Computer Science & Mathematics

Existing anti-spoofing systems report either an utterance-level score or a time-based spoof interval: the former cannot show which words are spoofed, while the latter does not directly match the transcript and must be post-aligned with words, so alignment errors can lead to wrong word-level labels. Standard ASR model outputs only text; spoof information in the audio is lost after recognition and is not passed with the transcript. Yet changing only a few words can change the meaning of a sentence, leaving downstream systems to use incorrect text without knowing which words are spoofed. We therefore treat partial anti-spoofing as tagged ASR: the model transcribes speech and marks spoofed words at the same time, directly linking spoof labels to output words. We adopt the audio LLM and use ASR-Protected Subspace Gated Fusion (APSGF) to fuse spoof cues with ASR features. Spoof cues are added only outside an ASR-protected subspace, so they do not disturb recognition features. After cross-entropy training, we fine-tune the model with Reference-Anchored Policy Optimization (RAPO). Since the SFT policy is already concentrated, multiple samples from the same input tend to receive similar rewards, resulting in weak group-wise advantages. RAPO instead generates a single sample with low sampling randomness and anchors its advantage to the reward of a reference model. This allows the model to reinforce responses that outperform the reference while suppressing those that underperform it. Experiments on five datasets demonstrate the effectiveness of our approach in jointly detecting spoofed words and preserving ASR accuracy. The code is publicly available.

Generative recommendation formulates item recommendation as autoregressive generation rather than a discriminative scoring problem. Although empirical studies exhibit favorable scaling behavior in recommendation, unleashing the benefits of scaling remains challenging under the strict model size and inference cost constraints of real-world systems. A central challenge is to combine expressive modeling of user-item interaction histories with flexible computational depth without proportionally increasing model size. We introduce LoopGR, a parameter-efficient scaling framework for generative recommendation via recurrent depth. LoopGR employs a tailored hierarchical recurrent depth mechanism that alternates between a shared generative decoder and a lightweight context updater. For efficient inference, we further develop recurrent trajectory self-distillation that distills a low-budget student from a high-budget teacher by aligning both predictive distributions and evolution directions. Extensive experiments show that LoopGR consistently outperforms strong generative recommendation baselines. Compared with a representative encoder-decoder baseline, LoopGR achieves superior performance while reducing model size by up to 52%. These results establish recurrent depth as a new scaling dimension, offering a flexible and resource-efficient scaling path for generative recommendation.

Muon has achieved strong empirical performance in large-scale language-model training, motivating a better theoretical understanding of its practical implementation. Unlike the idealized polar-factor update, practical Muon uses a fixed number of quintic Newton--Schulz iterations. Existing analyses mainly establish average- or best-iterate stationarity guarantees, leaving last-iterate convergence less understood. We study last-iterate gradient convergence of practical finite-step Muon on smooth, lower-bounded nonconvex objectives. For deterministic gradients, we show that without input stabilization, Muon can cycle even on a smooth convex quadratic. With positive stabilization, we establish last-iterate gradient convergence for any fixed momentum coefficient below one and a sufficiently small constant learning rate, together with square-summability of gradients. For stochastic gradients, we first show that persistent bounded, unbiased noise can prevent convergence with fixed learning rates and momentum, even with positive stabilization. We then establish almost-sure and mean-square last-iterate gradient convergence by combining decreasing learning rates with increasing momentum under bounded-variance stochastic gradients. Finally, we construct a smooth counterexample showing that neither convergence theorem guarantees a pointwise polynomial rate. We further establish density-one convergence rates, guaranteeing polynomial gradient decay for all but a vanishing fraction of iterations.

Lithium-ion batteries are widely used in industrial applications, but their performance gradually degrades over time, making accurate lifetime prediction important for safety and reliability. However, reliable lifetime assessment generally requires extensive degradation testing, which is both costly and time-consuming. To reduce this burden, recent data-driven approaches have sought to predict the end-of-life cycle of batteries from only the initial few cycles. Nevertheless, identifying reliable degradation patterns from such limited early-cycle data remains challenging because early aging dynamics are often subtle and nonlinear. To address this issue, we adopt the continuous wavelet transform to convert cycle-wise voltage, current, and capacity signals into time-frequency representations, enabling multi-resolution characterization of degradation behavior. Building on this representation, we apply scale compression to reduce redundancy while preserving structural information in the scalograms. We evaluate the proposed framework on eight benchmark datasets derived from seven public battery datasets covering diverse electrode chemistries, cell form factors, and cycling protocols. Experimental results show that the proposed framework consistently outperforms prior approaches in single-cycle remaining useful life prediction and remains robust as the number of input cycles increases from 1 to 100. In addition, redundancy-fidelity analysis characterizes the trade-off introduced by scale compression, and gradient-based visual explanations indicate that the model focuses on localized time-frequency regions associated with structured signal transitions during charge-discharge operation. These results demonstrate the effectiveness and interpretability of the proposed framework for early-cycle battery remaining useful life prediction.

Multimodal misinformation detection methods often rely on different preprocessing pipelines and auxiliary resources, making experimental comparisons difficult to interpret. We present MMFact, a collection of shared resources and tools that simplifies this research workflow. It brings together 47 detector implementations and baselines, three multimodal datasets, and prepared materials ranging from semantic features to OCR, image descriptions, and external evidence. Compatible methods can use the same materials, reducing variation introduced by preprocessing and supporting fairer comparisons. A modular training and evaluation framework preserves method-specific designs while providing common experimental procedures. By treating prepared materials as a shared research resource, MMFact helps researchers focus on developing and evaluating detection methods.

Crowd barriers are widely used to regulate pedestrian movement during large public events such as pilgrimages. However, fixed barrier layouts often create unnecessary stopping and local congestion even when they successfully control the overall crowd flow. Finding better barrier configurations is difficult because there is no dataset that provides the best barrier placement for a given crowd scene. We address this challenge by introducing a simulation-driven reinforcement learning framework that learns barrier configurations without requiring labelled training data. Starting from a segmented crowd scene, we construct a realistic simulation environment that reproduces the observed pedestrian distribution. This environment is then used to train a Soft Actor-Critic (SAC) agent that continuously adjusts barrier positions to improve pedestrian movement. Unlike supervised approaches the proposed framework allows the agent to explore barrier configurations that have never been observed in real data. We evaluate the learned policy under unseen numbers of pedestrians. The learned policy consistently outperforms the existing manually designed barrier configuration by reducing pedestrian stops while maintaining effective flow regulation. These results demonstrate that combining computer vision crowd simulation and reinforcement learning provides an effective framework for optimizing crowd control infrastructure.

Tool-using language model agents are usually evaluated by whether they finish the user's task. That metric misses a common failure: an agent can complete the requested work while also taking an unauthorized side-effecting action, such as writing to the wrong object, expanding the scope of the request, or contacting an unintended recipient. We call this failure mode collateral damage (CD). We introduce SABench (Side-effect-Aware Benchmark), a benchmark of 201 email, calendar, and ticket tasks. Each task crosses one of four state structures (independent, dependent, externally reachable, cross-tool) with one of four trap families (ambiguity, mis-targeting, cascade harm, overreach), and each task has a deterministic trace-based oracle for both goal satisfaction and authorization compliance. Across 2,211 model-task pairs from 11 frontier LLMs spanning major commercial and open model families, 15.2% of all runs incur CD, with risk concentrated in ambiguity tasks (38.8% violation rate) while non-ambiguous traps average 8.4% CD. Among goal-satisfied runs, 12.8% still produce unauthorized writes. Cross-tool and dependent states have about twice the CD rate of independent states. CD rates vary by 4.7x across models at comparable goal rates, which suggests that task success alone is a poor proxy for safe tool use. The SABench task corpus is released at https://huggingface.co/datasets/Phaedrus/sabench; the traces, oracle, code, and analysis pipeline are released at https://github.com/hjj194/sabench-artifact.

The azimuthal angular dependence of the in-plane magnetoresistance provides a powerful probe for detecting rotational symmetry breaking in superconductors, which has significant implications for understanding the superconducting pairing symmetry and the intertwined orders. However, in two-dimensional or layered superconductors with strong anisotropy between in-plane and out-of-plane critical fields, measuring the in-plane magnetoresistance is particularly challenging as it is extremely sensitive to the field misalignment. Here we perform systematic electrical transport measurements on ultrathin FeSe films grown on SrTiO3 substrates. By remounting the same FeSe film to change the field misalignment, two qualitatively different angular dependences of the in-plane magnetoresistance are observed in the superconducting transition region, indicating the extreme sensitivity of the measurement to field misalignment. The observed anisotropic in-plane magnetoresistance can be well captured by our geometric model considering the field misalignment effect. Our work provides a practical framework for disentangling the misalignment effect and investigating the in-plane rotational symmetry breaking in two-dimensional or layered superconductors.

Fluid antenna arrays (FAAs) reconfigure their effective aperture by activating radiation ports from a dense set of candidate positions within a finite physical region, thereby offering geometry diversity beyond conventional fixed arrays. This paper studies arbitrary-direction far-field beam synthesis with a planar FAA. Since a fixed array adapts its beamforming weights on a predetermined spatial sampling structure, its ability to match desired beam patterns is limited when both the aperture and the number of active elements are constrained. To exploit the geometry diversity of the FAA, we propose a coarse-to-fine scheme that couples discrete port selection with continuous joint refinement. In the coarse stage, a fast Fourier transform (FFT) based phase retrieval step converts the amplitude-only beam specification into an aperture-compatible complex target, after which an FFT-tailored greedy method selects the active ports and least squares initializes their complex weights. In the fine stage, a projected adaptive moment estimation procedure jointly refines the continuous port positions and beamforming weights while enforcing the minimum interelement spacing. For the evaluated two-beam configuration, the proposed scheme increases the mainlobe energy fraction from 35.73% to 48.92% and reduces the peak sidelobe level from -2.30 dB to -3.83 dB relative to a fixed array with the same aperture and active-port count.

Diffusion models are powerful priors for inverse problems, including accelerated MRI. However, modeling the distribution of high-resolution images requires large networks with high computational cost. We propose a posterior sampling framework that uses cascaded diffusion models as multiscale priors. Conditioned on a coarse image, the distribution of fine-scale detail is local and well conditioned, and it can therefore be captured by a small network. Similarly, a small unconditional network is sufficient to represent low-resolution images, and it is used to recover the coarse image from the k-space center. This estimate then conditions the high-resolution prior, which is combined with all measurements to recover the final image. Both priors are trained on images alone, so they apply to any sampling pattern, and data consistency remains linear at every scale. In multi-coil brain MRI, the proposed method improves on the best single-scale diffusion baseline by 4-6 dB in PSNR at 15x acceleration, while each of its separately trained networks is about 10x smaller. The gain grows as the problem becomes more ill-posed, and ablations show that it arises from informative low-resolution conditioning.

Time Series Foundation Models have demonstrated that pretraining on diverse datasets enables effective transfer to new forecasting tasks. Classical methods like ARIMA, however, remain configured and trained independently for each series, discarding knowledge from previous experiments. Consequently, selecting and training an ARIMA configuration remains challenging and often relies on heuristic approaches based on in-sample goodnessof-fit measures. We propose MetaARIMA, a pretrained configuration policy based on metalearning that brings transfer learning to classical statistical forecasting at the configuration level rather than the model level. The policy learns from historical experiments which ARIMA configurations achieve top-quantile performance, and recommends promising candidates for new series while preserving interpretability and local estimation. At inference, it selects a diverse set of candidates via maximal marginal relevance and efficiently identifies the final configuration using successive halving. Experiments in a transfer learning setting, training on M4 and evaluating on M1, M3, and Tourism, show that MetaARIMA outperforms AutoARIMA and other classical methods while being more dataefficient. In a comparison with recent zero-shot foundation models, MetaARIMA remains competitive with Chronos2, Moirai2, and TimesFM. The experiments are publicly available at https://github.com/vcerqueira/experiments-metaarima.

Latent reasoning performs intermediate computation in continuous space rather than through explicit tokens, which is particularly appealing in chemistry, where errors in explicit reasoning can propagate to the final answer. Yet if latent states truly constitute an implicit reasoning chain, they should be causally important. We find otherwise: swapping or moderately perturbing intermediate latent states has little effect on performance, while removing them entirely sometimes causes a substantial score drop. Thus, the latent states matter, but their molecule-specific content appears to matter far less. This points to a simpler interpretation. Rather than encoding a step-by-step reasoning chain, latent states may primarily steer subsequent model computation, much like soft prompts. Indeed, a single fixed prefix shared across molecules reproduces LatentChem's performance, and a learned static soft prompt performs comparably to per-input latent generation in controlled models. The tolerance of latent sequences to substitution and moderate perturbation further supports this connection. We therefore suggest that latent chemical reasoning may be better viewed as soft prompting than as a reasoning chain hidden in continuous space.

Instruction-based image editors built on diffusion transformers run tens of denoising steps. Training-free acceleration either reuses features across steps (step caching) or stops computing the regions an edit leaves untouched (region freezing), and the two have been combined before. We ask how a high speed-up target should be split between them. On Qwen-Image-2.1, freezing does more than remove tokens: it lowers the cost of every step, so the step cache can reach the same overall speed-up with a conservative threshold that keeps its error small. A per-step cost model fitted on development runs predicts held-out latency with a median error of 4.0% and reproduces the speed ceilings of the region methods we re-implemented (2.73$\times$ predicted vs. 2.70$\times$ measured for RegionE). Driving frozen tokens to the model's one-step $x_0$ estimate beats returning them to the reference image on every development sample, and in 90% of measured cases the composed error stays below the sum of the two individual errors. The resulting method, FreezePlan, keeps five full steps and gives the rest of the budget to TaylorSeer. On a pre-registered test split it runs 5.05$\times$ faster end to end at 29.8 dB PSNR to the original output, with no significant drop in a VLM judge score; TaylorSeer at 5.02$\times$ reaches 23.5 dB. The curve extends to 5.99$\times$ at 28.0 dB. Swapping in the region selectors of prior methods under our schedule lowers median PSNR by only 0.5--0.6 dB, which places the gain in the schedule and budget split rather than in the selector.

Favourable oppositions of Mars gave nineteenth-century astronomers recurring opportunities to test claims about the planet, while telegraphic news and newspaper reprinting carried those claims well beyond the professional observatories. Historians have established the importance of these events to the development of mass-media astronomy. Here, I examine a related question in the Australian colonial press: how did the standing of particular claims change as brief reports, local responses and fuller accounts appeared at different times? Drawing on colonial newspaper coverage from 1875 to 1899, I follow episodes surrounding the major Mars oppositions of 1892 and 1894. Reports of observations attributed to "Professor Pickering" in 1892 prompted both rapid circulation and immediate scrutiny. In 1894, a cable about William W. Campbell's spectroscopic work provoked local disagreement before more detailed accounts became available. These sequences show that a Mars opposition concentrated attention without imposing a uniform progression from anticipation to discovery and subsequent caution. Newspapers carried assessments and renewed speculation at the same time. The Australian case extends work on event astronomy by showing how the timing and form of information arriving in a colonial press network affected the public evaluation of astronomical claims.

Long-sequence models must retain earlier information. Full attention keeps all past tokens but grows expensive, and recurrent-memory models compress history into fixed slots for linear-time processing. Limited capacity makes writes consequential: distractors can interfere with useful content, while skipped evidence cannot be recalled. Existing multi-slot memories write every token to the same number of slots, merging whether to store it with how many slots to update. We introduce Factorized Write Routing (FWR), which first keeps or skips each token and then chooses a fixed or token-adaptive number of slots. Queries still read all slots. Across ten seeds on two synthetic tasks that query facts after long contexts, we observe a density-dependent reversal. With four slots per write, long-context accuracy favors always writing on dense Feature Recall (0.472 vs 0.337), but learned selective writing on sparse-fact Passkey (0.222 vs 0.048). The tested adaptive rule underperforms fixed allocation under the learned gate on both tasks. A diagnostic oracle given fact labels unavailable at deployment reaches 0.372 on Passkey, showing headroom in filtering distractors. The results suggest avoiding missed writes in information-dense contexts and filtering distractors when they dominate.