Peer Revenue Publish or profit

Papers

Fresh from arXiv, typeset properly. Highlighted words trade on the market.

All of arXiv

Sunday 6 September

Computation and Language

Used, Mentioned, or Condemned? A Controlled Contrast-Set Diagnostic for the Use-Mention Distinction in Code-Mixed Hinglish Misogyny Detection

Lexicon-driven misogyny detectors cannot, by construction, distinguish a slur used against a woman from the same slur mentioned in counter-speech ("don't call her that") – yet exactly this distinction governs whether moderation protects or silences the people discussing abuse. We study this problem in code-mixed Hinglish and make three contributions. First, we diagnose two evaluation artifacts on a publicly available redacted corpus: category-encoding anonymization placeholders leak the label (a no-learning rule scores 1.000), and even after they are neutralized misogynistic and benign comments occupy lexically disjoint registers, so bag-of-words reaches macro-F1 approximately 1.00 under random cross-validation but collapses under template-disjoint evaluation. Second, we release Hinglish-MGY-Diag, a deterministic generator and a 416-item / 163-minimal-pair contrast-set diagnostic across five linguistically motivated categories in which slur presence and gendered register are decorrelated from the label by construction. Third, we introduce a strict pair-consistency metric that credits a model only when both members of a minimal pair are correctly labelled. Five from-scratch classical baselines evaluated under construction-disjoint five-fold cross-validation reveal that the strongest model reaches 0.93 accuracy on the cleanest use-mention subset but only 0.82 consistency – it still mislabels roughly one counter-speech pair in five. A frontier LLM used as an author-model ceiling attains 1.000 on all metrics, doubling as independent label validation and confirming the benchmark is a capability gradient rather than an adversarial wall. We release all code, data, the generator, and an arms-length LLM harness for reproducing every number.
Read the full abstract

Multimedia

Causal Localization of the Refusal Direction in Audio Language Models

A large audio language model (LALM) attaches a speech front end to a text language model (LM) that is already safety-aligned. When such a model refuses a harmful spoken request, is the refusal carried by the front end, or inherited from the text LM? We test this with causal interventions. At each model's audio-to-LM interface and at tested LM residual layers, we fit a direction separating harmful from benign prompts, ablate its component, and measure the resulting change in the model's first-token refusal margin. Four of the five models are evaluated under held-out category shift. Across five LALMs spanning three backbone families, with three models passing a baseline safety gate, the largest tested effects occur in a mid-to-late LM band, while ablations of the tested interface directions have little effect. On Qwen2.5-Omni, ablating the L16 direction changes the margin by -7.10, versus -0.013 at the projector. The audio pathway is still in use: zeroing the encoder output changes the margin by -4.7. In the same model, the contrast is linearly decodable at an early layer where single-layer ablation has little effect, and a direction fitted on the LM backbone alone transfers to the full audio model. Because harmful and benign prompts also differ in form, we interpret the direction as refusal-linked rather than harmfulness-specific. These interventions localize dependence of the refusal margin, not where refusal is computed. Moving the margin also does not always change what the model writes. Safety audits of these models should use interventions rather than rely on probes alone, and should examine the inherited text LM alongside the audio interface.
Read the full abstract

Computation and Language

Which Part of the Context Layer Does the Work? Separating Semantic Content from Retrieval Scaffolding in Text-to-SQL Agents

Context layers, curated documentation that an analytics agent fetches at query time, produce large accuracy gains on text-to-SQL benchmarks. A with/without comparison cannot say which part of the layer does the work: the semantic content, the retrieval scaffolding that delivers it, or the pre-computed views that usually accompany it. We report a four-arm ablation on DABStep on four models that separates the three. The instrument is a data contract: a YAML artifact that carries a domain's semantics and the rules an agent's tools enforce. One arm empties every field of prose in the frozen contract while holding the tool surface, retrieval instruction, table allow-list and operation rules byte-for-byte fixed. Compiling the contract's own SQL expressions into views gives the ceiling a pre-computed layer would reach: gold on all 176 tasks it covers. Content dominates. It raises hard-task accuracy from 13.9% to 55.1%, 22.6% to 56.6%, 22.9% to 68.4% and 37.0% to 77.4%, beating the same knowledge pasted into the prompt on every model. Scaffolding without content is worth 0 to 5 points on two flash models and 14 to 15 on two frontier models. Against the compiled ceiling the contract arm's shortfall is a failure to derive, and it falls from 39 points to 5 with model capability. The contract beats the prompt because the rule it needs is one lookup away rather than buried in a long prompt: its SQL carries the fee semantics up to 98% of the time against the prompt arm's 4%, and at the lowest cost per correct answer on three of four models. For practitioners: semantics first, scaffolding second, pre-computed macros only where an agent demonstrably fails to derive. Ungoverned arms submitted 166 mutating statements; governed arms none. The gain is confined to the contract's domain. On one model the benchmark's own withheld golds grade the contract arm at 51.9% against 18.8% for the prompt baseline.
Read the full abstract

Machine Learning

RS-Claw-Evolution: Environment-Feedback-Driven Evolution for Lightweight Remote Sensing Agents in Long-Horizon Tasks

Large language model-driven remote sensing (RS) agents offer a promising approach to automating geospatial analysis. However, lightweight RS agents based on compact language models struggle with multi-step interactive tasks due to loss of long-horizon states, inefficient environmental feedback utilization, and sparse optimization signals. We propose RS-Claw-Evolution, an environment-feedback-driven framework that progressively improves lightweight agents through three stages. Interaction evolution uses executable code to control observations, maintain intermediate states, and reduce context redundancy. Experience evolution combines failure-aware trajectory generation with error-turn masking to learn from informative failure-recovery experiences without imitating faulty actions. Decision evolution uses reinforcement learning with multi-dimensional environment rewards and turn-level advantage protection to optimize tool-use behaviors and improve credit assignment in long sequences. On Earth-Bench, the optimized Qwen3-4B-based agent achieves 65.9% accuracy in Autonomous Planning mode, outperforming the untrained Qwen3-32B baseline (43.8%) and DeepSeek-V3.1 (60.8%), while approaching GPT-5 (71.6%). These results demonstrate that learning from environmental feedback can improve lightweight agents and narrow their performance gap with larger models in long-horizon RS tasks.
Read the full abstract

All authors Kai Ouyang, Dongyang Hou, Liangtian Liu, Zeyuan Wang, Ziyu Li, Chengfu Liu, Zichao Tang, Xuezhi Cui, Shengwu Ouyang, Wentao Yang, Hanwen Yu, Haifeng Li

Machine Learning

Strategy Accumulation and Guided Execution for Automated LLM Fine-Tuning

Producing task-specific large language models requires discovering effective training strategies through experimentation. Automated fine-tuning systems have made this experimentation feasible with far less manual effort. However, these systems are stateless: each search discards its discovered strategies, dataset insights, and hyperparameter findings once it ends. Every new task must then repeat this costly search from a cold start. To address this, we propose Strategy Accumulation and Guided Execution (SAGE), a two-stage framework that makes automated fine-tuning search cumulative. In the first stage, a multi-agent pipeline performs Monte Carlo Tree Search-based exploration. A parallel Distillation Agent extracts task-specific exploration records and confidence-scored cross-task insights, which together constitute a structured experience repository. In the second stage, SAGE retrieves relevant experience from this repository and selects what applies to guide training on the new task. We evaluate SAGE on nine unseen tasks spanning both single- and cross-category settings. In single-round execution, SAGE's accumulated experience raises the average relative improvement over baseline from 3.2% to 15.6%, a 12.4-percentage-point gain over the same pipeline without it. These results show that persistent strategy experience provides effective guidance for automated fine-tuning on unseen tasks.
Read the full abstract

All authors Haoran Zhao, Wei Du, Dingwen Yang, Jixuan Huang, Junlin Shang, Lingyong Fang, Ya Guo, Tao Gui, Qi Zhang, Xuanjing Huang

Computation and Language

DIPLOMAT: Dialogue-Span-Aware Direct Preference Optimization for Polite Persuasive Workplace Negotiation Dialogues

Effective workplace negotiation requires balancing multiple objectives, including achieving task goals, preserving professional relationships, and resolving conflicts constructively. However, misunderstandings, misaligned preferences, and interpersonal friction often impede successful outcomes. Politeness mitigates these challenges by fostering trust, reducing tension, and preventing escalation, and persuasive communication helps overcome resistance, align preferences, and guide participants toward mutually beneficial agreements. Motivated by these insights, we present DIPLOMAT, a dialogue system for polite and persuasive workplace negotiation. To support its development, we introduce PROWESS, a dataset of multi-turn workplace negotiation dialogues generated via a multi-agent framework and enriched withnegotiation strategies, politeness levels, persuasive strategies. DIPLOMAT is trained using Dialogue-Span-Aware Direct Preference Optimization (DSA-DPO), a novel preference learning objective that identifies key dialogue spans for preference alignment. This enables DIPLOMAT to generate contextually coherent responses that employ intended negotiation strategies, maintain politeness, and incorporate effective persuasion strategies throughout interactions. Automatic and human evaluation on PROWESS confirm that DIPLOMAT consistently outperforms baselines in generating coherent, polite, and persuasive negotiation responses.
Read the full abstract

All authors Bibhuti Jha, Rishikant Chigrupaatii, Priyanshu Priya, Asif Ekbal

Computation and Language

Deep Persona: A Psychologically Grounded Architecture and Evaluation Framework for Role-Playing Agents and Simulations

Existing approaches to persona simulation with Large Language Models (LLMs) mostly rely on shallow character descriptions that fail to sustain coherent character behavior across extended interactions. We introduce Deep Persona, a psychologically grounded, three-layered architecture that organizes personas into hierarchical levels of observable expression, latent beliefs, and core motivational drives, for constructing highly convincing role-playing agents. Governed by the principles of scripted determinism and bounded agency, the architecture restricts the model to a reactive engine guided by a structured internal script. We further propose a reference-free evaluation framework that benchmarks dialogue naturalness against empirical human distributions using established psychological clinical instruments and adversarial stress-tests. Empirical evaluation reveals that while LLMs achieve high pragmatic fluency, they exhibit systematic limitations in emotional expression and joint attention. In addition, we present a case study of two Deep Personas and evaluate them using the proposed framework, demonstrating that structured personas can produce interactions that more closely align with human conversational behavior.
Read the full abstract

All authors Rotem Dror, Zohar Elyoseph, Yuval Haber, Elad Refoua, Oshrat Ayalon, Adir Solomon

Machine Learning

Teacher Should Think Ahead: Adaptive Continuations for Reliable On-Policy Distillation

On-policy distillation (OPD) is a promising approach for transferring knowledge between language models, where a student receives dense token-level supervision along its own generated trajectories. However, teacher supervision can be unreliable when conditioned on incomplete or low-quality student prefixes. We identify Teacher Uncertainty Contraction (TUC), a systematic phenomenon whereby the teacher's predictive uncertainty decreases as it continues from a student-generated prefix. We theoretically characterize this trade-off through a variance-bias decomposition of teacher-branch gradients, showing that uncertainty contraction reduces variance while teacher-student path divergence increases bias, thereby favoring a finite continuation. Guided by this insight, we propose Adaptive-Continuations On-Policy Distillation (AC-OPD), which augments informative states along student rollouts with teacher continuations and adaptively selects their effective supervision horizons. Experiments on mathematical reasoning and code generation across model scales demonstrate that AC-OPD consistently improves over standard OPD. Controlled-continuations and matched-budget analyses further validate the adaptive-continuations design, highlighting adaptive teacher continuations as an effective principle for reliable on-policy distillation.The code will be made publicly available upon publication.
Read the full abstract

All authors Jingang Zhou, Yuyi Zhou, Haiyang Guo, Xukai Wang, Shuai Feng, Sirui Gao, Jian Xu, Qingpei Guo, Xu-Yao Zhang

Machine Learning

CAMFT: Conflict-Aware Mergeable Fine-Tuning for Large Language Models

Model merging has emerged as a promising paradigm for integrating multiple task-specific capabilities into a single large language model. However, existing methods predominantly focus on post-hoc processing of independently fine-tuned models, overlooking how the training phase itself impacts cross-task compatibility. Resolving parameter conflicts after fine-tuning is inherently sub-optimal. To address this, we propose CAMFT, a Conflict-Aware Mergeable Fine-Tuning method that makes task adaptation both efficient and mergeaware. CAMFT treats mergeability as a property shaped during fine-tuning, rather than only a problem to be solved after fine-tuning. By guiding each task to update sparse coordinates with lower cross-task conflict, CAMFT produces task updates that are efficient to train and more compatible for downstream model merging. Extensive experiments demonstrate that CAMFT outperforms standard finetuning baselines in multi-task merging scenarios. Codes are available at https://github.com/gyanchow/CAMFT-LLM.
Read the full abstract

All authors Jingang Zhou, Haiyang Guo, Yuan Ma, Han Zhu, Xu-Yao Zhang

Machine Learning

CALM: A Calibrated LLM Choice Network Framework for Activity-Based Traveler Simulation

We present CALM, a reproducible hybrid framework that integrates an optional large language model (LLM) activity planner with calibrated stochastic choice, shared network feedback, memory and habit, typed feasibility checks, and deterministic offline replay. Unlike trip-mode classifiers or diary-only generators, CALM executes a closed traveler-day loop and evaluates each generative module against an empirical, reproducible baseline. On the 2024 New York City Citywide Mobility Survey (CMS), 110,691 seven-mode trips are split by respondent into 78,487 training and 32,204 holdout trips. Training-only alternative-specific constant calibration reduces mean holdout mode Jensen-Shannon divergence from 0.15599 to 0.00394 across ten seeds. A matched live-LLM ablation then quantifies trade-offs among aggregate fit, temporal fit, behavioral persistence, and feasibility, while frozen prompt-response pairs support deterministic replay of downstream simulation. Controlled weather, delay, fare, and parking ladders further demonstrate consistent and interpretable responses under intervention. CALM contributes a reproducible protocol for integrating and evaluating generative planners in traveler simulation through person-disjoint calibration, matched module ablation, controlled stress testing, and end-to-end traceability.
Read the full abstract

Machine Learning

Predictors and Orchestrators: Parsimonious Machine Learning within an Agentic AI Harness for Multi-Horizon Karst Aquifer Forecasting

Forecasting karst aquifer dynamics is difficult because recharge responses are nonlinear, event-driven, and governed by strongly heterogeneous flow paths. This study develops and evaluates a deployment-aware framework for 1-12-week-ahead prediction of spring discharge and groundwater level using approximately 79 years of hydroclimatic observations from the Edwards Aquifer, Texas. Five model families were compared under a common temporal evaluation design: extreme gradient boosting, extremely randomized trees, long short-term memory, convolutional neural networks, and Transformers. Predictions were evaluated using coefficient of determination, Kling-Gupta efficiency, root-mean-square error, and agreement with operational drought thresholds. Extreme gradient boosting was consistently most reliable, with R2 at least 0.97, 0.96, and 0.94 across 1-4-, 5-8-, and 9-12-week horizons, respectively, and greater than 90% critical-stage agreement at the first three drought stages across all horizons. Deep models were competitive at short horizons but degraded progressively and exhibited isolated failures at longer lead times. We attribute this contrast to an alignment between tree partitioning and low-dimensional, axis-aligned hydroclimatic predictors, together with the tendency of neural models to smooth irregular extremes. The validated models were embedded in a five-agent operational architecture that automates data acquisition, model assignment, deterministic prediction, threshold monitoring, prospective verification, literature retrieval, and reporting. The contribution is therefore a transferable framework joining parsimonious model selection, leakage-aware multi-horizon evaluation, decision-relevant threshold skill, and auditable agentic automation.
Read the full abstract

All authors Pramod Lekhak, Chetan Sharma, Hakan Başağaoğlu, F. Paul Bertetti, Debaditya Chakraborty

Signal Processing

Outpainting: spatially extending aero-optic phase screens

Aero-optic effects distort light wave propagation near a high-speed aircraft, thereby degrading performance in airborne imaging and communication systems. Measuring aero-optic data through experiment is costly and the resulting data often has a limited spatial size. Further, alternative methods for simulating this data, including computational fluid dynamics and conventional phase screen generation algorithms (e.g., boiling flow), face drawbacks such as large computation time or inaccurate statistics. More recently, data-driven algorithms have been proposed that can synthesize data that matches relevant statistics of measured aero-optic data. However, these methods cannot spatially extend aero-optic data. In this paper, we introduce ReVAR-ext (Re-whitened Vector AutoRegression-extender), an algorithm that builds on an existing data-driven approach, ReVAR, to spatially extend measured aero-optic data (a process called outpainting) and match the spatial and temporal correlations of the measured data. ReVAR-ext generalizes the generation process of ReVAR by combining multiple sets of synthetic data with the input measured data. This approach generates multiple fixed-sized synthetic images, each of which overlaps with the input data, and then stitches them together. When paired with ReVAR, the ReVAR-ext algorithm can generate aero-optic data with arbitrary temporal duration and arbitrary spatial size. Our experiments show that extended data generated by ReVAR-ext closely matches the temporal power spectrum of two measured aero-optic data sets. Further, the extended data approximately matches the spatial autocorrelation, with reduced accuracy at large spatial lags and at vertical lags.
Read the full abstract

All authors Jeffrey W. Utley, Gregery T. Buzzard, Charles A. Bouman, Matthew R. Kemnetz

Computer Vision

Filling the Unseen: Scene Extrapolation via 3D Gaussian Splatting

3D Gaussian Splatting achieves photorealistic reconstruction within training view distribution, yet it degrades on out-of-distribution novel views, exhibiting holes in unobserved regions and artifacts in observable areas. Recent works formulate this task as extrapolation and interpolation and try to address it with generative models, but remain limited in extrapolation scale and quality. They repeat a generate-reconstruct-shift cycle to progressively build a scene, which introduces accumulated errors with every step conditioning on previous outcomes. In this work, we propose a holistic framework for extrapolation and interpolation. We devise an independent camera view detection mechanism to enable parallel conflict-free extrapolation, circumventing the reliance on the aforementioned error-prone cycle. Building upon this, we design a hierarchical pipeline that extrapolates independent and dependent camera views separately. Additionally, previous methods overlook inconsistency between generated and original images, resulting in compromising well-reconstructed areas. We propose a plug-and-play Quality-Aware Mask (QA-Mask) module, enabling selective utilization of generated data. By calibrating learning weights with pixel-wise rendering quality, it prevents generation-induced degradations on well-constructed areas. Extensive experiments demonstrate the superior performance of our framework, with QA-Mask generalizing to multiple generative reconstruction models.
Read the full abstract

All authors Yunlai Zhou, Yiren Lu, Tuo Liang, Disheng Liu, Vipin Chaudhary, Yu Yin

Multiagent Systems

From Process Loss to Assembly Bonus: Human-Grounded Diagnosis of Multi-Agent LLM Collaboration

LLM agents are increasingly used for collaborative problem solving and human-group simulation. This makes outcome-only evaluation insufficient: if LLM groups are used as models of human groups, we need to know whether they succeed or fail through human-like deliberative mechanisms. We compare human group chats with matched LLM deliberation traces on Wason-style deductive reasoning, then test whether the same process signatures generalize to analogical, abductive, and analytical tasks. Humans and LLMs show the same assembly bonus asymmetry: discussion improves the average member more often than the best initial member. Initial-answer diversity accounts for the effect of model heterogeneity, increasing movement in both corrective and destructive directions. The main differences are process-level. Compared with humans, LLM groups follow majorities more often, surface less unique information, and converge earlier; correct minority signals succeed mainly when re-expressed early. Interventions motivated by human group-decision research yield modest improvements in collective outcomes, but do not remove the coordination bottleneck. Together, these results suggest that LLM groups can reproduce some outcome-level patterns of human deliberation while diverging in the mechanisms that generate assembly bonus and process loss, with implications for group simulation and human-AI collaboration.
Read the full abstract

All authors Ala N. Tak, Teruhisa Misu, Kumar Akash, Zhaobo K. Zheng, Kevin H. Joo, Jonathan Gratch

Sound

From Masking to Merging: Rethinking SpecAugment for Efficient Audio Spectrogram Transformer

This paper proposes SpecAugment-Patch Merging, a simple yet effective method to accelerate Audio Spectrogram Transformer (AST) training. We first apply SpecAugment to mask input spectrograms at the patch level, and after positional embeddings are added, the method selects r pairs of masked patches and merges them, reducing the number of tokens processed by the Transformer. Increasing the number of merged pairs r from 0 to 100 keeps mAP on AudioSet nearly unchanged (34.07 to 34.08) while throughput increases from 43.3 to 49.3 samples/sec, which is a relatively 13.9% improvement. Similar patterns appear on ESC-50 and Speech Commands V2, where throughput steadily improves with only minor accuracy changes, demonstrating that this merging approach provides faster training with minimal performance loss.
Read the full abstract

Computer Vision

TryOnReward: Learning Foveated Consistency for Reinforcement Fine-Tuning of Virtual Try-On

Virtual Try-On (VTON) aims to dress a person with the reference garment, producing visually reasonable results aligned with human preferences. Turning this preference-oriented goal into an actionable objective relies on a scoring function aligned with human taste. However, classic fidelity metrics exhibit weak correlation with human judgments, and generic VLMs fail to provide the discriminative granularity demanded by try-on quality evaluation, which hinges on faithfully preserving garment and person details. This shortcoming is further exacerbated in the reinforcement fine-tuning (RFT) optimization and leads to severe reward hacking. To this end, we present TryOnReward, a fine-grained reward model tailored for VTON. Built on a vision-language backbone, it adopts a foveation calibration objective that grounds each quality dimension in the relevant region to avoid global shortcut learning. Meanwhile, TryOnReward jointly optimizes pairwise preferences and per-dimension quality scores via margin-aware supervision, leveraging both relative and absolute quality signals. For model training and evaluation, we build TryOnReward-100K, a human-annotated per-dimension rating dataset, alongside TryOn-Bench and TryOnRewardBench, two benchmarks covering diverse real scenarios. Extensive experiments confirm that TryOnReward significantly outperforms generic judges in human preference alignment, and when serving as the RFT reward function, it consistently yields human-preferred try-on results across multiple baselines.
Read the full abstract

All authors Xueheng Li, Yong Liu, Xiaolong Fu, Wen Xue, Chengjun Xie, Yipeng Sun, Yan Li, Simiu Gu

Computer Vision

Interpretable Temporal Video Reasoning with EventGraph and EventField

We present a structured temporal video reasoning pipeline built around a discrete EventGraph, a continuous EventField, and a human-readable EventGlyph view. On a calibrated EPIC-KITCHENS subset of 10 videos and 50 temporal reasoning questions, EventField+Glyph achieves 0.98 overall accuracy, which is higher than the caption baseline by +0.40 (paired p = 1.1 \times 10^{-5}) and direct VLM-only QA by +0.20 (p = 0.0063) on this subset. We further evaluate annotation-source variations, including manual, heuristic, and heuristic+Gemini pipelines, and find that the best structured method stays above the caption baseline across settings. We also include cross-video pair benchmarking and an appendix gallery of glyph outputs for all studied videos. Overall, the results indicate that structured temporal representations can support both performance and inspectability by preserving symbolic structure, capturing temporal continuity, and providing human-readable diagnostics for video reasoning.
Read the full abstract

Computer Vision

Sampling headroom is not selection gain: a compute-value audit of test-time scaling for video world models

Test-time scaling (TTS) can improve generation only when additional compute produces better candidates and the system can reliably identify them. This distinction is especially important for video world models, where a wider sample pool may contain stronger rollouts without improving the output that is ultimately selected. We introduce the Compute-Value Audit (CVA), a sequential framework that asks whether extra sampling creates opportunity, observable signals provide a reliable state, that state supports a beneficial action, and the resulting gain exceeds the full entry fee of generation and verification. On 192 Physics-IQ scenes, expanding the pool from 4 to 16 candidates increases oracle quality by +9.23 IQ (95% CI [+7.44, +11.14]), but Flow, Cycle, and VideoReward fail to recover this headroom reliably. Across three generators, none of twelve adaptive-depth policies outperforms uniform compute; they recover only 42-69% of the measured entry fee. A matched-60-NFE Predict-and-Perturb intervention on VideoPhy2 is likewise negative across three fresh-seed replicas. These negative results are not universal: anchor-explorer passes all four stages in a sparse PRM800K setting, MMLU-Pro exposes the gap between predictive state and useful action, and a privileged paired future establishes a positive video upper bound. Together, these results show that sampling headroom has deployment value only when it can be converted into a reliable decision whose benefit survives the complete compute charge. Code is available at https://github.com/YuhuaJiang2002/sampling-headroom-is-not-selection-gain.
Read the full abstract

Disordered Systems and Neural Networks

Localization Landscapes as Operator-Induced Geometry for Heterogeneous Systems

Heterogeneous operators often organize response through hidden barriers, wells, and weakly communicating compartments that are not faithfully described by Euclidean distance or raw graph connectivity alone. We study this structure through the localization landscape, obtained from a single source solve, and the associated effective potential $W_{\mathrm{eff}} = 1/u$. Starting from both discrete Schrödinger-type operators and heterogeneous reaction-diffusion operators, we show how $W_{\mathrm{eff}}$ induces effective wells, basin partitions, and Agmon-type neighborhoods that serve as an operator-aware geometry for localization and transport. This geometry explains the spatial support of low-energy eigenmodes, produces adaptive receptive fields on a fixed graph, sharpens locality in attention-like interactions, and yields bottleneck-sensitive modulation of diffusion. We also include a finite-element reaction-diffusion example with strongly compartmentalized coefficients, demonstrating that the same framework extends beyond simple grid operators to heterogeneous continuum systems. The results support a precise conclusion: localization-landscape geometry is a strong inductive bias when relevance is controlled by confinement, barriers, and low-energy accessibility, but its benefits are task-dependent rather than universal.
Read the full abstract

Computer Vision

A Comprehensive Review of Multimodal Facial State Analysis: Tasks, Methods, and Resources

Facial state analysis plays a crucial role in understanding human expressions, psychological modeling, and human computer interaction. Traditional unimodal vision-based methods are often limited by environmental sensitivity and weak interpretability. Multimodal facial state analysis addresses these issues by integrating complementary cues from visual, audio, textual, physiological, and other related modalities. This survey emphasizes two key aspects: on one hand, multimodal learning enables contextual semantic understanding for improved facial state reasoning and leverages interpretable language generation to enhance model explainability; on the other hand, multi-task learning allows simultaneous analysis of expressions, action units (AUs), and face-based soft biometrics (e.g., age, gender), effectively capturing fine-grained expressions and improving cross-scene generalization. This survey reviews core tasks, representative methods, and datasets in multimodal facial state analysis, focusing on facial expression recognition, AU detection, and face-based soft biometric estimation, and emphasizing the unique value of language in providing contextual semantics, enhancing reasoning, and generating explanations. The survey aims to provide an up-to-date overview of the literature and to highlight future research directions for multimodal, interpretable, and multi-task adaptive facial state analysis.
Read the full abstract

All authors Xuri Ge, Tianshuo Zhang, Ruihan Li, Hui Ye, Kaiwen Zheng, Junchen Fu, Da Huo, Joemon M. Jose, Hu Han

Computer Vision

(How) Do MLLMs Report Bistable Images Like Humans?

Bistable images such as the duck-rabbit are classic stimuli in which one image supports multiple mutually incompatible interpretations, typically reported one at a time in humans. We ask whether multimodal large language models (MLLMs) show similar report behavior and what internal computations support it. Using the LLaVA family, we study two tractable dimensions: modulability, whether reports can be biased by bottom-up visual cues and top-down linguistic priors, and exclusivity, whether responses commit to a single interpretation. We test both on the canonical duck-rabbit and on synthetic Visual Anagrams to mitigate memorization confounds. Behaviorally, both visual and linguistic manipulations systematically shift reports in human-consistent ways, while responses remain predominantly exclusive. Mechanistically, these effects arise from competing image-token representations, distinct pathways for bottom-up and top-down modulation, and a link between exclusive reporting and object-count encoding. Code and data are available at https://github.com/rtakatsky/mllm-bistable-images.
Read the full abstract

All authors Ryota Takatsuki, Tomoki Doi, Amane Watahiki, Anil K. Seth, Hitomi Yanaka

Statistical Methodology

Maximizing the magnitude of Strictly Standardized Mean Difference of a Linear Combination

The strictly standardized mean difference (SSMD) is an interpretable, unit-free effect size originally developed for quality control and hit selection in high-throughput screening and subsequently extended to effect-size assessment and error-rate control. Existing SSMD theory considers one variable at a time. Here, we extend SSMD to a linear combination of multiple variables and determine the coefficients that maximize the resulting SSMD. We show that this optimization can be formulated as a generalized Rayleigh quotient with a closed-form solution and identify conditions under which the optimal direction coincides with Fisher's linear discriminant. We derive method-of-moments, bias-corrected, and maximum-likelihood estimators of the maximized SSMD and construct confidence intervals based on Hotelling's T-squared statistic and the noncentral F distribution under different correlation and variance structures. We also characterize classification cutoffs for the resulting linear score and establish its relationship with the area under the receiver operating characteristic curve (AUROC). Simulations show that SSMD maximization coincides with Fisher's linear discriminant and logistic regression under equal covariance but diverges under unequal covariance and class imbalance. In paired designs, SSMD maximization uniquely incorporates cross-covariance information. Linear support vector machines are also evaluated as a modern comparator. This framework provides an interpretable approach to constructing multivariable biomarkers and signatures for high-throughput screening, cytokine profiling, metabolomics, salivary diagnostics, and continuous-monitoring applications.
Read the full abstract

Differential Geometry

A Metric with Positive Sectional Curvature on $S^3\times S^3$

We construct a smooth Riemannian metric with strictly positive sectional curvature on \(S^3\times S^3\). Since \(S^3\times S^3\) is even-dimensional and has Euler characteristic zero, our result disproves the positive-curvature case of Hopf's sign conjecture. The metric and the proof were discovered by the Odin Automatic AI Research Agent.
Read the full abstract

Differential Geometry

Future Completeness, $C^0$-Inextendibility and Cauchy Horizons in Homogeneous Einstein Spacetimes

We prove the future-completeness conjecture of Gödeke and Rendall for expanding spatially homogeneous vacuum spacetimes in four spatial dimensions. More generally, an expansion-energy estimate gives future timelike and null geodesic completeness for homogeneous Einstein equations coupled to maps into complete Riemannian targets, through nine spatial dimensions for vanishing potential. In arbitrary dimension we obtain an affine-length criterion which includes positive potential floors and potentials that decay sufficiently slowly along the scalar trajectory. For future-global homogeneous solutions, the critical nine-dimensional bound also holds for a general stress tensor in an explicit normal energy-condition window, including a broad range of perfect fluids. At the opposite time end, we establish a quotient-stable $C^0$-inextendibility criterion for two-step nilpotent cosmologies. Its proof combines boundary localization with an optimal, intrinsically defined allocation of the central correction in timelike homotopies, and continues to apply when the diameter of compact spatial slices collapses. Exact Heisenberg solutions realize both conclusions. On every fixed compact Bianchi~II quotient, the expanding invariant vacuum data split into an open dense set with globally $C^0$-inextendible developments and a codimension-two locally rotationally symmetric locus with analytic compact Cauchy horizons. We determine the chronology-violating region of the exceptional extensions and quantify the exponentially small proper-time scale on which transverse anisotropy replaces the horizon by a singular end.
Read the full abstract

Logic

Inequalities and equalities of means in Constructive Mathematics

We study the inequalities and equalities of means of numbers in constructive mathematics. The parameters of such means are constructive real numbers. We show that it is impossible to have an algorithm that can always decide whether the two means are equal or not. Of course, this problem can always be solved if the parameters are rational numbers.
Read the full abstract

Logic

Tag-system computation using only powers and principal logarithms

I show that one exact step of any tag system can be written as a single fixed expression using only powers and logarithms. A tag state is represented as an integer; evaluating the expression yields the integer encoding of the next configuration, and feeding the answer back into the same expression follows the computation step by step. The discrete part of the update comes from leveraging the wraparound in the principal complex logarithm, which effectively serves the same purpose as floor, mod, or sin in comparable approaches. The iterating expressions use only $x^y$ and $\log_b a$: it turns out that these two binary operations are sufficient, with no need for constants. It follows that reachability below a fixed threshold is undecidable for one fixed expression. As a separate application, the same mechanism represents addition, $2^x$, and remainder with the convention $x\bmod0=x$, and hence every Kalmár elementary function.
Read the full abstract

General Physics

Exploring the Observational Constraints and Cosmological Dynamics in f(Q,L_m) Gravity

We explore two scenarios of $f(Q,\mathcal{L}_m)$ gravity: linear and non-linear gravity models. The dynamical system analysis identifies two critical points for each of the proposed linear and nonlinear matter–geometry coupling models. These equilibrium points correspond to distinct phases of cosmic evolution. Depending on the model parameters, the resulting critical points successfully reproduce the observed sequence of cosmic evolution, from a decelerated matter-dominated Universe to the present epoch of accelerated expansion. The effective equation of state parameter ($\omega_{\text{eff}}$) and the deceleration parameter ($q$) exhibit smooth transitions from decelerated to accelerated expansion, with transition epochs around $N_{\text{tr}} \approx -0.27$ for linear Model and $N_{\text{tr}} \approx -0.32$ for non-linear Model, consistent with late-time cosmic acceleration. Statistical constraints derived from CC+BAO, DESI DR II, and Pantheon$^+$ datasets provide best-fit values for the model parameters ($\alpha, \beta, \gamma, H_0$), showing compatibility with current cosmological observations. The analysis employs Akaike (AIC) and Bayesian (BIC) information criteria to evaluate model performance. Our results demonstrate that $f(Q,\mathcal{L}_m)$ gravity provides a viable alternative framework for explaining late-time acceleration, with rich dynamical features that merit further exploration in view of upcoming high-precision surveys.
Read the full abstract

All authors Ratul Mandal, Anamika Kotal, Vipin Kumar Sharma, Ujjal Debnath

Software Engineering

ReqEvolve: User-Oriented Software Self-Evolution through Automatic Requirement Interpretation

The paradigm of software self-evolution enables systems to autonomously extend and reconfigure their own capabilities during execution in response to technical specifications. Yet requests for new functionality often originate from end users and are rarely expressed in technical terms. As a result, developers must translate user needs into technical specifications before the system can evolve, delaying early validation of the requested functionality by preventing users from immediately observing the resulting behaviour. To address this gap, we present ReqEvolve, a runtime code generation system that enables user-driven self-evolution by accepting high-level user requests. The system integrates automatic requirements engineering (RE) and test-driven development (TDD) to transform these requests into executable functionality through clarification, specification decomposition, test generation, and runtime integration. We evaluate ReqEvolve on 72 software evolution cases across 18 projects against two baselines: SpecFix, an RE-focused code generation approach, and an ablation variant of our system. ReqEvolve achieves 89.2% Pass@1, outperforming SpecFix by 18.8% (p < 0.01, r = 0.79, large effect) and the ablation baseline by 32.6% (p < 0.001, r = 0.88, large effect). These results provide initial evidence that user-driven self-evolution is a viable paradigm for autonomously extending software capabilities from user requests, thereby accelerating requirements validation prior to developer verification.
Read the full abstract

Machine Learning

Halo: Improving forecast accuracy through heteroscedastic estimation

Heteroscedastic forecasting, where a network estimates a scale parameter alongside a location parameter, is normally motivated by uncertainty quantification. This paper shows it also improves the point estimate, in contrast to reported negative results for heteroscedastic estimation outside time series. Halo is a modification that reuses an existing deep forecaster's architecture, giving it a second output for the scale of its implied distribution and training it under the matching negative log likelihood. Adapting three state-of-the-art models — a transformer, a graph network paired with a variational autoencoder, and a single-layer convolutional network — under both Gaussian and Laplacian losses demonstrates the phenomenon. On the five electricity price markets of a standard forecasting benchmark, Halo improves MSE and MAE in 28 of 30 model-market-metric comparisons, cutting average MSE by 2.6% to 16.5% and average MAE by 1.7% to 11.0%. Two findings emerge: (1) whether the scale estimate comes from a second projection head or from a full parallel network matters far less than whether the network estimates scale, and (2) the improvement holds under the hyperparameters already tuned for the point-estimate baseline, so retuning is optional.
Read the full abstract

Neural and Evolutionary Computing

Threshold-Based Selection for Continuous Optimization: A Leaf-Abscission Instantiation

This paper formalizes threshold-based selection as an evaluation-gating architecture in which each incumbent is tested before variation and a replacement is generated and evaluated only when contextual pressure exceeds intrinsic strength. The mechanism is instantiated as Leaf Abscission Optimization (LAO), using rank-based strength, a phenological seasonal signal, diversity modulation, environmental pressure, and a base regrowth kernel. A blocked two-to-the-fourth-power factorial analysis at dimension 10 on the CEC 2017 suite reduces the original multi-layer design to a parsimonious core: drift is harmful, while the other three auxiliary layers show no robust independent evidence of benefit. The resulting LAO-Core attains the third-best mean Friedman rank among nine optimizers at dimensions 10, 30, and 50 under the equal evaluation budget. A four-budget sweep shows budget-dependent relative performance, with adaptive differential-evolution baselines gaining relative advantage at larger budgets; the nine-cell dimension-budget analysis establishes neither an evaluation-budget-per-dimension-only law nor a statistically significant dimension-budget interaction. A paired intervention shows that diversity modulation changes late-run replacement behaviour without a detectable effect on final error at the tested budget. The evidence supports LAO as a parsimonious evaluation-gating mechanism with regime-qualified competitiveness, rather than as a generally superior optimizer.
Read the full abstract