deriving a draft from a predefined target, BitNest first constructs a strong low-precision base and then recovers the higher-precision target through residual refinement, enabling both models to share a single physical weight representation. BitNest further extends this progressive-precision design to the KV cache for long-context inference. Across multiple 7B–8B edge-friendly LLMs and diverse workloads, BitNest achieves an average speculative acceptance rate of 95.2% while closely preserving higher-precision model quality, and delivers 1.48–1.61x end-to-end speedup over FP16 autoregressive decoding. On the LLaMA models supported by all representative self-speculative baselines, BitNest also achieves consistently competitive or higher decoding speedup.
Read the full abstract ▾
All authors Chence Yang, Ningxi Cheng, Arash Akbari, Qitao Tan, Qingchan Zhu, Ci Zhang, Changdi Yang, Yanzhi Wang, Wei Niu, Jinhui Wang, Jin Lu, Geng Yuan
Computer Vision
FUSEye: Training-Light Fisheye Detection with Overlapping Views and Zero-Initialized Adapters
Wenya Su, Kai Luo, Di Wen et al. (+5 more)
Fisheye cameras give mobile
robots a single-sensor, low-cost view of their surroundings, yet the COCO-pretrained detectors that practitioners routinely reuse fail on them: strong radial distortion warps local image structure, while boundary compression shrinks objects to near-invisible sizes. Full fine-tuning closes much of the gap but requires abundant fisheye labels and compute. We present FUSEye, a training-light framework that turns a frozen-backbone COCO-pretrained extra-large YOLO26 detector (YOLO26-x) into a fisheye detector. FUSEye adds roughly 227k new parameters while updating the inserted modules and the pretrained detection head. It addresses the transfer gap at three causally linked levels. At the input level, overlapping grid view generation and box remapping (GridViews) enlarge compressed boundary regions. At the feature level, zero-initialized residual adapters (Z-Adapters) correct distortion-induced feature misalignment. At the decision level, learned cross-projection agreement fusion (AgreeFusion) promotes low-confidence detections only when they are supported by consistent evidence across multiple views. On the WoodScape surround-view fisheye
benchmark, FUSEye raises YOLO26-x from 0.148 to 0.266 mAP50 and retains 84.3% fully fine-tuned accuracy. Moreover, randomly using only 25% of the labeled training images, FUSEye achieves 0.2597 mAP50, retaining 97.6% of its full-label performance. FUSEye also consistently improves YOLOv8-11 detectors, showing that the recipe is architecture-agnostic. Source code will be available at https://github.com/Su-wenya/FUSEye.
Read the full abstract ▾
All authors Wenya Su, Kai Luo, Di Wen, Ruiping Liu, Yufan Chen, Junwei Zheng, Kunyu Peng, Kailun Yang
Machine Learning
Muon Learns Facts Better: Understanding the Role of Spectral Orthogonalization
Xuheng Li, Qiwei Di, Yuan Cao et al. (+1 more)
The
Muon optimizer applies spectral orthogonalization to
matrix-valued updates and has shown strong performance in large-scale neural network training, yet the mechanisms of this transformation in feature learning remain poorly understood. In this work, we investigate this question through a tractable factual-recall model, where a fact maps each subject-relation pair to an answer, and a linear
transformer learns the subject- and relation-dependent information required to recover this mapping. The
transformer is optimized with gradient flow (GF), spectral GF, or Sign GF, which are continuous-time limits of gradient descent,
Muon, and Adam, respectively. Prior studies (Nichani et al., 2025) have shown that when the number of subjects exceeds the number of relations, GF learns relation-dependent information before subject-dependent information, producing a feature-separation phase during training. We characterize this separation with the learning times when the subject- and relation-dependent components of the prediction reach a target accuracy. With $S$ subjects and $R$ relations, GF has a learning-time ratio of $\widetilde{\Theta}(\sqrt{S/R})$, whereas Spectral GF reduces this ratio to $\widetilde{\Theta}(1)$. In addition, for fixed $S$ and $R$, the subject- and relation-dependent errors decay as $1/(T\log T)$ in training time $T$ under GF, but as $\exp(-\mathrm{poly}(T))$ under spectral GF. Finally, we show that GF and spectral GF are equivariant under orthogonal transformations of the
token embeddings, whereas Sign GF is not: Different orthonormal
embeddings can potentially produce no feature separation, a large feature-separation phase, or even a reversed learning order. These results provide a mechanistic view of how spectral orthogonalization can fundamentally reshape feature-learning dynamics.
Read the full abstract ▾
All authors Xuheng Li, Qiwei Di, Yuan Cao, Quanquan Gu