Graphics
HoOPOE: A Holography-Optimized Perceptual ObjectivE function
Ethan Chen, Xi Peng, Alexandre Chapiro et al. (+6 more)
Holographic devices must reconstruct an entire light field given a finite number of spatial light modulator (SLM) pixels, and must do so using scalar-wave diffraction from coherent illumination alone. As a result, computer-generated holography (CGH) often has speckling artifacts. We propose HoOPOE (Holography-Optimized Perceptual ObjectivE function), a CGH-specific, perceptually-aware loss function that hides speckles from human
vision. HoOPOE is effective for CGH optimizations because it accounts for the human visual system's sensitivity to spatio-temporal frequencies and color, and its parameters are tuned to maximize its performance as a loss function for CGH. We use HoOPOE to generate holograms for mesh-derived focal stacks. We then conduct a user study to
benchmark HoOPOE-generated holograms against existing loss functions. HoOPOE yields the most visually pleasing results; users prefer HoOPOE 68% of the time over the next best objective function on average.
Read the full abstract ▾
All authors Ethan Chen, Xi Peng, Alexandre Chapiro, Dario Seyb, Michael Grundmann, Carl Marshall, Sushant Kondguli, Praneeth Chakravarthula, Yuhao Zhu
Artificial Intelligence
REA: From Correct LLM Judgments to Safe Decision Delivery
Jingxiang Meng, Aofan Liu, Yaoshuai Ma et al. (+2 more)
Generative safety guards must classify requests correctly and return outputs that applications can parse.
Reasoning guards can improve classification accuracy while producing outputs that applications cannot parse. When applications cannot extract a correct prediction, fallback handling can allow harmful requests or block safe ones. We introduce Resolve–Express–Act (REA), a framework that traces judgments through parsing and fallback to application actions. Experiments on classifiers and safety guards show that correct predictions can appear in incorrectly formatted outputs. Parsing the safety verdict preserves the
reasoning guard's accuracy advantage, while stricter explanation requirements reject additional correct predictions. Accepting formatting variations recovers most rejected correct predictions. Held-out tests confirm that output requirements and generation limits affect whether correct predictions can be parsed. In our fail-open replay, matching the parser to the output and fixing formatting reduced the fraction of harmful requests allowed despite correct guard judgments from 95.5% to 0%. A fixed-output comparison shows that model-based extraction can preserve guard verdicts, but is not automatically reliable; deterministic normalization already repairs the observed native-format failures. Fallback replay shows that the same correct prediction can lead to different safety actions depending on the parser and fallback policy, including allowing requests the guard correctly identifies as harmful.
Read the full abstract ▾
All authors Jingxiang Meng, Aofan Liu, Yaoshuai Ma, Fangxin Liu, Yongbiao Chen
Multiagent Systems
Scaling Inference-Time Compute with Teams of Coding Agents
Keenan Samway, Daniel D'souza, Omar Darwiche Domingues et al. (+3 more)
Multi-
agent systems promise a new axis for scaling inference: rather than having one
agent think longer or sample more attempts, a task is split across many
agents that work in parallel and coordinate. However, in practice, more
agents can easily produce duplicate work, coordination failures, and higher costs. We therefore formulate team design as a compute allocation problem: starting from a solo
agent, where should additional inference compute go to reach the reward-cost Pareto frontier? We build a minimal multi-
agent harness from the ground up and trace this frontier by varying, one at a time, the workflow stage at which a lead delegates to its workers (planning, implementation, or verification), the models that form the team, and the number of workers. On ProgramBench, teams outperform solo
agents but cost three to seven times as much. With the right compute allocation, however, a heterogeneous 17-
agent team comes within 1.4 points of a strong homogeneous 5-
agent team at 70% lower cost. This efficiency stems from three findings. First, planning is the most valuable use of workers: in a homogeneous team whose lead decides how many workers to spawn, a lead that delegates only planning to its workers, and then implements and verifies the code itself, matches the reward of a lead that delegates to workers throughout planning, implementation, and verification, at half the cost. Second, cheap models pay off as planners but not as implementers: a strong lead with cheap planners recovers 47.5% of the reward gain of an all-strong team for only 13.9% of its additional cost, whereas cheap implementers lower reward. Third, planners keep improving reward as the team grows, whereas implementers and verifiers plateau beyond four workers. Together, our results offer a guide to spending an
agent budget where it counts, given the task, cost, and latency constraints a user has.
Read the full abstract ▾
All authors Keenan Samway, Daniel D'souza, Omar Darwiche Domingues, Marzieh Fadaee, Tan Yi-Chern, Nouha Dziri
Machine Learning
Assessing the Performance of AI Models in Misinformation Detection Using Predefined Social Noise Constructs
Manar Alsaid
Social media platforms generate vast volumes of user-generated content that often obscure meaningful discourse, a phenomenon conceptualized as social noise. While existing misinformation detection methods primarily focus on factual verification, they largely overlook the role of social noise in amplifying misinformation. This study assesses the performance of six text-based models and a graph neural network (GNN) in mitigating the effects of misinformation using predefined social noise constructs. The
dataset consists of 500,000 tweets collected from the X platform using the Ukraine hashtag during the Russia-Ukraine conflict from March 2024 to March 2025. Advanced machine learning models achieve strong performance, with accuracies ranging from 79.94% to 97.17%. RoBERTa demonstrates the highest performance, with an accuracy of 97.17%, Cohen's kappa of 0.9660, MCC of 0.9660, and AUC of 0.9977. The GNN achieves an accuracy of 64.52% and an AUC of 0.899, demonstrating performance above random-chance classification by exploiting the relational structure between tweets. All text-based models achieve kappa values greater than 0.75, indicating substantial overall agreement. Explainable AI analysis using LIME reveals that 89.6% of predictive weight is attributed to contextual features rather than isolated keywords. The findings highlight that integrating social noise into AI pipelines enhances misinformation detection and supports more effective mitigation strategies in large-scale social media environments.
Read the full abstract ▾
Robotics
From Orbit Matching to Docking: A Hierarchical Reinforcement-Learning Approach to Multiphase Rendezvous Trajectory Design
Mariko Storey-Matsutani, Anatoly Zlotnik, Lee Holguin et al. (+2 more)
As the complexity of space missions increases, autonomous spacecraft guidance must accommodate transitions between mission phases with distinct dynamics, objectives, and constraints. Rendezvous and proximity operations (RPO) are particularly challenging because they span multiple operating regimes, from orbital-scale matching and far-range approach to close-range maneuvering and terminal docking. Existing reinforcement-learning approaches generally address only a subset of this sequence or rely on manually defined switching conditions between controllers. This study presents a hierarchical reinforcement-learning framework for autonomous, three-degree-of-freedom RPO that spans the complete trajectory from orbit matching to docking. Five specialized policies are trained for orbit matching, far-range approach, mid-range approach, close-range approach, and docking. A learned high-level manager policy then selects among these phase-specific controllers based on the evolving spacecraft state. The hierarchical approach is evaluated over the full end-to-end rendezvous sequence and compared with a fixed sequential-invocation heuristic to assess trajectory performance and transition behavior. Training and inference metrics are also analyzed for the individual phase policies and the complete hierarchical system.
Read the full abstract ▾
All authors Mariko Storey-Matsutani, Anatoly Zlotnik, Lee Holguin, Zigfried Hampel-Arias, Richard Linares
Information Retrieval
Computed, not Memorized: Bit-Factorized Identifiers for Efficient Generative Retrieval
I-Fan Lin, Zhen Zhang, Faegheh Hasibi et al. (+1 more)
Generative
retrieval is known for its efficient end-to-end indexing and
retrieval. In particular, numeric Document Identifiers (DocIDs) are generally more efficient because they are shorter and generally fixed-length sequences over a small vocabulary, requiring fewer decoding steps during beam search. However, they tend to generalize poorly to unseen documents and must be learned during indexing-stage training. In this paper, we propose a numeric DocID design for generative
retrieval that enables better adaptation to unseen documents without retraining. Our DocID design inherits the
language model's knowledge: each DocID is a sequence of
tokens factorized into bits, and each
token is scored as the sum of its bits. Unlike existing numeric DocIDs, whose
tokens carry meaning only through
embeddings memorized during indexing training, each bit here derives its meaning from the model's representation. Therefore, the DocIDs of unseen documents remain scorable without retraining. Experiments on three
benchmarks show that our DocID design substantially improves unseen-document
retrieval while maintaining comparable performance on seen documents. It achieves over 20 percentage points higher Hit@10 on unseen documents and up to 7 times lower inference latency than existing numeric DocID designs on NQ320K and TriviaQA, while performing only 3 percentage points below weight-update methods on MS MARCO without additional training. These results show that an appropriate DocID design can heavily reduce retraining costs when adapting generative retrievers to new documents.
Read the full abstract ▾
All authors I-Fan Lin, Zhen Zhang, Faegheh Hasibi, Suzan Verberne
Computer Vision
Efficient Fréchet Distributional Decoder Alignment for Latent Generative Models
Xianghong Fang, Jiajun Zhu, Esma Aimeur et al. (+2 more)
Fréchet Distributional (FD) objectives provide an effective distribution-level signal for post-training generative models. For latent generative models, however, existing FD-based post-training methods optimize only the latent generator while keeping the decoder frozen: the decoder is trained on reconstruction latents obtained from real images but deployed on generator-produced latents at generation time. When these latent distributions differ, this decoder train-generation mismatch means that the decoder is deployed on inputs drawn from a distribution it was not directly trained on. We introduce Fréchet Distributional Decoder
Alignment (FDDA), an efficient post-training method that freezes the latent generator and directly optimizes the decoder on generation-time latents using an FD objective. A single epoch of FDDA consistently improves gFID and gFDr$^6$ across diverse flow-based and autoregressive latent generative models. Across all 11 evaluated models, FDDA reduces gFDr$^6$ by 34.0-59.6% from the original pretrained models and provides a further 10.2-57.2% reduction after generator-side FD post-training. FDDA also reduces total wall-clock time by factors of $3.6\times$-$328.7\times$ relative to generator-side FD post-training across these models. These results show that generator-side post-training alone does not exhaust the benefits of FD optimization, and that further gains can be obtained by adapting the decoder at substantially lower cost.
Read the full abstract ▾
All authors Xianghong Fang, Jiajun Zhu, Esma Aimeur, Dehan Kong, Tim G. J. Rudner
Artificial Intelligence
An FPGA-Based Spiking Neural Network for Spatiotemporal Pattern Learning and Classification
Jingang Jin, Yue Ma, Zhenhang Zhang et al. (+1 more)
Spiking Neural Networks (SNNs) are promising for energy-efficient spatiotemporal pattern recognition at the edge, but efficient deployment and on-device adaptation require specialized hardware. In this work, we present an FPGA implementation of multilayer SNNs for spatiotemporal pattern classification, in which both inference and training take place on the same hardware. Our design adopts a temporal-forward-only training
algorithm that avoids the
memory and latency overhead associated with traditional Backpropagation Through Time (BPTT). A mixed-precision scheme balances training stability with resource efficiency, and architectural optimization maximizes hardware and
memory utilization. We further identify and resolve hazards that arise when inference and learning share the same
memory, including port conflicts between the forward and backward access patterns and read-after-write dependencies in floating-point potential accumulation. Experimental evaluations on MNIST and five multivariate time-series classification
datasets demonstrate that, with fully on-chip training, our SNN model achieves accuracy comparable to SNN or LSTM trained with BPTT. Compared to CPU and GPU based implementations, our FPGA design delivers 2.5 to 6 times higher throughput while consuming an order of magnitude less energy per sample.
Read the full abstract ▾
All authors Jingang Jin, Yue Ma, Zhenhang Zhang, Qinru Qiu
Robotics
Act4R: Action-conditioned 4D reconstruction for kinematics-free control
Zhaoliang Zhang, Chenhao Yu, Zhimin Shao et al. (+2 more)
Precise control of movement across various robotic embodiments is a longstanding challenge. Modeling complex robotic structures requires significant time, dedicated sensors, and manual labeling. Recent advancements in 4D representation learning offer an interesting alternative: can we leverage 4D features lifted from 2D observations to densely map a
robot's spatial movement based on the action signal? To this end, we propose Act4R, a framework that builds on 3D foundation model to predict a
robot's 3D scene flow with any given action. Act4R introduces a Spatial-Action Encoder, which encodes the current 2D
robot state and its action signals into
embeddings that represent future
robot state in 3D. Then, both the current and future spatial
embeddings are decoded into point maps to estimate action-conditioned scene flow. To effectively learn the mapping between action and future state, Act4R introduces spatial-action fusion in its
transformer-based encoder, and a spatial
alignment loss that guides the encoder for future flow prediction. After training on some samples of a given embodiment, Act4R can perform inverse control by optimizing the signal to achieve the desired scene flow. We evaluate Act4R on a public real-world
dataset and synthetic data collected in simulator. Experiments on various robotic platforms show that Act4R outperforms the previous SoTA in scene flow prediction. Our method also performs better in inverse control, both on the action accuracy metric and in closed-loop control in simulation.
Read the full abstract ▾
All authors Zhaoliang Zhang, Chenhao Yu, Zhimin Shao, Xijun Liu, Cheng Peng
Computation and Language
Distilling Text LMs into Speech-to-Speech LMs by Matching Internal Text Predictions
Ju-Chieh Chou, Jiawei Zhou and Karen Livescu
Text
language models (LMs) acquire broad linguistic and factual capabilities through large-scale pretraining, while comparable capabilities remain difficult to learn from
speech alone. Recent work has shown that knowledge
distillation from pretrained text LMs offers a promising way to transfer their linguistic and factual capabilities to
speech models. However, existing
distillation approaches have largely focused on
speech-input, text-output models. This idea has yet to be explored for
speech-to-
speech models, which operate on both
speech input and
speech output. In this work we introduce a
speech-to-
speech pretraining method that creates an internal text interface for knowledge transfer while preserving the
speech-only input and output. The model first consumes
speech context without its transcription, switches to text prediction, and then uses the predicted text to lead future
speech generation word by word. It also provides an interface for knowledge
distillation: the internal text predictions can be directly distilled from the base text LM. To the best of our knowledge, this is the first application of text LM
distillation to a
speech-to-
speech LM. Under matched training conditions, the proposed sequence construction substantially improves the generative perplexity of spoken continuations over
speech-only and interleaved
speech-text models, approaching the performance of a text-leading inner-monologue model with external ASR
prompt transcription. More importantly,
distillation improves factual performance under both text and
speech evaluation, indicating better retention of knowledge from the base text
language model.
Read the full abstract ▾
Information Theory · Cross-listed from eess.AS
Co-Adaptive Entropy Modeling and Rate-Distortion-Optimal Bit Allocation for Perceptual Audio Coding
Soohyun Kim, Jiwon Jeong and Marina Bosi
We present a perceptual audio coder in which the
entropy-coding model and the bit allocation co-adapt across blocks without model side information. Mantissas are coded by a hybrid of bit packing and arithmetic coding with per-band probability models learned online. Encoder and decoder accumulate identical histograms from decoded blocks and advance the same model state. The model enters bit allocation directly: per-band rate–distortion frontiers combine measured perceptual distortion with
entropy-coded rate estimates under the current model, and a dynamic program attains the exact minimum of total objective perceptual distortion for each block's budget under the model's rate estimates, with reservoir carry-over. Under a strict per-block rate,
entropy-coding-aware bit allocation lowers this distortion (band noise-to-mask ratio in linear scale) by 15-24% relative to the same solver without it, and co-adaptation removes a further 3-4% (up to 15% on oboe) that a backward-adaptive coder alone cannot realize in one pass; a MUSHRA test at 80 kbps per channel confirms the ranking.
Read the full abstract ▾
Machine Learning · Cross-listed from stat.ME
Selective Inference for Clustering Under Unknown Covariance
Yiqun T. Chen and Lucy L. Gao
Unsupervised clustering is widely used to discover underlying group structure, after which researchers often seek to validate these groups via post-hoc hypothesis testing on the population means. However, using the same data both to form clusters and to test for a difference in means inflates the Type I error rate. Recent work in selective inference has proposed solutions when the underlying data are drawn from a multivariate Gaussian distribution with a known covariance
matrix or an unknown isotropic covariance
matrix. We propose a new selective test for the difference in means between two clusters that provably controls the Type I error rate under an arbitrary unknown covariance
matrix. Our test statistic does not require estimating the feature covariance
matrix; instead, it leverages a Monte Carlo sampling procedure over the set of orthogonal
matrices. We show that this new selective test can be computed efficiently, and we derive closed-form solutions when clusters are formed using k-means or hierarchical clustering. In simulations, we demonstrate that our proposed p-value controls the selective Type I error rate and achieves substantial power, and we illustrate its application on gene expression and drug review data sets.
Read the full abstract ▾
Cryptography and Security
BrowseSafe++: Benchmarking Prompt Injection Detection Across Web Contexts, Languages, and Browser Views
Yuetian Chen, Kaiyuan Zhang, Yuntao Du et al. (+6 more)
Browser
agents need to make decisions and execute actions on behalf of users while consuming untrusted webpages, creating opportunities for malicious instructions embedded in webpages to redirect legitimate tasks. We introduce BrowseSafe++, which extends BrowseSafe from 14,719 pages to 38,675 pairs of pages. Most of its
prompt injections were observed in the wild on production websites. We keep each injection unchanged and rewrite the sensitive parts of the page around it to protect
privacy. Each attacked page has a clean copy of the same page as its control. Both are provided as HTML, Markdown, an accessibility tree, and a screenshot. Every pair includes a user task and its expected answer. The
benchmark includes twelve types of websites, from news articles to shared documents and forums, with 24 attack types appearing in 18 different locations on a page. We use these paired pages to train BrowseSafe-Guard, two 0.8B-parameter detectors for text and screenshots. Both achieve higher F1 scores than the detector based on frontier models, while keeping false-positive rates on benign pages and inference cost low. BrowseSafe-Adapt revises
benchmark injections from browser-
agent feedback, and attacks that succeed on only a few percent of tasks when replayed directly reach up to 95.41% success once adapted.
Read the full abstract ▾
All authors Yuetian Chen, Kaiyuan Zhang, Yuntao Du, Thomas Li, Mark Tenenholtz, Kyle Polley, Jerry Ma, Denis Yarats, Ninghui Li
Computation and Language
Compositional RL: Evaluating and Training LLMs for Collaborative Reasoning
Shangbin Feng, Yulia Tsvetkov, Jan Kautz et al. (+1 more)
Language models are often evaluated alone but increasingly deployed together, routed between, made to debate, ensembled, or collaboratively trained. For a model inside a system, what matters most is not how well it performs on its own, but how much the system gains from its presence. We call this a model's compositional strength and formalize it using the Shapley value of a cooperative game over coalitions of a model pool, and use a model's leave-one-out contribution to the full coalition as a tractable proxy, requiring n+1 rather than 2^n system evaluations. Evaluating individual vs. compositional strengths across five model pools, twelve collaboration methods, and twelve
datasets, we find them largely uncorrelated: in 12 of 15 (pool, method-family) settings, individual strength does not translate into compositional advantages, and the coupling is weakest among general-purpose models that practitioners are most likely to deploy. Standalone
benchmarks are therefore often poor proxies for models' value in collaborative systems. We then propose compositional reinforcement learning (C-RL), which trains a policy inside a live multi-model system and rewards the outcome produced by the system as a whole, rather than the policy's correctness in isolation. The leave-one-out baseline in Shapley values cancels under a group policy gradient, so this needs no additional rollout cost beyond RL on the collaborative system's outcome and never requires running a coalition without the policy. Across three collaboration protocols and eight tasks spanning
reasoning, coding, and scientific discovery, C-RL produces the strongest collaborator in 21 of 24 settings, lifting collaborative performance by +4.0 to +5.4 pts on average (~3x the gain of baselines), up to +13.1 pts.
Read the full abstract ▾
All authors Shangbin Feng, Yulia Tsvetkov, Jan Kautz, David Acuna
Machine Learning
Effect of Spherical Parameter Space on Number of Non-Forgetting Tasks and Capacity of Continual Learning
Nazanin Mirhosseini
We propose a continuous learning formulation for $T$ non-forgetting tasks with the spherical parameter space $\mathbb{S}^{d-1}(\sqrt{d})$ in asymptotic regime $d\rightarrow \infty$. Each task $i$ has an optimum $\bm{\Theta}_i$, minimizing its corresponding loss function $R_i(\bm{w})$ on sphere. We reduce each task $i$ to an acceptable loss region modeled by a geodesic ball $B_{\bm{\Theta}_i}(r_i(d))$ on $\mathbb{S}^{d-1}(\sqrt{d})$ centered at $\bm{\Theta}_i$ with radius $r_i(d)$. To model task dependencies (similarities), task optima $\bm{\Theta}_i$ are distributed by a Neyman-Scott clustered point process $\Phi$. Cluster centers $\{\bm{Y}_j\}_{j=1}^{N_p}$ form a homogeneous Poisson point process on sphere, while intra-cluster task optima follow a von Mises-Fisher distribution with mean $\bm{Y}_j$ and concentration $\kappa$. Each task $t\in \{1, ..., T\}$ learning
algorithm is considered to be a channel $Q_{t}(\mathrm{d}\bm{w}_t | \bm{w}_{t-1}, \mathcal{K}_{t-1}(\bm{\theta}_{1:t-1}), \bm{\theta}_t)$, where $\bm{W}_t$ is the learned parameter of task $t$ and $\mathcal{K}_{t-1}(\bm{\Theta}_{1:t-1})=\bigcap_{i=1}^{t-1}B_{\bm{\Theta}_i}(r_i(d))$. Since in continual learning, the learner does not need to reach $\bm{\Theta}_t$ exactly to successfully learn task $t$, to avoid forgetting as well as reliable learning, it only needs for the learned parameter vector $\bm{W}_{t}$ to enter $B_{\bm{\Theta}_t}(r_t(d)) \cap \mathcal{K}_{t-1}(\bm{\Theta}_{1:t-1})$. Using this model, we derive an upper bound on $T$ ensuring $\mathbb{P}[\mathcal{K}_{T}(\bm{\Theta}_{1:T}) \neq \emptyset] \rightarrow 1$ as $d\rightarrow \infty$ and $\kappa/d \rightarrow \alpha$, where $\alpha>0$ is a constant. Finally, for $T$ tasks sampled uniformly from $\Phi$, we derive an upper bound for total information theoretic capacity under the non-forgetting constraint for each task.
Read the full abstract ▾
Machine Learning
On Sleep-Wake Disorder Identification from Polysomnographic Representations
Alvise Dei Rossi, Luigi Fiorillo, Giuliana Monachino et al. (+6 more)
Self-supervised polysomnography foundation models (PSG FMs) aim to capture clinically useful information beyond sleep staging, yet are rarely compared with sleep-staging encoders pretrained at comparable scale and modality coverage. Using a common whole-night, missingness-aware state-space downstream modeling framework, we compared frozen representations from prominent large-scale, multi-cohort sleep-stage-supervised encoders and self-supervised PSG FMs for multilabel identification of six sleep-wake and circadian disorder groups in 7,906 PSGs from an unseen registry. Although PSG FMs outperformed an
EEG-only, single-cohort supervised baseline, this ordering reversed when supervised pretraining approached comparable scale and modality coverage. Transfer learning from neural sleep scorers achieved higher overall performance while exhibiting greater downstream data efficiency. These findings underscore the need for scale- and modality-matched pretrained supervised baselines when assessing PSG FMs' downstream potential.
Read the full abstract ▾
All authors Alvise Dei Rossi, Luigi Fiorillo, Giuliana Monachino, Alessia Calzoni, Julia van der Meer, Markus H. Schmidt, Claudio L.A. Bassetti, Silvia Santini, Francesca Faraci
Game Theory
Unit-Demand Pricing for Min-Buying Customers
Titing Cui, Michael Hamilton, Jourdain Lamperski et al. (+1 more)
We study the unit-demand pricing problem under min-buying behavior, where customers purchase the lowest-priced item that yields non-negative utility. In contrast to the quasi-linear model, we show that uniform pricing becomes substantially more effective under min-buying. First, we study symmetric environments. We show that for min-buying customers with independent and identically distributed valuations, a uniform price across items is optimal. We then extend this optimality result to all valuations drawn from exchangeable and affiliated distributions. However, uniform pricing is not optimal in all symmetric environments: for min-buying customers we construct an exchangeable and non-affiliated valuation distribution for which the gap between uniform pricing and optimal item pricing is logarithmic in the number of items. This gap is tight and matches the worst-case gap in the quasi-linear setting. Next, we consider asymmetric environments in which valuations are independent but not identically distributed. When these valuations are regular and customers are min-buying, we show that a uniform price guarantees approximately 69.86% of the optimal item-pricing revenue and this is tight. Overall, our results highlight that the value of non-uniform pricing substantially diminishes, and often disappears entirely, under more conservative demand models in which customers engage in satisficing behaviors such as min-buying.
Read the full abstract ▾
All authors Titing Cui, Michael Hamilton, Jourdain Lamperski, Kasra Tari
Hardware Architecture
Formal-Verification-Guided Bayesian Optimization for Non-Intrusive Last-Mile Coverage Closure
Chengjia Liu, Priyadarsi Mishra, David Kebo Houngninou et al. (+3 more)
Last-mile functional coverage closure for modern chip designs remains costly because a mature UVM environment exposes many controls while direct hits on the remaining bins are sparse. We present a non-intrusive workflow that closes pre-defined bins in an existing, human-authored functional coverage model; it does not synthesize verification objectives from the design specification. The workflow first uses abstract-syntax-tree (AST) parsing and cone-of-influence (COI) tracing to map each residual target to existing testbench knobs. Under a matched 20-simulation budget,
Bayesian optimization (BO) is compared with continued constrained-random verification (CRV) and random search over the same AST/COI-reduced space. Formal reachability then removes only targets supported by complete unreachability proofs, after which retained targets are grouped by formal difficulty and processed by group-specific BO under a second matched 20-simulation budget. Cleanup and grouping never add numerator bins; only simulator coverage artifacts do. On OpenTitan AES, first-pass reduced-space BO reaches 241/271 bins; formal cleanup removes two denominator bins; the integrated post-cleanup stage - difficulty grouping, policy routing, and group-specific BO - adds 20 simulator-confirmed hits, yielding 261/271 raw coverage (96.31%) and 261/269 effective coverage (97.03%). On
Entropy Source, first-pass reduced-space BO reaches 2117/2277 bins; formal cleanup removes ten denominator bins; the integrated post-cleanup stage - difficulty grouping, policy routing, and group-specific BO - adds 93 simulator-confirmed hits, yielding 2210/2277 raw coverage (97.06%) and 2210/2267 effective coverage (97.49%). These results characterize the integrated diagnosis-and-search workflow; the present evaluation does not isolate the causal contributions of difficulty classification, policy routing, and post-cleanup BO.
Read the full abstract ▾
All authors Chengjia Liu, Priyadarsi Mishra, David Kebo Houngninou, Michael Quinn, Aakash Tyagi, Jiang Hu
Computer Vision
TableVision: Recovering Verified Structure from Historical Tables
Todd Y. Zhou and James M. Snyder Jr
Gaps, skips, and mistakes are the normal state of a historical register: rows go missing, tables cross page breaks, columns slip under wrong names, and column sums disagree with the corresponding row entries. Readers read digits correctly but lose the table structure. On seven clean panels of election returns, the best open-source reader reproduces 99.0% of the digits but files only 83.7% of the figures in the correct
cells and gets 11 of 30 columns correct. TableVision treats table structure recovery as the problem. On three degraded 1888 pages, Amazon Textract files only 1 of 1494 figures correctly; TableVision correctly files 99.2%, and all 51 columns its exact-total check releases are correct. A dynamic program cuts a volume into blocks by how many columns sum to their last line; witnesses read the
cells; the gate classifies each column as exactly reconciling, flagged as faithful to a page whose arithmetic is wrong, or withheld. A theory of the sum check says which errors it cannot see and why its optimal block is about $\theta^{-1/2}$ rows at defect rate $\theta$. On 2201 columns of Wisconsin electoral data, the gate accepts 2042, flags 118, and withholds 41; failure rises with column length $R$ as $1-(1-\theta)^R$ at 1.1 defects per 1000
cells in general elections; official returns confirm 933 of 934 testable accepted sums and all 35 testable flagged totals; and the deployment added 491\,359 gated precinct rows to a 9.3-million-row
dataset. One implication is that the design of the verification block is critical.
Read the full abstract ▾
Hardware Architecture
When Is RTL Better? Auditing Evaluation Stability with Tool-Grounded Requirement Profiles
Bodong Hou and Zhixin Pan
RTL-generation studies increasingly report functional correctness and post-synthesis quality, yet the evaluator itself is rarely treated as an experimental variable. A candidate can appear better when a security rule, protocol obligation, target context, feasibility gate, uncertainty policy, or provenance constraint is omitted. We introduce tool-grounded requirement profiles: machine-readable contracts binding each requirement's meaning to its executable evidence and comparison rule, together with cross-requirement gates, uncertainty handling, and provenance. We audit evaluator stability by freezing candidate pairs and perturbing only their evaluation profile. In a preregistered controlled pilot with six designs, twelve pairs, three requirement families, six evaluator conditions, and 72 decisions, a generic
cell-count evaluator reports unsupported improvement for 6/12 pairs (50%; Wilson 95% interval 25.4 to 74.6%; design-cluster bootstrap interval 25 to 75%). The matched evaluator detects all twelve injected regressions, whereas syntax, generic synthesis, context mismatch, and gate ablation each lose the required distinction for 12/12 pairs. In a separately frozen external validation of all 290 public RTLLM v1.1 text-only candidates, 81/215 evaluable comparisons (37.7%; task-cluster 95% interval 24.8 to 51.4%) yield unsupported scalar improvements, including 72 functional-gate reversals. Separately, 26 OpenROAD-flow-scripts runs show why timing context and activity qualification must be part of the contract. The study does not rank generators; it establishes evaluator configuration as a measurable, auditable source of conclusion instability.
Read the full abstract ▾
Machine Learning
The belief-action gap in language model agents
Ayse Sila Okcu, Weisheng Wang, Tongmeng Xie et al. (+4 more)
Language model (LM)
agents can fail for different reasons, requiring different explanations and interventions. We study how state beliefs, action values, and action preferences interact as LM
agents reason and commit to decisions in text-rendered grid worlds. We estimate task-relevant beliefs using report-based and representation-based probes, and action values using inverse reinforcement learning. We find that task-relevant state and value information is often represented more reliably than it is reflected in behaviour. Tracking action preferences throughout
reasoning further shows that decisions sharpen around a commitment point and reported belief uncertainty decreases near commitment, although individual belief changes do not consistently explain shifts in action preference. Finally, forced actions follow
reasoning prefixes from other decisions when transplanted, whereas the tested
reasoning-window activation edits provide limited control over the action. Together, these results suggest that some failures arise not from missing task-relevant information, but from how available information is translated into action. Our measurements distinguish information availability from belief-action consistency without by themselves identifying the cause of each failure. Our code is available at: https://anonymous.4open.science/r/belief-action-gap-F745/
Read the full abstract ▾
All authors Ayse Sila Okcu, Weisheng Wang, Tongmeng Xie, Niall Dalton, Angelos Nalmpantis, Raghu Arghal, Mario Giulianelli
Game Theory
A Stochastic Growth Model for Online Platforms
Farbod Ekbatani and René Caldentey
We investigate the growth trajectory of online platforms operating as
market makers in two-sided matching
markets. Their expansion, often referred to as the “chicken-and-egg dilemma” in the literature, poses an inherent challenge: service providers find value in joining the platform because of the presence of customers, while customers are drawn to the platform by the availability of service providers. Much of the existing literature addresses this expansion challenge through either a static
market-clearing lens or aggregate dynamic models, emphasizing how network externalities shape a platform's growth trajectory and
equilibrium size. These approaches do not fully capture how gradual growth must be implemented through server-level admission, assignment, and compensation decisions. Embedded in this growth process are intertemporal participation constraints that the platform must satisfy to attract and retain forward-looking servers. To explicitly account for the
stochastic dynamics of a platform's gradual growth, we model the system as a Markov process. Potential servers and customers arrive according to Poisson processes, and customer demand is non-decreasing in the number of active servers. Under mild conditions, we characterize the platform's optimal admission, assignment, and compensation policies. The platform admits servers at the maximum feasible rate until it reaches an endogenous target size, which can be smaller than the static
market-clearing optimum. In the baseline model, seniority-based compensation acts as an operational substitute for financially subsidized growth: instead of using upfront subsidies to induce early server participation, the platform uses future cash flows to reward early servers for joining when demand is limited and for helping the platform reach later, higher-demand states.
Read the full abstract ▾
Computer Vision
Know-Thy-Not: Training-Free Targeted Negation in Dual-Encoder Vision-Language Models
DoYoung Kim, Changkyu Choi, Adín Ramírez Rivera et al. (+2 more)
Dual-encoder
vision-
language models systematically fail at negation, scoring ”a cat without a dog” nearly identically to ”a cat with a dog.” We show that this failure is inherent to the single-
embedding framework. Under contrastive training, single-
embedding methods can at best ignore the negated concept (dilution) but never penalize its presence (rejection). We propose Know-Thy-Not (KTN), a training-free method that introduces an image-side rejection dimension to penalize the negated concept directly in the visual representation. We also introduce COCO-Confusion, the first
benchmark requiring genuine rejection to succeed. Across 9 backbones, KTN improves COCO-Confusion mAP by up to +25.6 over vanilla VLMs and +9.6 over the strongest existing method.
Read the full abstract ▾
All authors DoYoung Kim, Changkyu Choi, Adín Ramírez Rivera, YunSeok Choi, Jee-Hyong Lee
Artificial Intelligence
Large Language Models Extend Known Research But Do Not Create New Research Directions
Zhihua Liu, Kurt Butler, Damian Machlanski et al. (+2 more)
The success of autonomous research systems relies on the quality of the scientific hypotheses they generate. Recent studies report that human reviewers often rate LLM-generated ideas as more novel than those from human experts, raising hope that AI can accelerate scientific discovery. Yet it is unclear whether these models can do more than extend existing knowledge. Can LLMs drive genuine innovation by revealing new research directions, or are they limited to repeating and recombining what science already knows? This unresolved question lies at the heart of discussions about AI and the future of science. To address this, we distinguish two types of novelty: distance, which measures how far a hypothesis lies from existing work, and direction, which captures whether the hypothesis pursues new lines of inquiry beyond those already present. These two measures diverge sharply for LLM-generated work. We represent scientific papers in a shared conceptual space using a pretrained scientific-paper
embedding model. Within this space, we embed 26.9 million human-authored papers across 1,325 research topics in six natural-science fields and 524,308 LLM-generated hypotheses from eight models. Distance is measured using existing metrics. To quantify direction, we introduce the orthogonal novelty score (ONS). LLMs consistently generate ideas more distant from existing work than human-authored papers, up to 16% further when the LLM is given the papers farthest from the centre of the topic. However, LLM hypotheses have a 15–23% lower median ONS than published papers from the same topic. Thus, LLMs move further from what is already known, but remain within established directions. This pattern persists across changes in various configurations. As a result, LLMs excel at extending the frontier but the creation of new directions is still led by human scientists.
Read the full abstract ▾
All authors Zhihua Liu, Kurt Butler, Damian Machlanski, Danilo Bueno, Sotirios A. Tsaftaris
Artificial Intelligence
SchemaWeaver: Accelerating On-Device Mobile Agentic AI via Schema-Guided Parallel LLM Decoding
Boyuan Yang and Wei Gao
Large
language models (LLMs) on mobile devices can act as
agents that call external software tools to complete complex tasks, but the major challenge of supporting on-device mobile agentic AI with LLMs is the long latency of LLM tool calling on mobile devices. In particular, the decode phase is the main contributor of such long latency, but is hard to speed up on mobile processors as it is bound by
memory bandwidth rather than compute power. To address this limitation, in this paper we present SchemaWeaver, a new on-device mobile agentic AI technique that enforces schema-guided parallel decoding in the decode phase of LLM tool calling, to reduce its latency by producing multiple
tokens in each decode pass. SchemaWeaver can be generically applied to the LLM inference engine on mobile devices without involving any training efforts or changes on LLMs, and our experiment results on major mobile SoCs and LLM families show that SchemaWeaver can reduce the LLM tool calling latency by up to 3.9 times, compared to the competitive baselines.
Read the full abstract ▾
Computer Vision
World-T3: Test-Time Training as Persistent Memory for Real-Time Video World Models
Junyi Wu, Zekun Li, Chenhongyi Yang et al. (+9 more)
Recent advances in
video world models have enabled plausible interactive environments, yet long-horizon generation places a fundamental demand on visual
memory: the previously observed world must remain consistent as the model continues to generate. Existing autoregressive approaches often implicitly rely on the generative model itself to retain such information, leading to spatial
memory decay beyond the active context. We introduce World-T3, a camera-controlled
video world model with a test-time training
memory that consolidates past observations into dedicated model parameters. To robustly update this
memory, we propose a recursive least-squares rule that incrementally absorbs novel visual features via online pose-keyed
memory updates. Our TTT
memory reads out previously observed scene features from the fast-weight state by camera pose, enabling consistent generation with constant storage and per-step computation regardless of rollout length. To facilitate real-time interactive generation with this robust
memory, we further distill the autoregressive model into a few-step generator via dual-teacher distribution matching. On a long-horizon revisit
benchmark, World-T3 raises revisit PSNR from 13.52 to 18.31 dB and reduces absolute rotation error from 3.344 to 1.075 relative to the strongest baseline on both metrics, while sustaining 20.6 FPS at 1280 x 704 on a single NVIDIA B200 GPU.
Read the full abstract ▾
All authors Junyi Wu, Zekun Li, Chenhongyi Yang, Chen Guo, Lingchen Yang, Yongan Zhang, Xinyi Zhang, Hongbing Hu, Bartek Rymkowski, Srinath Sridhar, Yan Yan, Xijie Huang
Cryptography and Security
VeriRouter: Towards Verifiable LLM Routing
Mengyu Yao, Ziqi Zhang, Shaofei Li et al. (+4 more)
Large
language model (LLM) routers are increasingly deployed to optimize quality, latency, and cost through dynamic model selection and request rewriting. However, a compromised router can cause ineligible selection on the control plane, unendorsed rewriting or unfaithful relay on the data plane, undermining LLM routing integrity. We present VeriRouter, a verifiable LLM routing framework. Under an endorsed public context binding a private semantic index and rewrite banks, VeriRouter combines ZK proofs with a provider-issued serving certificate to establish integrity across both planes while keeping the router's private routing assets hidden from clients. For model selection, we design an efficient ZK proof for semantic search. For rewriting, local checks enforce message preservation and additions from committed banks. On real-world workloads, VeriRouter's model-selection and rewrite proofs average 21.92~s and 4.24~s, yielding 1,307$\times$ and 101$\times$ speedups over the fastest completing baselines. Relative to serving without verification, VeriRouter adds only 4.08 s under per-turn selection and 0.11 s under session-pinned selection.
Read the full abstract ▾
All authors Mengyu Yao, Ziqi Zhang, Shaofei Li, Yifeng Cai, Ding Li, Yao Guo, Ning Luo
Computational Geometry
Optimal Planar $k$ Nearest Neighbors Queries for Additively Weighted Euclidean Distances and Convex Metrics
Chih-Hung Liu
Given a set $P$ of $n$ point sites in the plane, the $k$ nearest neighbors problem is to build a data structure that, for a query point $v$ and a query integer $k$, reports the $k$ nearest point sites of $v$ in $P$ efficiently. For the Euclidean metric, after four decades of efforts, an optimal data structure has been developed with $O(n)$ space, $O(\log n+k)$ query time and $O(n\log n)$ preprocessing time [Mat92b, Cha00, AC09, CT16]. In contrast, for a family of distance functions, the state-of-the-art data structure [AES99, KMR+20, Liu22] attains $O(n\log\log n)$ space, $O(\log n+k)$ query time and expected $O(n\log n)$ preprocessing time. An open question is the existence of an optimal data structure with $O(n)$ space and $O(\log n + k)$ query time for distance functions more general than the Euclidean metric. Such an optimal data structure also remains unknown for non-point sites in the Euclidean metric, even for disk sites or, more generally, additively weighted Euclidean distances. We develop an optimal $k$-nearest-neighbors data structure for additively weighted Euclidean distances with $O(n)$ space, $O(\log n + k)$ query time and expected $O(n\log n)$ preprocessing time. Since this data structure can be adjusted to disk sites, it serves as an initial result toward optimality for non-point sites. We also adapt our data structure to point sites under a family of convex metrics, including commonly used $L_p$ metrics and uniform orientation metrics. The data structure can be further extended to distance functions that satisfy certain axioms. Thus, we demonstrate the existence of optimal $k$-nearest-neighbors data structures for distance functions more general than point sites in the Euclidean metric. Our main technical advance is to generalize Matoušek's shallow partition
theorem for hyperplanes [Mat92b] to these settings, while achieving a logarithmic crossing number.
Read the full abstract ▾
Machine Learning
Monarch-Muon: Structure-Aware Muon for Fast and Memory-Efficient Pretraining
Alexander Miasnikov, Ruslan Kabirov, Gleb Molodtsov et al. (+7 more)
Training large
language models is constrained by both wall-clock time and
memory footprint, and recent
matrix-aware optimizers sharpen this tradeoff:
Muon can improve optimization but its dense polar update remains expensive. We propose Monarch-
Muon, a structured
matrix-aware optimizer for weights parameterized by Monarch factors. The resulting structure reduces weights, gradients, and optimizer state, and exposes small independent update subproblems in place of a single dense orthogonalization; we formalize this through a blockwise trust-region interpretation. In quality runs, Monarch-
Muon improves over Monarch-AdamW at fixed structure: 3.06 vs. 3.09 in the dense 257M model and 2.68 vs. 2.77 in the 1B MoE model; the two-block MoE variant also matches dense AdamW while using 15% fewer active and 25.4% fewer total parameters. In 6.89B-parameter systems measurements, Monarch-
Muon reduces peak
memory from 68.9 to 52.9 GB,
Muon optimizer state from 14.60 to 6.77 GB, and the
Muon optimizer step from 1288 to 304 ms.
Read the full abstract ▾
All authors Alexander Miasnikov, Ruslan Kabirov, Gleb Molodtsov, Dmitrii Vlashchuk, Vladimir Aletov, Nail Bashirov, Daniil Tikhonov, Maxim Krutikov, Aleksandr Shestakov, Aleksandr Beznosikov
Robotics
Smoothness Ranks Skill, Not Success: An Audit of Published Trajectory-Smoothness Curation Metrics Under Episode-Length Controls
Jaiveer Bassi
Trajectory smoothness has been proposed as a cheap, training-free signal for curating imitation-learning demonstrations, most recently by rinse, which introduces Spectral Arc Length (SAL) and a contact-aware Trajectory-Envelope Distance (TED). We test whether these published metrics survive episode-length controls on real robomimic data. On can/mh, SAL separates better from worse operators with AUROC 0.952, but episode length alone achieves 0.957, and inside a duration-matched band SAL falls to 0.628 while raw mean jerk, the baseline rinse argues against, rises to 0.896. The confound replicates on square/mh. On can/mg, where every episode is exactly 150 steps, SAL is at chance (0.454) and TED is inverted (0.376) against task success, while jerk reaches 0.706. Training GMM behavior-cloning policies on each metric's curated subset (10 seeds), curating by TED costs roughly a third of downstream success relative to random selection of the same size (0.240 vs. 0.360, p=0.0001, surviving Bonferroni correction), while SAL and jerk are indistinguishable from not curating. Under a
diffusion policy TED still ranks worst, though its deficit is not resolvable at five seeds, and jerk becomes significantly better than both baselines, so the curation decision does not transfer unchanged across the two policy configurations we tested. Inspecting trajectories shows why TED inverts: successful manipulation requires sustained high-deviation motion through contact, while failure is low-amplitude hovering that a smoothed envelope follows closely.
Read the full abstract ▾