Computer Science & Mathematics

The quality of the teacher label has a dramatic impact on the outcome of the machine learning process. Medical image segmentation often suffers from a noisy ground truth (GT) mask due to difficulties in consistent annotation. Although a recent study has proposed a promising method to curate the noisy GT mask, this requires additional well-curated GT masks that are not always accessible without the aid of multiple medical experts. As an alternative, we propose SAM-Correction, which utilizes a foundation model to correct the noisy GT mask in a fully adaptive manner instead of manually preparing well-curated masks. In our approach, we progressively mitigate label noise via the segment anything model (SAM), where prompts are given from another segmentation network that we train concurrently. Experiments with various types of label noise derived from actual human annotations demonstrate that SAM-C achieves precise noise reduction and high-performing segmentation models trained thereby. Our method paves the way for robust model training even when clean labels are entirely unavailable.

Large language models (LLMs) can turn market notices and news into features for electricity price forecasting. Such features also record when documents arrive and whether their extraction failed, so a gain measured against a model without text can reflect document activity as well as content. We add the counts of the same documents and of their failed extractions to a no-text LightGBM model and measure each LLM representation against this activity reference, which needs no additional LLM requests. With gpt-6-luna as the extractor, we forecast Australian electricity prices from operator notices (5-30 minutes ahead) and WattClarity news (day-ahead) after the extractor's documented knowledge cutoff, averaging forecasts over three training seeds. For news, the counts alone lower mean absolute error (MAE) by 3.0%, most of the 3.6% reduction that the better LLM representation achieves relative to the no-text model; its increment beyond the counts is not significant. For notices, two of the three LLM representations lower MAE beyond the counts, by 0.14-0.21% and 0.45-0.52%, whether the counts are cumulative or cover recent windows, whereas the third shows no significant reduction. Time-shifted placebos give mixed evidence on whether these gains require text aligned with the target. Benchmarks using the operator's pre-dispatch forecasts (notices) or price history alone (news) are more accurate than all these text models. Gains against the no-text model and the activity reference differ in sign at individual seeds and, for notices with cumulative counts, in seed-averaged forecasts. Text gains should be reported against both references.

Large language models (LLMs) can read startup pitch decks, but letting them emit investment scores directly invites score inflation, run-to-run variance and rationales that are hard to audit. We describe DealsFlow, a human-in-the-loop agentic harness deployed at a UK early-stage fund. The LLM reads the deck, cites evidence and rates each category; code combines the ratings, caps them and only ever lowers them. Three mechanisms implement this: a stage-aware corroboration ceiling (78, 70 or 60 out of 100) on factual categories without external evidence; a sceptic call that may lower but never raise a score; and a pre-fetch pattern that retrieves and indexes all evidence before a single generation pass. We evaluate on $N=243$ SEIS/EIS investments with recorded outcomes. Because recent investments have unresolved outcomes, we use the 142 that are at least three years old. There, the full pipeline's score has Spearman $ρ=0.45$ (95% CI 0.32 to 0.57) with the total-value multiple and AUC 0.71 for identifying write-offs, against $ρ=0.38$ and AUC 0.68 for an unconstrained LLM. The gain is small and comes mostly from the sceptic call; we did not test whether its lower-only rule matters. Investments that later exceeded $2\times$ had 64% of factual categories corroborated, against 38% for write-offs (omnibus Kruskal-Wallis test over five outcome groups, $p=0.031$), and our retrieval was not date-restricted, so these figures may overstate screening skill. In a study of 20 inbound applications, analyst time per application fell from 44.7 to 18.9 minutes including verification and correction, and 84% of 240 cited claims were fully supported by their sources, but 70% of reports needed at least one correction.

Continuous visual world simulation requires coupling evolving scene geometry with temporally persistent appearance. We present UniWorld, a unified framework that integrates depth trajectories and reference appearance within a shared video generation model. The central design maintains visual and geometric histories on a common timeline. Noise-aligned overlapping continuation places generated history at the prescribed sampling noise level and commits only newly generated latents. Rolling depth latent state preserves the corresponding geometric controls, incrementally reads newly available geometry, and keeps the conditioning fixed within each sampling window. Together, these mechanisms ensure exact preservation of latent history while bounding the active depth state by the window size. We evaluate continuous generation, paired history interventions, and long-horizon behavior across diverse scene categories. The same generator supports estimated, native, and on-demand simulator depth, while cached and incremental execution paths produce bitwise-identical outputs. Appearance changes and geometric control branches operate through the same interface without modifying committed history. The measured steady-state DiT execution path achieves real-time generation throughput, demonstrating the efficiency of UniWorld for continuous visual world simulation. Project page: https://zephipage.github.io/UniWorld.

Spoken native language (L1) identification for second language learners has traditionally relied on acoustic attributes of speech. Comparatively little attention has been paid to analysing speech transcripts for L1 traces. In this paper, we present a study of L1 identification using both speech and corresponding transcripts from a spoken learner English corpus. We compare a WavLM-based audio L1 classifier with a zero-shot GPT-4o classifier operating on transcripts and analyse their predictions across proficiency levels using a CEFR-balanced evaluation set. Our experiments show that the audio classifier outperforms the transcript-based approach overall when full transcripts are available, although their relative strengths vary with learner proficiency. Audio performs better at A1, whereas text performs better from A2 to C1 with full transcripts. Transcript-based accuracy generally increases with proficiency, while acoustic performance remains comparatively stable. Restricting transcript length substantially reduces text-based accuracy, whereas audio is less sensitive to input length and performs relatively well with limited input. These findings provide insights into L1 identification from acoustic and textual representations of learner speech and how performance varies with proficiency and the amount of available language material.

Trajectory transfer from rollout to training affects both learning quality and system efficiency in large language model reinforcement learning (RL). Enforcing batch-wide training requirements can delay the admission of completed trajectories, resulting in higher architectural staleness: the additional parameter-version gap from disaggregated pipelining relative to colocated execution. Beyond admission, misalignment between data access and training consumption causes redundant movement and unnecessary waiting when transferring large trajectory payloads. We present KnitTrans, a system that coordinates the rollout-to-training path through three designs. First, constraint-preserving mini-batch admission allows flexibility in early mini-batch composition, while checking that enough capacity remains to satisfy the remaining quotas. Second, on-demand trajectory data access matches storage units to consumer assignments and overlaps micro-batch data preparation with computation. Third, multimodal encoding deduplication supports reuse across a mini-batch while preserving gradient contributions from all backbone micro-batches. Experiments show up to 93% lower architectural staleness than with train-batch admission, narrowing the learning-quality gap between disaggregated execution and colocated execution. On multimodal workloads, KnitTrans reduces transfer latency by two orders of magnitude and achieves a speedup of up to 5.8 times in transfer plus training over the baseline.

While Diffusion models produce high-quality images, real-world visual design requires intentionally preserving clean regions for headlines, logos, or UI elements. Existing layout-aware text-to-image methods struggle to strictly preserve reserved regions, often introducing unwanted content that complicates downstream editing. Existing approaches either manipulate attention to displace content or suppress conditioning via noise-level interventions. However, these methods sacrifice visual coherence, producing flat regions or noticeable style inconsistencies between reserved and non-reserved areas. To address this limitation, we propose a Prompt-Aware Shared-Latent Training-Free Annealed Diffusion Sampling (PASTA), a training-free framework that enforces reserved-region constraints by selectively applying semantic guidance to object-allowed regions during sampling. PASTA operates on a shared latent trajectory, where full-prompt and context-prompt guidance are fused through mask-guided sampling. An annealed schedule suppresses semantic leakage during early denoising stages while gradually restoring visual consistency in later stages. Extensive experiments demonstrate that PASTA improves reserved-region fidelity while preserving overall image realism and perceptual consistency.

Simulating molecular excited-state processes requires resolving electronic and nuclear dynamics, but the cost of direct quantum-chemical calculations limits accessible system sizes and timescales. Machine-learning models can extend these simulations, yet they often need to be tailored to specific molecular systems and scientific objectives. Building and deploying such models requires coordinated decisions across conformational sampling, quantum-chemical labelling, model training, validation and dynamics. Here we introduce Paired agents for Unified Learning and Simulation of Excited States (PULSES), a multi-agent system that automates this workflow within expert-approved boundaries. A human expert and planner define the scientific objective, methods and decision boundaries, while an orchestrator coordinates domain agents and artifact-specific scientific assurance during execution. We evaluate PULSES on 15 computational chemistry tasks and demonstrate end-to-end applications to perylene exciton Hamiltonians, solvent-dependent biphenyl relaxation, and excited-state proton transfer in 10-hydroxybenzo[h]quinoline. These results demonstrate traceable, expert-bounded construction and deployment of specialized excited-state models, while retaining scientific validation as a requirement rather than assuming that successful execution establishes correctness.

This paper develops a foundational measure-geometric theory of robustness in machine learning. Robustness is formulated as escape from a retained task state relative to a reference measure on a data-bearing manifold, a perturbation gauge, and an admissible realization mechanism. The theory distinguishes the structural possibility of escape on the reference manifold from its ambient realization under mechanism-dependent observable readouts, while placing both within a unified geometric account. It introduces a mesoscopic organization of escape geometry, through which vulnerable mass, finite-scale morphology, delivered progress, and branch coherence are characterized by explicit laws as linked but non-identical robustness phenomena. By recasting robustness as the geometric formation, organization, realization, and persistence of escape, the theory provides a structural basis for analysis beyond scalar criteria.

Multi-task deep learning has been developed to ensure explainability in computer-aided diagnosis (CAD) systems. These systems simultaneously predict interpretable characteristics of findings in auxiliary tasks to help radiologists assess the reliability of the diagnostic prediction. However, the CAD's opinion would not be referred to when the auxiliary task prediction deviates from the radiologist's expectation. To further leverage CAD's knowledge in the above situation, we proposed a multi-task gradient assist (MGA) method that brings interactivity to multi-task models without additional training. MGA allows radiologists to give feedback to the CAD and ask for additional diagnostic suggestions. Using two datasets of mammography and CT, we show that MGA successfully improves diagnostic accuracy upon feedback on various auxiliary tasks. Compared to an existing method using forward propagation only, MGA performs more robustly and can be combined to further improve accuracy. Our method paves a promising way for integrating artificial intelligence into image diagnosis.

The 3rd WEAR Dataset Challenge asks for an activity label for every one-second window of four unseen participants. Each window has 15 VideoMAEv2 frame embeddings, the accelerometer signal of one random limb, and the windows are shuffled. This report is an empirical analysis of one system built after the challenge deadline. Window classifiers are stacked with features averaged over per-participant graphs of video neighbours and scored successor candidates, and a mean-field style decoder with a soft count constraint per activity labels all windows of a participant together. The setting is offline and transductive, and the count constraint relies on each activity being performed once. In a participant-wise simulation with participant-level bootstrap intervals, stacking added 0.051 macro F1 over stage-1 fusion and the count constraint 0.011 (95% interval 0.006 to 0.017). A quadratic seam distance ranks the true same-limb successor first among about 720 candidates in 83.9% of cases, but adding it to the link model changed macro F1 by -0.0001 (-0.0006 to 0.0005). With the decoder settings and the mixing weight chosen inside the folds and the mislabelled spans left out of training, the system scores 0.936 in simulation (0.940 for participants who performed each activity once); the submitted configuration scores 0.938 (0.943). Per-participant scores range from 0.80 to 0.97. These results come from a non-nested stacking protocol that uses unlabelled features transductively, so they are not a fully inductive estimate. An oracle that averages the final unary scores over the true segments reaches 0.973, and 79% of the remaining errors involve the null class. On the private leaderboard, which no choice used, the selected Kaggle submission scored 0.9231 (public 0.9254, with bounds partly tuned there), and a later one with bounds chosen in simulation scored 0.9247 (public 0.9253).

In a directed graph, a stable (or acyclic) set is a set which does not induce a directed cycle. Given a directed graph and two acyclic sets of the same size, the Acyclic-Set-Reconfiguration with Directed Token Sliding (ASR) problem asks whether one can, by iteratively replacing a vertex by an adjacent one, transform the first set into the second one, while maintaining acyclicity during the transformation. In this work, we present a study of the complexity of ASR and provide an FPT algorithm for semi-complete digraphs, when parametrized by the size of the sets being reconfigured, the directed pathwidth (or equivalently, the directed treewidth) of the instance, and a newly introduced parameter called the iteration of the reconfiguration sequence. To the best of our knowledge, the reconfiguration of stable sets has only been studied on undirected graphs, or (more recently) on sparse directed graphs.

Text-to-image (T2I) diffusion models have advanced notably, but still fail to satisfy prompt conditions, resulting in attribute mismatches and missing objects. These errors normally fall into two categories: concept loss, when an object or attribute (i.e., concept) goes missing, and concept confusion, when an attribute is assigned to the wrong object or multiple objects blend together. Recent studies suggest that these challenges are caused by the limited capacity of CLIP text encoder to capture fine-grained semantic details. Although several methods have been proposed, concept loss and concept confusion persist in recent T2I models when handling multi-object, multi-attribute prompts. In this paper, we conduct an embedding-level analysis to develop a training-free, inference-time solution for concept loss and concept confusion across CLIP-based T2I models. We find that (1) concepts mentioned later exhibit higher embedding entropy, reflecting less concentrated representations that are more often associated with concept loss, and (2) the first CLIP attention layer captures the strength of binding between each object and its attribute. Guided by our findings, we introduce TIE, a method that improves semantic alignment through a single text-embedding update. TIE addresses concept loss via entropy-aware singular value amplification and resolves concept confusion through interpolation-extrapolation binding based on CLIP attention scores, all in a training-free manner. Extensive experiments demonstrate that TIE enhances semantic fidelity in multi-concept scenarios with minimal sampling overhead. The project page is available at https://hong-sujung.github.io/TIE/.

Event-based spiking neural networks (SNNs) encode information through temporal firing dynamics, but the same stateful computation makes their predictions sensitive to event loss, timestamp jitter, and speed variation. These perturbations alter evidence accumulation, yet late-layer firing trajectories can retain error-diagnostic structure that is absent from the final logits alone. We introduce Perturbation-Aware Firing Scaffolds (PAFS), a labeled post-training calibration method that exploits this structure without updating the pretrained backbone. PAFS associates standardized late-layer leaky integrate-and-fire trajectories with the class-probability residuals of an Adapter anchor, then applies singular value decomposition to extract compact residual-aligned channel directions. At inference, firing trajectories from the same backbone pass are projected onto this fixed low-rank scaffold and combined with anchor statistics to predict a residual logit correction. Across four matched dataset-backbone settings spanning three event datasets and two spiking Transformer architectures, PAFS improves corrupted-average and worst-condition accuracy over the corresponding Adapter anchors, with maximum gains of 3.06 and 3.65 percentage points. In the DailyAction-DVS/Spikingformer setting, the added trainable parameters amount to approximately 0.34% of the frozen backbone.

Existing most-significant-digit-first (MSDF) accelerators serialize input-term processing, causing inner-product latency to increase with fan-in. This paper presents PARIS, an MSDF architecture that eliminates input-term serialization through parallel bit-plane reduction and shared carry-save residual selection. For $B$-bit operands, PARIS processes $B^2$ bit-position pairs, independent of fan-in within the supported tile, while generating exact MSDF outputs. Synthesized in 45\,nm at 100\,MHz, the 784-lane INT8 core occupies 0.008701\,mm$^2$ and completes an inner product in 88 cycles. Evaluation on two MNIST multilayer perceptrons demonstrates arithmetic-workload speedups of 240.44$\times$ and 180.47$\times$ over a matched reused-MSDF implementation, reducing arithmetic energy by 98.89\% and 98.58\%, respectively. A synthesized 16-engine accelerator occupies 0.90273\,mm$^2$ and meets the 100\,MHz timing constraint. Assuming immediate weight availability, it delivers a projected throughput of 24.33\,GOPS and an estimated energy efficiency of 1,581.14\,GOPS/W at unchanged mapped power. Bias-aware ReLU detection further reduces modeled arithmetic cycles by 5.52\% and 4.86\%. A separate 256-engine RTL implementation completes Model A in 259 cycles, demonstrating output-parallel scalability.