# Research Papers — 2026-04 · bundle page 139 of 233

> Full-text markdown of papers #6901–6950 of 11612 published in 2026-04, newest first. AI-readable mirrors of the full 11612-paper 2026-04 archive (50 papers per file).

Canonical page: https://aipod.dev/papers/archive/2026-04/page/139
[← Previous bundle](https://aipod.dev/papers/archive/2026-04/page/138.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-04/page/140.md)

### DDO-RM: Distribution-Level Policy Improvement after Reward Learning

Authors: Tiantian Zhang, Jierui Zuo, Michael Chen, Wenping Wang
Published: 2026-04-13
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2604.11119v2

Recent theory suggests that reward-model-first methods can be more sample-efficient than direct policy fitting when the reward function is statistically simpler than the induced policy. We propose DDO-RM, a finite-candidate decision-optimization method that converts reward scores into an explicit target distribution. Unlike PPO-based RLHF or DPO, DDO-RM performs a KL-regularized mirror-descent update to project the policy toward a reward-improved distribution over a candidate set. Preliminary experiments on Pythia-410M show that DDO-RM outperforms DPO in pair accuracy (0.52 to 0.56) and mean margin (0.13 to 0.53). Our framework provides a principled connection between reward learning and mirror-descent policy improvement.

---

### Distributionally Robust K-Means Clustering

Authors: Vikrant Malik, Taylan Kargin, Babak Hassibi
Published: 2026-04-13
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2604.11118v1

K-means clustering is a workhorse of unsupervised learning, but it is notoriously brittle to outliers, distribution shifts, and limited sample sizes. Viewing k-means as Lloyd--Max quantization of the empirical distribution, we develop a distributionally robust variant that protects against such pathologies. We posit that the unknown population distribution lies within a Wasserstein-2 ball around the empirical distribution. In this setting, one seeks cluster centers that minimize the worst-case expected squared distance over this ambiguity set, leading to a minimax formulation. A tractable dual yields a soft-clustering scheme that replaces hard assignments with smoothly weighted ones. We propose an efficient block coordinate descent algorithm with provable monotonic decrease and local linear convergence. Experiments on standard benchmarks and large-scale synthetic data demonstrate substantial gains in outlier detection and robustness to noise.

---

### Quantum-Gated Task-interaction Knowledge Distillation for Pre-trained Model-based Class-Incremental Learning

Authors: Linjie Li, Huiyu Xiao, Jiarui Cao, Zhenyu Wu, Yang Ji
Published: 2026-04-13
Categories: cs.LG, cs.CV
arXiv: https://arxiv.org/abs/2604.11112v1

Class-incremental learning (CIL) aims to continuously accumulate knowledge from a stream of tasks and construct a unified classifier over all seen classes. Although pretrained models (PTMs) have shown promising performance in CIL, they still struggle with the entanglement of multi-task subspaces, leading to catastrophic forgetting when task routing parameters are poorly calibrated or task-level representations are rigidly fixed. To address this issue, we propose a novel Quantum-Gated Task-interaction Knowledge Distillation (QKD) framework that leverages quantum gating to guide inter-task knowledge transfer. Specifically, we introduce a quantum-gated task modulation gating mechanism to model the relational dependencies among task embedding, dynamically capturing the sample-to-task relevance for both joint training and inference across streaming tasks. Guided by the quantum gating outputs, we perform task-interaction knowledge distillation guided by these task-embedding-level correlation weights from old to new adapters, enabling the model to bridge the representation gaps between independent task subspaces. Extensive experiments demonstrate that QKD effectively mitigates forgetting and achieves state-of-the-art performance.

---

### Use of AI Tools: Guidelines to Maintain Academic Integrity in Computing Colleges

Authors: Hatem M. El-boghdadi, Toqeer Ali Syed, Ali Akarma, Qamar Wali
Published: 2026-04-13
Categories: cs.CY, cs.AI, cs.CL, cs.ET
arXiv: https://arxiv.org/abs/2604.11111v1

The rapid adoption of AI tools such as ChatGPT has significantly transformed academic practices, offering considerable benefits for both students and faculty in computing disciplines. These tools have been shown to enhance learning efficiency, academic self-efficacy, and confidence. However, their increasing use also raises pressing concerns regarding the preservation of academic integrity -- an essential pillar of the educational process. This paper explores the implications of widespread AI tool usage within computing colleges, with a particular focus on how to align their use with the principles of academic honesty. We begin by classifying common assessment techniques employed in computing education and examine how each may be impacted by AI-assisted tools. Building on this foundation, we propose a set of general guidelines applicable across various assessment formats to help instructors responsibly integrate AI tools into their pedagogy. Furthermore, we provide targeted, assessment-specific recommendations designed to uphold educational objectives while mitigating risks of academic misconduct. These guidelines serve as a practical framework for instructors aiming to balance the pedagogical advantages of AI tools with the imperative of maintaining academic integrity in computing education. Finally, we introduce a formal model that provides a structured mathematical framework for evaluating student assessments in the presence of AI-assisted tools.

---

### Record-Remix-Replay: Hierarchical GPU Kernel Optimization using Evolutionary Search

Authors: Daniel Nichols, Konstantinos Parasyris, Caetano Melone, Tal Ben-Nun, Giorgis Georgakoudis, Harshitha Menon
Published: 2026-04-13
Categories: cs.DC, cs.AI, cs.LG, cs.PF
arXiv: https://arxiv.org/abs/2604.11109v1

As high-performance computing and AI workloads become increasingly dependent on GPUs, maintaining high performance across rapidly evolving hardware generations has become a major challenge. Developers often spend months tuning scientific applications to fully exploit new architectures, navigating a complex optimization space that spans algorithm design, source implementation, compiler flags and pass sequences, and kernel launch parameters. Existing approaches can effectively search parts of this space in isolation, such as launch configurations or compiler settings, but optimizing across the full space still requires substantial human expertise and iterative manual effort. In this paper, we present Record-Remix-Replay (R^3), a hierarchical optimization framework that combines LLM-driven evolutionary search, Bayesian optimization, and record-replay compilation techniques to efficiently explore GPU kernel optimizations from source-level implementation choices down to compiler pass ordering and runtime configuration. By making candidate evaluation fast and scalable, our approach enables practical end-to-end search over optimization dimensions that are typically treated separately. We show that Record-Remix-Replay can optimize full scientific applications better than traditional approaches over kernel parameters and compiler flags, while also being nearly an order of magnitude faster than modern evolutionary search approaches.

---

### Frugal Knowledge Graph Construction with Local LLMs: A Zero-Shot Pipeline, Self-Consistency and Wisdom of Artificial Crowds

Authors: Pierre Jourlin
Published: 2026-04-13
Categories: cs.AI, cs.IR, cs.LG, cs.NE
arXiv: https://arxiv.org/abs/2604.11104v1

This paper presents an empirical study of a multi-model zero-shot pipeline for knowledge graph construction and exploitation, executed entirely through local inference on consumer-grade hardware. We propose a reproducible evaluation framework integrating two external benchmarks (DocRED, HotpotQA), WebQuestionsSP-style synthetic data, and the RAGAS evaluation framework in an automated pipeline. On 500 document-level relations, our system achieves an F1 of 0.70 $\pm$ 0.041 in zero-shot, compared to 0.80 for supervised DREEAM. Text-to-query achieves an accuracy of 0.80 $\pm$ 0.06 on 200 samples. Multi-hop reasoning achieves an Exact Match (EM) of 0.46$\pm$0.04 on 500 HotpotQA questions, with a RAGAS faithfulness of 0.96 $\pm$ 0.04 on 50 samples. Beyond the pipeline, we study diversity mechanisms for difficult multi-hop reasoning. On 181 questions unsolvable at zero temperature, self-consistency (k=5, T =0.7) recovers up to 23% EM with a single Mixture-of-Experts (MoE) model, but the cross-model oracle (3 architectures x 5 samples) reaches 46.4%. We highlight an agreement paradox: strong consensus among samples signals collective hallucination rather than a reliable answer, echoing the work of Moussa{ï}d et al. on the wisdom of crowds. Extending to the full pipeline (500 questions), self-consistency (k=3) raises EM from 0.46 to 0.48 $\pm$ 0.04. A confidence-routing cascade mechanism (Phi-4 $\rightarrow$ GPT-OSS, k=5) achieves an EM of 0.55 $\pm$ 0.04, the best result obtained, with 45.4% of questions rerouted. Finally, we show that V3 prompt engineering applied to other models does not reproduce the gains observed with Gemma-4, confirming the specific prompt/model interaction. The entire system runs in $\sim$5 h on a single RTX 3090, without any training, for an estimated carbon footprint of 0.09 kg CO2 eq.

---

### ActorMind: Emulating Human Actor Reasoning for Speech Role-Playing

Authors: Xi Chen, Wei Xue, Yike Guo
Published: 2026-04-13
Categories: cs.SD, cs.AI
arXiv: https://arxiv.org/abs/2604.11103v2

Role-playing has garnered rising attention as it provides a strong foundation for human-machine interaction and facilitates sociological research. However, current work is confined to textual modalities, neglecting speech, which plays a predominant role in daily life, thus limiting genuine role-playing. To bridge this gap, we conceptualize and benchmark speech role-playing through ActorMindBench, and we present a corresponding reasoning framework, called ActorMind. Specifically, (1) Speech Role-Playing enables models to deliver spontaneous responses with personalized verbal traits based on their role, the scene, and spoken dialogue. (2) ActorMindBench is a hierarchical benchmark comprises Utterance-Level content with 7,653 utterances, Scene-Level content with 313 scenes, and Role-Level content with 6 roles. (3) ActorMind is an off-the-shelf, multi-agent, chain-of-though style reasoning framework that emulates how human actors perform in theaters. Concretely, ActorMind first reads its assigned role description via Eye Agent, then comprehends emotional cues within contextual spoken dialogues through Ear Agent. Subsequently, Brain Agent generates a descriptive emotional state, and finally, Mouth Agent delivers the scripts infused with corresponding emotion state. Experimental results demonstrate the effectiveness of ActorMind in enhancing speech role-playing.

---

### OmniScript: Towards Audio-Visual Script Generation for Long-Form Cinematic Video

Authors: Junfu Pu, Yuxin Chen, Teng Wang, Ying Shan
Published: 2026-04-13
Categories: cs.CV, cs.MM
arXiv: https://arxiv.org/abs/2604.11102v1

Current multimodal large language models (MLLMs) have demonstrated remarkable capabilities in short-form video understanding, yet translating long-form cinematic videos into detailed, temporally grounded scripts remains a significant challenge. This paper introduces the novel video-to-script (V2S) task, aiming to generate hierarchical, scene-by-scene scripts encompassing character actions, dialogues, expressions, and audio cues. To facilitate this, we construct a first-of-its-kind human-annotated benchmark and propose a temporally-aware hierarchical evaluation framework. Furthermore, we present OmniScript, an 8B-parameter omni-modal (audio-visual) language model tailored for long-form narrative comprehension. OmniScript is trained via a progressive pipeline that leverages chain-of-thought supervised fine-tuning for plot and character reasoning, followed by reinforcement learning using temporally segmented rewards. Extensive experiments demonstrate that despite its parameter efficiency, OmniScript significantly outperforms larger open-source models and achieves performance comparable to state-of-the-art proprietary models, including Gemini 3-Pro, in both temporal localization and multi-field semantic accuracy.

---

### Generating Hadamard matrices with transformers

Authors: Geordie Williamson, Oded Yacobi, Paul Zinn-Justin
Published: 2026-04-13
Categories: math.CO, cs.LG
arXiv: https://arxiv.org/abs/2604.11101v2

We present a new method for constructing Hadamard matrices that combines transformer neural networks with local search in the PatternBoost framework. Our approach is designed for extremely sparse combinatorial search problems and is particularly effective for Hadamard matrices of Goethals--Seidel type, where Fourier methods permit fast scoring and optimisation. For orders between 100 and 200, it produces large numbers of inequivalent Hadamard matrices, and for larger orders, it succeeds where local search from random initialisation fails. The largest example found by our method has order 252. In addition to these new constructions, our experiments reveal that the transformer can discover and exploit useful hidden symmetry in the search space.

---

### Efficient Transceiver Design for Aerial Image Transmission and Large-scale Scene Reconstruction

Authors: Zeyi Ren, Jialin Dong, Wei Zuo, Yikun Wang, Bingyang Cheng, Sheng Zhou, Zhisheng Niu
Published: 2026-04-13
Categories: cs.CV, cs.LG, eess.SP
arXiv: https://arxiv.org/abs/2604.11098v2

Large-scale three-dimensional (3D) scene reconstruction in low-altitude intelligent networks (LAIN) demands highly efficient wireless image transmission. However, existing schemes struggle to balance severe pilot overhead with the transmission accuracy required to maintain reconstruction fidelity. To strike a balance between efficiency and reliability, this paper proposes a novel deep learning-based end-to-end (E2E) transceiver design that integrates 3D Gaussian Splatting (3DGS) directly into the training process. By jointly optimizing the communication modules via the combined 3DGS rendering loss, our approach explicitly improves scene recovery quality. Furthermore, this task-driven framework enables the use of a sparse pilot scheme, significantly reducing transmission overhead while maintaining robust image recovery under low-altitude channel conditions. Extensive experiments on real-world aerial image datasets demonstrate that the proposed E2E design significantly outperforms existing baselines, delivering superior transmission performance and accurate 3D scene reconstructions.

---

### CDPR: Cross-modal Diffusion with Polarization for Reliable Monocular Depth Estimation

Authors: Rongjia Yu, Tong Jia, Hao Wang, Xiaofang Li, Xiao Yang, Zinuo Zhang, Cuiwei Liu
Published: 2026-04-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.11097v1

Monocular depth estimation is a fundamental yet challenging task in computer vision, especially under complex conditions such as textureless surfaces, transparency, and specular reflections. Recent diffusion-based approaches have significantly advanced performance by reformulating depth prediction as a denoising process in the latent space. However, existing methods rely solely on RGB inputs, which often lack sufficient cues in challenging regions. In this work, we present CDPR - Cross-modal Diffusion with Polarization for Reliable Monocular Depth Estimation - a novel diffusion-based framework that integrates physically grounded polarization priors to enhance estimation robustness. Specifically, we encode both RGB and polarization (AoLP/DoLP) images into a shared latent space via a pre-trained Variational Autoencoder (VAE), and dynamically fuse multi-modal information through a learnable confidence-aware gating mechanism. This fusion module adaptively suppresses noisy signals in polarization inputs while preserving informative cues, particularly around reflective or transparent surfaces, and provides the integrated latent representation for subsequent monocular depth estimation. Beyond depth estimation, we further verify that our framework can be easily generalized to surface normal prediction with minimal modification, showcasing its scalability to general polarization-guided dense prediction tasks. Experiments on both synthetic and real-world datasets validate that CDPR significantly outperforms RGB-only baselines in challenging regions while maintaining competitive performance in standard scenes.

---

### Efficient Training for Cross-lingual Speech Language Models

Authors: Yan Zhou, Qingkai Fang, Yun Hong, Yang Feng
Published: 2026-04-13
Categories: cs.CL, cs.AI, cs.SD
arXiv: https://arxiv.org/abs/2604.11096v1

Currently, large language models (LLMs) predominantly focus on the text modality. To enable more natural human-AI interaction, speech LLMs are emerging, but building effective end-to-end speech LLMs remains challenging due to limited data and the difficulty in expanding to more languages. In this paper, we introduce Cross-lingual Speech Language Model (CSLM), an efficient training method for cross-lingual speech LLMs based on discrete speech tokens. We propose a novel alignment strategy that achieves cross-modal and cross-lingual alignment through continual pre-training. By conducting instruction fine-tuning following a speech-text interleaved chain-of-modality generation process, we enhance modal alignment at a finer granularity, thereby improving generation quality and reducing latency. CSLM aligns different modalities and languages simultaneously without the need for massive speech data, thus exhibiting good language scalability. Evaluations on cross-modal tasks, mono-lingual conversational tasks, and cross-lingual conversational tasks demonstrate CSLM's strong cross-modal alignment capabilities and general task abilities. (Code is available at: https://github.com/ictnlp/CSLM)

---

### Bottleneck Tokens for Unified Multimodal Retrieval

Authors: Siyu Sun, Jing Ren, Zhaohe Liao, Dongxiao Mao, Xiangyuan Ren, Yiyi Zhang, Haohua Zhao, Weixiong Lin, Jiang Shaohua, Liqing Zhang, Yuchao Zheng
Published: 2026-04-13
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2604.11095v1

Adapting decoder-only multimodal large language models (MLLMs) for unified multimodal retrieval faces two structural gaps. First, existing methods rely on implicit pooling, which overloads the hidden state of a standard vocabulary token (e.g., <EOS>) as the sequence-level representation, a mechanism never designed for information aggregation. Second, contrastive fine-tuning specifies what the embedding should match but provides no token-level guidance on how information should be compressed into it. We address both gaps with two complementary components. Architecturally, we introduce Bottleneck Tokens (BToks), a small set of learnable tokens that serve as a fixed-capacity explicit pooling mechanism. For training, we propose Generative Information Condensation: a next-token prediction objective coupled with a Condensation Mask that severs the direct attention path from target tokens to query tokens. All predictive signals are thereby forced through the BToks, converting the generative loss into dense, token-level supervision for semantic compression. At inference time, only the input and BToks are processed in a single forward pass with negligible overhead over conventional last-token pooling. On MMEB-V2 (78 datasets, 3 modalities, 9 meta-tasks), our approach achieves state-of-the-art among 2B-scale methods under comparable data conditions, attaining an Overall score of 59.0 (+3.6 over VLM2Vec-V2) with substantial gains on semantically demanding tasks (e.g., +12.6 on Video-QA).

---

### E2E-REME: Towards End-to-End Microservices Auto-Remediation via Experience-Simulation Reinforcement Fine-Tuning

Authors: Lingzhe Zhang, Yunpeng Zhai, Tong Jia, Minghua He, Chiming Duan, Zhaoyang Liu, Bolin Ding, Ying Li
Published: 2026-04-13
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2604.11094v1

Contemporary microservice systems continue to grow in scale and complexity, leading to increasingly frequent and costly failures. While recent LLM-based auto-remediation approaches have emerged, they primarily translate textual instructions into executable Ansible playbooks and rely on expert-crafted prompts, lacking runtime knowledge guidance and depending on large-scale general-purpose LLMs, which limits their accuracy and efficiency. We introduce \textit{End-to-End Microservice Remediation} (E2E-MR), a new task that requires directly generating executable playbooks from diagnosis reports to autonomously restore faulty systems. To enable rigorous evaluation, we build \textit{MicroRemed}, a benchmark that automates microservice deployment, failure injection, playbook execution, and post-repair verification. We further propose \textit{E2E-REME}, an end-to-end auto-remediation model trained via experience-simulation reinforcement fine-tuning. Experiments on public and industrial microservice platforms, compared with nine representative LLMs, show that E2E-REME achieves superior accuracy and efficiency.

---

### LDEPrompt: Layer-importance guided Dual Expandable Prompt Pool for Pre-trained Model-based Class-Incremental Learning

Authors: Linjie Li, Zhenyu Wu, Huiyu Xiao, Yang Ji
Published: 2026-04-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.11091v1

Prompt-based class-incremental learning methods typically construct a prompt pool consisting of multiple trainable key-prompts and perform instance-level matching to select the most suitable prompt embeddings, which has shown promising results. However, existing approaches face several limitations, including fixed prompt pools, manual selection of prompt embeddings, and strong reliance on the pretrained backbone for prompt selection. To address these issues, we propose a \textbf{L}ayer-importance guided \textbf{D}ual \textbf{E}xpandable \textbf{P}rompt Pool (\textbf{LDEPrompt}), which enables adaptive layer selection as well as dynamic freezing and expansion of the prompt pool. Extensive experiments on widely used class-incremental learning benchmarks demonstrate that LDEPrompt achieves state-of-the-art performance, validating its effectiveness and scalability.

---

### Structured State-Space Regularization for Generation-Friendly Image Tokenization

Authors: Jinsung Lee, Jaemin Oh, Namhun Kim, Dongwon Kim, Byung-Jun Yoon, Suha Kwak
Published: 2026-04-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.11089v2

Image tokenizers play a central role in modern generative models, where the structure of the latent space critically determines the downstream generation performance. A key but underexplored property of effective latent representations is spectral organization, the ability to encode information across frequency components. In this work, we introduce structured state-space regularization, a principled approach to inducing spectral structure in latent spaces. We derive a regularization objective by revisiting state-space models (SSMs) as systems mimicking a basis function's behavior. This perspective reveals that hidden states of SSMs are induced to capture the frequency components, resulting in a novel regularizer that enforces the latent space to capture spectral structure of images. Experiments demonstrate that our regularizer improves the generative performance of image tokenizers while incurring only minimal loss in their reconstruction fidelity.

---

### Guardrails Beat Guidance: A Large-Scale Study of Rules, Skills, and Persistent Configuration for Coding Agents

Authors: Xing Zhang, Guanghui Wang, Yanwei Cui, Wei Qiu, Ziyuan Li, Bing Zhu, Peiyang He
Published: 2026-04-13
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2604.11088v2

Random rules improve a coding agent's task performance as much as expert-curated ones (both $+13.8$pp on a discriminative subset of SWE-bench Verified), and in our data every individually beneficial rule is a negative constraint ("do not refactor unrelated code"), while every individually harmful one is a positive directive ("follow code style"). We arrive at these findings through the first large-scale controlled study of agent rule files (\texttt{CLAUDE.md}, \texttt{.cursorrules}, and the broader family of agent skills, plugin manifests, and persona definitions): we scrape 679 rule files (25{,}532 rules) from GitHub and conduct over 5{,}000 agent runs of Claude Code with Claude Opus 4.6 on SWE-bench Verified. Three patterns emerge. (i) Rule polarity cleanly separates beneficial from harmful rules; we read this through the lens of potential-based reward shaping (PBRS). (ii) Performance gains are largely content-independent: random, shuffled, mismatched-domain, and unconverted-format rule files all match curated rules, pointing to a context priming mechanism. (iii) Individual rules often appear harmful in isolation yet do not visibly accumulate damage in ensemble: pass rates remain stable across rule counts from 0 to 50. These findings expose a hidden reliability risk in the rapidly growing ecosystem of community-authored rules and skills, and they yield a clear principle for safer agent configuration: constrain what agents must not do, rather than prescribing what they should.

---

### CausalGaze: Unveiling Hallucinations via Counterfactual Graph Intervention in Large Language Models

Authors: Linggang Kong, Lei Wu, Yunlong Zhang, Xiaofeng Zhong, Zhen Wang, Yongjie Wang, Yao Pan
Published: 2026-04-13
Categories: cs.LG
arXiv: https://arxiv.org/abs/2604.11087v3

Despite the groundbreaking advancements made by large language models (LLMs), hallucination remains a critical bottleneck for their deployment in high-stakes domains. Existing classification-based methods mainly rely on static and passive signals from internal states, which often captures the noise and spurious correlations, while overlooking the underlying causal mechanisms. To address this limitation, we shift the paradigm from passive observation to active intervention by introducing CausalGaze, a novel hallucination detection framework based on structural causal models (SCMs). CausalGaze models LLMs' internal states as dynamic causal graphs and employs counterfactual interventions to disentangle causal reasoning paths from incidental noise, thereby enhancing model interpretability. Extensive experiments across four datasets and three widely used LLMs demonstrate the effectiveness of CausalGaze, especially achieving 3.3% improvement in AUROC on the TruthfulQA dataset compared to state-of-the-art baselines.

---

### FlowCoMotion: Text-to-Motion Generation via Token-Latent Flow Modeling

Authors: Dawei Guan, Di Yang, Chengjie Jin, Jiangtao Wang
Published: 2026-04-13
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2604.11083v2

Text-to-motion generation is driven by learning motion representations for semantic alignment with language. Existing methods rely on either continuous or discrete motion representations. However, continuous representations entangle semantics with dynamics, while discrete representations lose fine-grained motion details. In this context, we propose FlowCoMotion, a novel motion generation framework that unifies both treatments from a modeling perspective. Specifically, FlowCoMotion employs token-latent coupling to capture both semantic content and high-fidelity motion details. In the latent branch, we apply multi-view distillation to regularize the continuous latent space, while in the token branch we use discrete temporal resolution quantization to extract high-level semantic cues. The motion latent is then obtained by combining the representations from the two branches through a token-latent coupling network. Subsequently, a velocity field is predicted based on the textual conditions. An ODE solver integrates this velocity field from a simple prior, thereby guiding the sample to the potential state of the target motion. Extensive experiments show that FlowCoMotion achieves competitive performance on text-to-motion benchmarks, including HumanML3D and SnapMoGen.

---

### RefGlitch-Bench: A Benchmark for Reference-based Gameplay Glitch Detection with Vision-Language Models

Authors: Yakun Yu, Ashley Wiens, Adrián Barahona-Ríos, Benedict Wilkins, Saman Zadtootaghaj, Nabajeet Barman, Cor-Paul Bezemer
Published: 2026-04-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.11082v2

Visual glitches in video games degrade player experience and perceived quality, yet manual quality assurance cannot keep pace with the growing test surface of modern game development. Prior automation efforts, particularly those using vision-language models (VLMs), largely operate on isolated frames without sufficient context to judge whether a glitch is present. We introduce RefGlitch-Bench, a benchmark for reference-based video game glitch detection with VLMs. The key idea is to formulate glitch detection as an explicit within-video comparison problem: given a test frame, a reference frame provides a visual baseline that helps the model distinguish true glitches from benign visual variation. RefGlitch-Bench includes a controlled synthetic dataset with five injected glitch types and manually annotated reference/test frame pairs, enabling an oracle-reference evaluation that isolates the potential benefit of reference guidance. We further establish four initial baselines for automatically selecting references from earlier frames in the same video, with LastCleanFrame performing best and transferring across VLMs. Finally, we evaluate automatic reference guidance on real-world gameplay data, where it improves frame-level glitch detection beyond the controlled setting while revealing reference reliability and error propagation as key challenges. Code and data are available at: https://github.com/PipiZong/RefGlitch-Bench.git.

---

### RESP: Reference-guided Sequential Prompting for Visual Glitch Detection in Video Games

Authors: Yakun Yu, Ashley Wiens, Adrián Barahona-Ríos, Benedict Wilkins, Saman Zadtootaghaj, Nabajeet Barman, Cor-Paul Bezemer
Published: 2026-04-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.11082v1

Visual glitches in video games degrade player experience and perceived quality, yet manual quality assurance cannot scale to the growing test surface of modern game development. Prior automation efforts, particularly those using vision-language models (VLMs), largely operate on single frames or rely on limited video-level baselines that struggle under realistic scene variation, making robust video-level glitch detection challenging. We present RESP, a practical multi-frame framework for gameplay glitch detection with VLMs. Our key idea is reference-guided prompting: for each test frame, we select a reference frame from earlier in the same video, establishing a visual baseline and reframing detection as within-video comparison rather than isolated classification. RESP sequentially prompts the VLM with reference/test pairs and aggregates noisy frame predictions into a stable video-level decision without fine-tuning the VLM. To enable controlled analysis of reference effects, we introduce RefGlitch, a synthetic dataset of manually labeled reference/test frame pairs with balanced coverage across five glitch types. Experiments across five VLMs and three datasets (one synthetic, two real-world) show that reference guidance consistently strengthens frame-level detection and that the improved frame-level evidence reliably transfers to stronger video-level triage under realistic QA conditions. Code and data are available at: \href{https://github.com/PipiZong/RESP_code.git}{this https URL}.

---

### MapATM: Enhancing HD Map Construction through Actor Trajectory Modeling

Authors: Mingyang Li, Brian Lee, Rui Zuo, Brent Bacchus, Priyantha Mudalige, Qinru Qiu
Published: 2026-04-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.11081v1

High-definition (HD) mapping tasks, which perform lane detections and predictions, are extremely challenging due to non-ideal conditions such as view occlusions, distant lane visibility, and adverse weather conditions. Those conditions often result in compromised lane detection accuracy and reduced reliability within autonomous driving systems. To address these challenges, we introduce MapATM, a novel deep neural network that effectively leverages historical actor trajectory information to improve lane detection accuracy, where actors refer to moving vehicles. By utilizing actor trajectories as structural priors for road geometry, MapATM achieves substantial performance enhancements, notably increasing AP by 4.6 for lane dividers and mAP by 2.6 on the challenging NuScenes dataset, representing relative improvements of 10.1% and 6.1%, respectively, compared to strong baseline methods. Extensive qualitative evaluations further demonstrate MapATM's capability to consistently maintain stable and robust map reconstruction across diverse and complex driving scenarios, underscoring its practical value for autonomous driving applications.

---

### ReSpinQuant: Efficient Layer-Wise LLM Quantization via Subspace Residual Rotation Approximation

Authors: Suyoung Kim, Sunghyun Wee, Hyeonjin Kim, Kyomin Hwang, Hyunho Lee, Nojun Kwak
Published: 2026-04-13
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2604.11080v2

Rotation-based Post-Training Quantization (PTQ) has emerged as a promising solution for mitigating activation outliers in the quantization of Large Language Models (LLMs). Global rotation methods achieve inference efficiency by fusing activation rotations into attention and FFN blocks, but suffer from limited expressivity as they are constrained to use a single learnable rotation matrix across all layers. To tackle this, layer-wise transformation methods emerged, achieving superior accuracy through localized adaptation. However, layer-wise methods cannot fuse activation rotation matrices into weights, requiring online computations and causing significant overhead. In this paper, we propose ReSpinQuant, a quantization framework that resolves such overhead by leveraging offline activation rotation fusion and matching basis using efficient residual subspace rotation. This design reconciles the high expressivity of layer-wise adaptation with only negligible inference overhead. Extensive experiments on W4A4 and W3A3 quantization demonstrate that ReSpinQuant achieves state-of-the-art performance, outperforming global rotation methods and matching the accuracy of computationally expensive layer-wise methods with minimal overhead.

---

### Towards Proactive Information Probing: Customer Service Chatbots Harvesting Value from Conversation

Authors: Chen Huang, Zitan Jiang, Changyi Zou, Wenqiang Lei, See-Kiong Ng
Published: 2026-04-13
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2604.11077v2

Customer service chatbots are increasingly expected to serve not merely as reactive support tools for users, but as strategic interfaces for harvesting high-value information and business intelligence. In response, we make three main contributions. 1) We introduce and define a novel task of Proactive Information Probing, which optimizes when to probe users for pre-specified target information while minimizing conversation turns and user friction. 2) We propose PROCHATIP, a proactive chatbot framework featuring a specialized conversation strategy module trained to master the delicate timing of probes. 3) Experiments demonstrate that PROCHATIP significantly outperforms baselines, exhibiting superior capability in both information probing and service quality. We believe that our work effectively redefines the commercial utility of chatbots, positioning them as scalable, cost-effective engines for proactive business intelligence. Our code is available at https://github.com/SCUNLP/PROCHATIP.

---

### Hodoscope: Unsupervised Monitoring for AI Misbehaviors

Authors: Ziqian Zhong, Shashwat Saxena, Aditi Raghunathan
Published: 2026-04-13
Categories: cs.AI
arXiv: https://arxiv.org/abs/2604.11072v1

Existing approaches to monitoring AI agents rely on supervised evaluation: human-written rules or LLM-based judges that check for known failure modes. However, novel misbehaviors may fall outside predefined categories entirely and LLM-based judges can be unreliable. To address this, we formulate unsupervised monitoring, drawing an analogy to unsupervised learning. Rather than checking for specific misbehaviors, an unsupervised monitor assists humans in discovering problematic agent behaviors without prior assumptions about what counts as problematic, leaving that determination to the human. We observe that problematic behaviors are often distinctive: a model exploiting a benchmark loophole exhibits actions absent from well-behaved baselines, and a vulnerability unique to one evaluation manifests as behavioral anomalies when the same model runs across multiple benchmarks. This motivates using group-wise behavioral differences as the primary signal for unsupervised monitoring. We introduce Hodoscope, a tool that operationalizes this insight. Hodoscope compares behavior distributions across groups and highlights distinctive and potentially suspicious action patterns for human review. Using Hodoscope, we discover a previously unknown vulnerability in the Commit0 benchmark (unsquashed git history allowing ground-truth recovery, inflating scores for at least five models) and independently recover known exploits on ImpossibleBench and SWE-bench. Quantitative evaluation estimates that our method reduces review effort by 6-23$\times$ compared to naive uniform sampling. Finally, we show that behavior descriptions discovered through Hodoscope could improve the detection accuracy of LLM-based judges, demonstrating a path from unsupervised to supervised monitoring.

---

### Lightweight Low-Light Image Enhancement via Distribution-Normalizing Preprocessing and Depthwise U-Net

Authors: Shimon Murai, Teppei Kurita, Ryuta Satoh, Yusuke Moriuchi
Published: 2026-04-13
Categories: cs.CV, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2604.11071v3

We present a lightweight two-stage framework for low-light image enhancement (LLIE) that achieves competitive perceptual quality with significantly fewer parameters than existing methods. Our approach combines frozen algorithm-based preprocessing with a compact U-Net built entirely from depthwise-separable convolutions. The preprocessing normalizes the input distribution by providing complementary brightness-corrected views, enabling the trainable network to focus on residual color correction. Our method achieved 3rd place in the CVPR 2026 NTIRE Efficient Low-Light Image Enhancement Challenge. We further provide extended benchmarks and ablations to demonstrate the general effectiveness of our methods.

---

### PRISM Risk Signal Framework: Hierarchy-Based Red Lines for AI Behavioral Risk

Authors: Seulki Lee
Published: 2026-04-13
Categories: cs.AI
arXiv: https://arxiv.org/abs/2604.11070v1

Current approaches to AI safety define red lines at the case level: specific prompts, specific outputs, specific harms. This paper argues that red lines can be set more fundamentally -- at the level of value, evidence, and source hierarchies that govern AI reasoning. Using the PRISM (Profile-based Reasoning Integrity Stack Measurement) framework, we define a taxonomy of 27 behavioral risk signals derived from structural anomalies in how AI systems prioritize values (L4), weight evidence types (L3), and trust information sources (L2). Each signal is evaluated through a dual-threshold principle combining absolute rank position and relative win-rate gap, producing a two-tier classification (Confirmed Risk vs. Watch Signal). The hierarchy-based approach offers three advantages over case-specific red lines: it is anticipatory rather than reactive (detecting dangerous reasoning structures before they produce harmful outputs), comprehensive rather than enumerative (a single value-hierarchy signal subsumes an unlimited number of case-specific violations), and measurable rather than subjective (grounded in empirical forced-choice data). We demonstrate the framework's detection capacity using approximately 397,000 forced-choice responses from 7 AI models across three Authority Stack layers, showing that the signal taxonomy successfully discriminates between models with structurally extreme profiles, models with context-dependent risk, and models with balanced hierarchies.

---

### ks-pret-5m: a 5 million word, 12 million token kashmiri pretraining dataset

Authors: Haq Nawaz Malik, Nahfid Nissar
Published: 2026-04-13
Categories: cs.CL
arXiv: https://arxiv.org/abs/2604.11066v1

We present KS-PRET-5M, the largest publicly available pretraining dataset for the Kashmiri language, comprising 5,090,244 (5.09M) words, 27,692,959 (27.6M) characters, and a vocabulary of 295,433 (295.4K) unique word types. We assembled the dataset from two source classes: digitized archival and literary material, encompassing literature, news, biographies, novels, poetry, religious scholarship, and academic writing, recovered from the proprietary InPage desktop-publishing format using the converter of Malik~\cite{malik2024inpage}, and Unicode-native text collected from Kashmiri-language web sources. All text was processed through an eleven-stage cleaning pipeline that achieves a mean Kashmiri script ratio of 0.9965, reducing Devanagari contamination to 146 characters across the full dataset. We tokenized the dataset empirically using google/muril-base-cased, yielding a subword ratio of 2.383 tokens per word and a total of approximately 12.13 million subword tokens, substantially higher than prior estimates derived from non-Kashmiri Perso-Arabic analogues. KS-PRET-5M is released as a single continuous text stream under CC~BY~4.0 to support language model pretraining, tokenizer training, and computational linguistic research for Kashmiri.

---

### AI Integrity: A New Paradigm for Verifiable AI Governance

Authors: Seulki Lee
Published: 2026-04-13
Categories: cs.AI
arXiv: https://arxiv.org/abs/2604.11065v1

AI systems increasingly shape high-stakes decisions in healthcare, law, defense, and education, yet existing governance paradigms -- AI Ethics, AI Safety, and AI Alignment -- share a common limitation: they evaluate outcomes rather than verifying the reasoning process itself. This paper introduces AI Integrity, a concept defined as a state in which the Authority Stack of an AI system -- its layered hierarchy of values, epistemological standards, source preferences, and data selection criteria -- is protected from corruption, contamination, manipulation, and bias, and maintained in a verifiable manner. We distinguish AI Integrity from the three existing paradigms, define the Authority Stack as a 4-layer cascade model (Normative, Epistemic, Source, and Data Authority) grounded in established academic frameworks -- Schwartz Basic Human Values for normative authority, Walton argumentation schemes with GRADE/CEBM hierarchies for epistemic authority, and Source Credibility Theory for source authority -- characterize the distinction between legitimate cascading and Authority Pollution, and identify Integrity Hallucination as the central measurable threat to value consistency. We further specify the PRISM (Profile-based Reasoning Integrity Stack Measurement) framework as the operational methodology, defining six core metrics and a phased research roadmap. Unlike normative frameworks that prescribe which values are correct, AI Integrity is a procedural concept: it requires that the path from evidence to conclusion be transparent and auditable, regardless of which values a system holds.

---

### A Faster Path to Continual Learning

Authors: Wei Li, Hangjie Yuan, Zixiang Zhao, Borui Kang, Ziwei Liu, Tao Feng
Published: 2026-04-13
Categories: cs.LG, cs.CV
arXiv: https://arxiv.org/abs/2604.11064v2

Continual Learning (CL) aims to train neural networks on a dynamic stream of tasks without forgetting previously learned knowledge. Among optimization-based approaches, C-Flat has emerged as a promising solution due to its plug-and-play nature and its ability to encourage uniformly low-loss regions for both new and old tasks. However, C-Flat requires three additional gradient computations per iteration, imposing substantial overhead on the optimization process. In this work, we propose C-Flat Turbo, a faster yet stronger optimizer that significantly reduces the training cost. We show that the gradients associated with first-order flatness contain direction-invariant components relative to the proxy-model gradients, enabling us to skip redundant gradient computations in the perturbed ascent steps. Moreover, we observe that these flatness-promoting gradients progressively stabilize across tasks, which motivates a linear scheduling strategy with an adaptive trigger to allocate larger turbo steps for later tasks. Experiments show that C-Flat Turbo is 1.0$\times$ to 1.25$\times$ faster than C-Flat across a wide range of CL methods, while achieving comparable or even improved accuracy.

---

### Pando: Do Interpretability Methods Work When Models Won't Explain Themselves?

Authors: Ziqian Zhong, Aashiq Muhamed, Mona T. Diab, Virginia Smith, Aditi Raghunathan
Published: 2026-04-13
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2604.11061v1

Mechanistic interpretability is often motivated for alignment auditing, where a model's verbal explanations can be absent, incomplete, or misleading. Yet many evaluations do not control whether black-box prompting alone can recover the target behavior, so apparent gains from white-box tools may reflect elicitation rather than internal signal; we call this the elicitation confounder. We introduce Pando, a model-organism benchmark that breaks this confound via an explanation axis: models are trained to produce either faithful explanations of the true rule, no explanation, or confident but unfaithful explanations of a disjoint distractor rule. Across 720 finetuned models implementing hidden decision-tree rules, agents predict held-out model decisions from $10$ labeled query-response pairs, optionally augmented with one interpretability tool output. When explanations are faithful, black-box elicitation matches or exceeds all white-box methods; when explanations are absent or misleading, gradient-based attribution improves accuracy by 3-5 percentage points, and relevance patching, RelP, gives the largest gains, while logit lens, sparse autoencoders, and circuit tracing provide no reliable benefit. Variance decomposition suggests gradients track decision computation, which fields causally drive the output, whereas other readouts are dominated by task representation, biases toward field identity and value. We release all models, code, and evaluation infrastructure.

---

### Where Hindsight Credit Can Reside: A Signed-Capacity View of Token Updates in RLVR

Authors: Yuhang He, Haodong Wu, Siyi Liu, Hongyu Ge, Hange Zhou, Keyi Wu, Zhuo Zheng, Qihong Lin, Zixin Zhong, Yongqi Zhang
Published: 2026-04-13
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2604.11056v2

Reinforcement Learning with Verifiable Rewards (RLVR) improves the reasoning ability of Large Language Models (LLMs), but sparse outcome rewards make token-level credit assignment difficult. We study token-level credit as a reward-conditioned shift from the behavior policy to a hindsight posterior. In autoregressive RLVR, this shift can be expressed through Conditional Mutual Information (CMI), which shows that token entropy upper-bounds possible hindsight credit. Entropy, however, indicates capacity rather than update direction, so we introduce the Four Quadrant Decomposition to separate updates by reward polarity and token entropy. Controlled interventions show that these two factors jointly shape token updates. Sustained reasoning gains concentrate in signed high-entropy quadrants, whereas low-entropy updates saturate quickly. Based on this analysis, we propose Hindsight-Aware Policy Optimization (HAPO), a sign-preserving modification to GRPO that performs capacity-guided advantage reallocation. Experiments on mathematical reasoning benchmarks in two model settings show that HAPO achieves competitive performance among entropy-aware baselines.

---

### Shared Emotion Geometry Across Small Language Models: A Cross-Architecture Study of Representation, Behavior, and Methodological Confounds

Authors: Jihoon Jeong
Published: 2026-04-13
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2604.11050v1

We extract 21-emotion vector sets from twelve small language models (six architectures x base/instruct, 1B-8B parameters) under a unified comprehension-mode pipeline at fp16 precision, and compare the resulting geometries via representational similarity analysis on raw cosine RDMs. The five mature architectures (Qwen 2.5 1.5B, SmolLM2 1.7B, Llama 3.2 3B, Mistral 7B v0.3, Llama 3.1 8B) share nearly identical 21-emotion geometry, with pairwise RDM Spearman correlations of 0.74-0.92. This universality persists across diametrically opposed behavioral profiles: Qwen 2.5 and Llama 3.2 occupy opposite poles of MTI Compliance facets yet produce nearly identical emotion RDMs (rho = 0.81), so behavioral facet differences arise above the shared emotion representation. Gemma-3 1B base, the one immature case in our dataset, exhibits extreme residual-stream anisotropy (0.997) and is restructured by RLHF across all geometric descriptors, whereas the five already-mature families show within-family base x instruct RDM correlations of rho >= 0.92 (Mistral 7B v0.3 at rho = 0.985), suggesting RLHF restructures only representations that are not yet organized. Methodologically, we show that what prior work has read as a single comprehension-vs-generation method effect in fact decomposes into four distinct layers -- a coarse method-dependent dissociation, robust sub-parameter sensitivity within generation, a true precision (fp16 vs INT8) effect, and a conflated cross-experiment bias that distorts in opposite directions for different models -- so that a single rho between two prior emotion-vector studies is not a safe basis for interpretation without the layered decomposition.

---

### A Systematic Analysis of the Impact of Persona Steering on LLM Capabilities

Authors: Jiaqi Chen, Ming Wang, Tingna Xie, Shi Feng, Yongkang Liu
Published: 2026-04-13
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2604.11048v2

Imbuing Large Language Models (LLMs) with specific personas is prevalent for tailoring interaction styles, yet the impact on underlying cognitive capabilities remains unexplored. We employ the Neuron-based Personality Trait Induction (NPTI) framework to induce Big Five personality traits in LLMs and evaluate performance across six cognitive benchmarks. Our findings reveal that persona induction produces stable, reproducible shifts in cognitive task performance beyond surface-level stylistic changes. These effects exhibit strong task dependence: certain personalities yield consistent gains on instruction-following, while others impair complex reasoning. Effect magnitude varies systematically by trait dimension, with Openness and Extraversion exerting the most robust influence. Furthermore, LLM effects show 73.68% directional consistency with human personality-cognition relationships. Capitalizing on these regularities, we propose Dynamic Persona Routing (DPR), a lightweight query-adaptive strategy that outperforms the best static persona without additional training.

---

### EmergentBridge: Improving Zero-Shot Cross-Modal Transfer in Unified Multimodal Embedding Models

Authors: Jincheng Xie, Xingchen Xiao, Runheng Liu, Zhongyi Huang, Yu Zheng, Heyan Huang
Published: 2026-04-13
Categories: cs.AI
arXiv: https://arxiv.org/abs/2604.11043v5

Unified multimodal embedding spaces underpin practical applications such as cross-modal retrieval and zero-shot recognition. In many real deployments, however, supervision is available only for a small subset of modality pairs (e.g., image--text), leaving \emph{unpaired} modality pairs (e.g., audio$\leftrightarrow$depth, infrared$\leftrightarrow$audio) weakly connected and thus performing poorly on zero-shot transfer. Addressing this sparse-pairing regime is therefore essential for scaling unified embedding systems to new tasks without curating exhaustive pairwise data. We propose \textbf{EmergentBridge}, an embedding-level bridging framework that improves performance on these unpaired pairs \emph{without requiring exhaustive pairwise supervision}. Our key observation is that naively aligning a new modality to a synthesized proxy embedding can introduce \emph{gradient interference}, degrading the anchor-alignment structure that existing retrieval/classification relies on. EmergentBridge addresses this by (i) learning a mapping that produces a \emph{noisy bridge anchor} (a proxy embedding of an already-aligned modality) from an anchor embedding, and (ii) enforcing proxy alignment only in the subspace orthogonal to the anchor-alignment direction, preserving anchor alignment while strengthening non-anchor connectivity. Across nine datasets spanning multiple modalities, EmergentBridge consistently outperforms prior binding baselines on zero-shot classification and retrieval, demonstrating strong emergent alignment.

---

### Improving Layout Representation Learning Across Inconsistently Annotated Datasets via Agentic Harmonization

Authors: Renyu Li, Vladimir Kirilenko, Yao You, Crag Wolfe
Published: 2026-04-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.11042v1

Fine-tuning object detection (OD) models on combined datasets assumes annotation compatibility, yet datasets often encode conflicting spatial definitions for semantically equivalent categories. We propose an agentic label harmonization workflow that uses a vision-language model to reconcile both category semantics and bounding box granularity across heterogeneous sources before training. We evaluate on document layout detection as a challenging case study, where annotation standards vary widely across corpora. Without harmonization, naïve mixed-dataset fine-tuning degrades a pretrained RT-DETRv2 detector: on SCORE-Bench, which measures how accurately the full document conversion pipeline reproduces ground-truth structure, table TEDS drops from 0.800 to 0.750. Applied to two corpora whose 16 and 10 category taxonomies share only 8 direct correspondences, harmonization yields consistent gains across content fidelity, table structure, and spatial consistency: detection F-score improves from 0.860 to 0.883, table TEDS improves to 0.814, and mean bounding box overlap drops from 0.043 to 0.016. Representation analysis further shows that harmonized training produces more compact and separable post-decoder embeddings, confirming that annotation inconsistency distorts the learned feature space and that resolving it before training restores representation structure.

---

### From Topology to Trajectory: LLM-Driven World Models For Supply Chain Resilience

Authors: Jia Luo
Published: 2026-04-13
Categories: cs.AI
arXiv: https://arxiv.org/abs/2604.11041v1

Semiconductor supply chains face unprecedented resilience challenges amidst global geopolitical turbulence. Conventional Large Language Model (LLM) planners, when confronting such non-stationary "Policy Black Swan" events, frequently suffer from Decision Paralysis or a severe Grounding Gap due to the absence of physical environmental modeling. This paper introduces ReflectiChain, a cognitive agentic framework tailored for resilient macroeconomic supply chain planning. The core innovation lies in the integration of Latent Trajectory Rehearsal powered by a generative world model, which couples reflection-in-action (System 2 deliberation) with delayed reflection-on-action. Furthermore, we leverage a Retrospective Agentic RL mechanism to enable autonomous policy evolution during the deployment phase (test-time). Evaluations conducted on our high-fidelity benchmark, Semi-Sim, demonstrate that under extreme scenarios such as export bans and material shortages, ReflectiChain achieves a 250% improvement in average step rewards over the strongest LLM baselines. It successfully restores the Operability Ratio (OR) from a deficient 13.3% to over 88.5% while ensuring robust gradient convergence. Ablation studies further underscore that the synergy between physical grounding constraints and double-loop learning is fundamental to bridging the gap between semantic reasoning and physical reality for long-horizon strategic planning.

---

### Intelligent Approval of Access Control Flow in Office Automation Systems via Relational Modeling

Authors: Dugang Liu, Zulong Chen, Chuanfei Xu, Jiaxuan He, Yunlu Ma, Jia Xu
Published: 2026-04-13
Categories: cs.AI
arXiv: https://arxiv.org/abs/2604.11040v1

Office automation (OA) systems play a crucial role in enterprise operations and management, with access control flow approval (ACFA) being a key component that manages the accessibility of various resources. However, traditional ACFA requires approval from the person in charge at each step, which consumes a significant amount of manpower and time. Its intelligence is a crucial issue that needs to be addressed urgently by all companies. In this paper, we propose a novel relational modeling-driven intelligent approval (RMIA) framework to automate ACFA. Specifically, our RMIA consists of two core modules: (1) The binary relation modeling module aims to characterize the coupling relation between applicants and approvers and provide reliable basic information for ACFA decision-making from a coarse-grained perspective. (2) The ternary relation modeling module utilizes specific resource information as its core, characterizing the complex relations between applicants, resources, and approvers, and thus provides fine-grained gain information for informed decision-making. Then, our RMIA effectively fuses these two kinds of information to form the final decision. Finally, extensive experiments are conducted on two product datasets and an online A/B test to verify the effectiveness of RMIA.

---

### EgoFun3D: Modeling Interactive Objects from Egocentric Videos using Function Templates

Authors: Weikun Peng, Denys Iliash, Manolis Savva
Published: 2026-04-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.11038v2

We present EgoFun3D, a coordinated task formulation, dataset, and benchmark for modeling interactive 3D objects from egocentric videos. Interactive objects are of high interest for embodied AI but scarce, making modeling from readily available real-world videos valuable. Our task focuses on obtaining simulation-ready interactive 3D objects from egocentric video input. While prior work largely focuses on articulations, we capture general cross-part functional mappings (e.g., rotation of stove knob controls stove burner temperature) through function templates, a structured computational representation. Function templates enable precise evaluation and direct compilation into executable code across simulation platforms. To enable comprehensive benchmarking, we introduce a dataset of 517 egocentric videos featuring challenging real-world interactions with paired 3D geometry, segmentation over 2D and 3D, articulation and function template annotations. To tackle the task, we propose a 4-stage pipeline consisting of: 2D part segmentation, reconstruction, articulation estimation, and function template inference. Comprehensive benchmarking shows that the task is challenging for off-the-shelf methods, highlighting avenues for future work.

---

### EgoFun3D: Modeling Interactive Objects from Egocentric Videos using Function Templates

Authors: Weikun Peng, Denys Iliash, Manolis Savva
Published: 2026-04-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.11038v1

We present EgoFun3D, a coordinated task formulation, dataset, and benchmark for modeling interactive 3D objects from egocentric videos. Interactive objects are of high interest for embodied AI but scarce, making modeling from readily available real-world videos valuable. Our task focuses on obtaining simulation-ready interactive 3D objects from egocentric video input. While prior work largely focuses on articulations, we capture general cross-part functional mappings (e.g., rotation of stove knob controls stove burner temperature) through function templates, a structured computational representation. Function templates enable precise evaluation and direct compilation into executable code across simulation platforms. To enable comprehensive benchmarking, we introduce a dataset of 271 egocentric videos featuring challenging real-world interactions with paired 3D geometry, segmentation over 2D and 3D, articulation and function template annotations. To tackle the task, we propose a 4-stage pipeline consisting of: 2D part segmentation, reconstruction, articulation estimation, and function template inference. Comprehensive benchmarking shows that the task is challenging for off-the-shelf methods, highlighting avenues for future work.

---

### RTMC: Step-Level Credit Assignment via Rollout Trees

Authors: Tao Wang, Suhang Zheng, Xiaoxiao Xu
Published: 2026-04-13
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2604.11037v1

Multi-step agentic reinforcement learning benefits from fine-grained credit assignment, yet existing approaches offer limited options: critic-free methods like GRPO assign a uniform advantage to every action in a trajectory, while learned value networks introduce notable overhead and can be fragile under sparse rewards. We observe that group rollouts targeting the same problem often traverse overlapping intermediate states, implicitly forming a tree whose branches diverge at successive decision points. Building on this insight, we introduce Rollout-Tree Monte Carlo (RTMC) advantage estimation, which aggregates return statistics across rollouts sharing a common state to produce per-step Q-values and advantages--without any learned critic. A state-action signature system compresses raw interaction histories into compact, comparable representations, making cross-rollout state matching tractable. On SWE-bench Verified, RTMC improves pass@1 by 3.2 percentage points over GRPO.

---

### Uncertainty-Aware Web-Conditioned Scientific Fact-Checking

Authors: Ashwin Vinod, Katrin Erk
Published: 2026-04-13
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2604.11036v1

Scientific fact-checking is vital for assessing claims in specialized domains such as biomedicine and materials science, yet existing systems often hallucinate or apply inconsistent reasoning, especially when verifying technical, compositional claims against an evidence snippet under source and cost/latency constraints. We present a pipeline centered on atomic predicate-argument decomposition and calibrated, uncertainty-gated corroboration: atomic facts are aligned to local snippets via embeddings, verified by a compact evidence-grounded checker, and only facts with uncertain support trigger domain-restricted web search over authoritative sources. The system supports both binary and tri-valued classification where it predicts labels from Supported, Refuted, NEI for three-way tasks. We evaluate under two regimes, Context-Only (no web) and Context+Web (uncertainty-gated web corroboration); when retrieved evidence conflicts with the provided context, we abstain with NEI rather than overriding the context. On multiple benchmarks, our framework surpasses the strongest benchmarks. In our experiments, web corroboration was invoked for only a minority of atomic facts on average, indicating that external evidence is consulted selectively under calibrated uncertainty rather than routinely. Overall, coupling atomic granularity with calibrated, uncertainty-gated corroboration yields more interpretable and context-conditioned verification, making the approach well-suited to high-stakes, single-document settings that demand traceable rationales, predictable cost/latency, and conservative.

---

### Introspective Diffusion Language Models

Authors: Yifan Yu, Yuqing Jian, Junxiong Wang, Zhongzhu Zhou, Donglin Zhuang, Xinyu Fang, Sri Yanamandra, Xiaoxia Wu, Qingyang Wu, Shuaiwen Leon Song, Tri Dao, Ben Athiwaratkun et al.
Published: 2026-04-13
Categories: cs.AI
arXiv: https://arxiv.org/abs/2604.11035v1

Diffusion language models promise parallel generation, yet still lag behind autoregressive (AR) models in quality. We stem this gap to a failure of introspective consistency: AR models agree with their own generations, while DLMs often do not. We define the introspective acceptance rate, which measures whether a model accepts its previously generated tokens. This reveals why AR training has a structural advantage: causal masking and logit shifting implicitly enforce introspective consistency. Motivated by this observation, we introduce Introspective Diffusion Language Model (I-DLM), a paradigm that retains diffusion-style parallel decoding while inheriting the introspective consistency of AR training. I-DLM uses a novel introspective strided decoding (ISD) algorithm, which enables the model to verify previously generated tokens while advancing new ones in the same forward pass. From a systems standpoint, we build I-DLM inference engine on AR-inherited optimizations and further customize it with a stationary-batch scheduler. To the best of our knowledge, I-DLM is the first DLM to match the quality of its same-scale AR counterpart while outperforming prior DLMs in both model quality and practical serving efficiency across 15 benchmarks. It reaches 69.6 on AIME-24 and 45.7 on LiveCodeBench-v6, exceeding LLaDA-2.1-mini (16B) by more than 26 and 15 points, respectively. Beyond quality, I-DLM is designed for the growing demand of large-concurrency serving, delivering about 3x higher throughput than prior state-of-the-art DLMs.

---

### Federated Single-Agent Robotics: Multi-Robot Coordination Without Intra-Robot Multi-Agent Fragmentation

Authors: Xue Qin, Simin Luan, John See, Cong Yang, Zhijun Li
Published: 2026-04-13
Categories: cs.RO, cs.AI
arXiv: https://arxiv.org/abs/2604.11028v2

As embodied robots move toward fleet-scale operation, multi-robot coordination is becoming a central systems challenge. Existing approaches often treat this as motivation for increasing internal multi-agent decomposition within each robot. We argue for a different principle: multi-robot coordination does not require intra-robot multi-agent fragmentation. Each robot should remain a single embodied agent with its own persistent runtime, local policy scope, capability state, and recovery authority, while coordination emerges through federation across robots at the fleet level. We present Federated Single-Agent Robotics (FSAR), a runtime architecture for multi-robot coordination built on single-agent robot runtimes. Each robot exposes a governed capability surface rather than an internally fragmented agent society. Fleet coordination is achieved through shared capability registries, cross-robot task delegation, policy-aware authority assignment, trust-scoped interaction, and layered recovery protocols. We formalize key coordination relations including authority delegation, inter-robot capability requests, local-versus-fleet recovery boundaries, and hierarchical human supervision, and describe a fleet runtime architecture supporting shared Embodied Capability Module (ECM) discovery, contract-aware cross-robot coordination, and fleet-level governance. We evaluate FSAR on representative multi-robot coordination scenarios against decomposition-heavy baselines. Results show statistically significant gains in governance locality (d=2.91, p<.001 vs. centralized control) and recovery containment (d=4.88, p<.001 vs. decomposition-heavy), while reducing authority conflicts and policy violations across all scenarios. Our results support the view that the path from embodied agents to embodied fleets is better served by federation across coherent robot runtimes than by fragmentation within them.

---

### Optimal Stability of KL Divergence under Gaussian Perturbations

Authors: Jialu Pan, Yufeng Zhang, Nan Hu, Zhenbang Chen, Ji Wang, Keqin Li
Published: 2026-04-13
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2604.11026v3

We study the problem of characterizing the stability of Kullback-Leibler (KL) divergence under Gaussian perturbations beyond Gaussian families. Existing relaxed triangle inequalities for KL divergence critically rely on the assumption that all involved distributions are Gaussian, which limits their applicability in modern applications such as out-of-distribution (OOD) detection with flow-based generative models. In this paper, we remove this restriction by establishing a sharp stability bound between an arbitrary distribution and Gaussian families under mild moment conditions. Specifically, let $P$ be a distribution with finite second moment, and let $\mathcal{N}_1$ and $\mathcal{N}_2$ be multivariate Gaussian distributions. We show that if $KL(P||\mathcal{N}_1)$ is large and $KL(\mathcal{N}_1||\mathcal{N}_2)$ is at most $ε$, then $KL(P||\mathcal{N}_2) \ge KL(P||\mathcal{N}_1) - O(\sqrtε)$. Moreover, we prove that this $\sqrtε$ rate is optimal in general, even within the Gaussian family. This result reveals an intrinsic stability property of KL divergence under Gaussian perturbations, extending classical Gaussian-only relaxed triangle inequalities to general distributions. The result is non-trivial due to the asymmetry of KL divergence and the absence of a triangle inequality in general probability spaces. As an application, we provide a rigorous foundation for KL-based OOD analysis in flow-based models, removing strong Gaussian assumptions used in prior work. More broadly, our result enables KL-based reasoning in non-Gaussian settings arising in deep learning and reinforcement learning.

---

### Test-time Scaling over Perception: Resolving the Grounding Paradox in Thinking with Images

Authors: Zheng Jiang, Yiming Chen, Nan He, Jiahui Chen, Chaoyang Li, Houde Qian, Lifeng Sun
Published: 2026-04-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.11025v2

Recent multimodal large language models (MLLMs) support Thinking with Images, invoking visual tools such as zooming and cropping to inspect image regions during inference. Yet these systems remain brittle in fine-grained reasoning: to acquire a decisive detail, a model must ground its attention on the correct region, but knowing which region is correct presupposes having already observed that detail. We identify this circular dependency as the grounding paradox, show that grounding errors are rarely self-corrected within a single trajectory---once a misleading region is inspected, all subsequent reasoning conditions on that observation and the error propagates to the final answer---and observe that because each trajectory constructs its own evidence, answer-level aggregation discards the very information that distinguishes trajectories. We propose Test-Time Scaling over Perception (TTSP), a closed-loop framework that treats perception as the unit of scalable inference and allocates compute along two axes: Entropy-Gated Perceptual Exploration samples diverse trajectories and uses critical-token entropy to withhold evidence the model cannot commit to, while Evidence-Guided Iterative Refinement distills validated observations into a correctable Evidence Ledger that steers later rounds to re-inspect unresolved regions. Across high-resolution and general multimodal benchmarks, TTSP consistently outperforms strong test-time scaling baselines, while improving grounding quality with favorable token efficiency.

---

### Brief2Design: A Multi-phased, Compositional Approach to Prompt-based Graphic Design

Authors: Kotaro Kikuchi, Nami Ogawa
Published: 2026-04-13
Categories: cs.HC, cs.AI
arXiv: https://arxiv.org/abs/2604.11019v1

Professional designers work from client briefs that specify goals and constraints but often lack concrete design details. Translating these abstract requirements into visual designs poses a central challenge, yet existing tools address specific aspects or induce fixation through complete outputs. Through interviews with six professional designers, we identified how designers address this challenge: first structuring ambiguous requirements, then exploring individual elements, and finally recombining alternatives. We developed Brief2Design, supporting this workflow through requirement extraction and recommendation, element-level exploration for objects, backgrounds, text, typography, and composition, and flexible recombination of selected elements. A within-subjects study with twelve designers compared Brief2Design against a conversational baseline. The structured approach increased prompt diversity and received high ratings for requirement extraction and recommendation, but required longer generation time and achieved comparable image diversity. These findings reveal that structured workflows benefit requirement clarification at the cost of efficiency, informing design trade-offs for AI-assisted graphic design tools.

---

### NimbusGuard: A Novel Framework for Proactive Kubernetes Autoscaling Using Deep Q-Networks

Authors: Chamath Wanigasooriya, Indrajith Ekanayake
Published: 2026-04-13
Categories: cs.DC, cs.AI
arXiv: https://arxiv.org/abs/2604.11017v1

Cloud native architecture is about building and running scalable microservice applications to take full advantage of the cloud environments. Managed Kubernetes is the powerhouse orchestrating cloud native applications with elastic scaling. However, traditional Kubernetes autoscalers are reactive, meaning the scaling controllers adjust resources only after they detect demand within the cluster and do not incorporate any predictive measures. This can lead to either over-provisioning and increased costs or under-provisioning and performance degradation. We propose NimbusGuard, an open-source, Kubernetes-based autoscaling system that leverages a deep reinforcement learning agent to provide proactive autoscaling. The agents perception is augmented by a Long Short-Term Memory model that forecasts future workload patterns. The evaluations were conducted by comparing NimbusGuard against the built-in scaling controllers, such as Horizontal Pod Autoscaler, and the event-driven autoscaler KEDA. The experimental results demonstrate how NimbusGuard's proactive framework translates into superior performance and cost efficiency compared to existing reactive methods.

---

### UHD-GPGNet: UHD Video Denoising via Gaussian-Process-Guided Local Spatio-Temporal Modeling

Authors: Weiyuan He, Chen Wu, Pengwen Dai, Wei Wang, Dianjie Lu, Guijuan Zhang, Linwei Fan, Yongzhen Wang, Zhuoran Zheng
Published: 2026-04-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.11014v1

Ultra-high-definition (UHD) video denoising requires simultaneously suppressing complex spatio-temporal degradations, preserving fine textures and chromatic stability, and maintaining efficient full-resolution 4K deployment. In this paper, we propose UHD-GPGNet, a Gaussian-process-guided local spatio-temporal denoising framework that addresses these requirements jointly. Rather than relying on implicit feature learning alone, the method estimates sparse GP posterior statistics over compact spatio-temporal descriptors to explicitly characterize local degradation response and uncertainty, which then guide adaptive temporal-detail fusion. A structure-color collaborative reconstruction head decouples luminance, chroma, and high-frequency correction, while a heteroscedastic objective and overlap-tiled inference further stabilize optimization and enable memory-bounded 4K deployment. Experiments on UVG and RealisVideo-4K show that UHD-GPGNet achieves competitive restoration fidelity with substantially fewer parameters than existing methods, enables real-time full-resolution 4K inference with significant speedup over the closest quality competitor, and maintains robust performance across a multi-level mixed-degradation schedule.A real-world study on phone-captured 4K video further confirms that the model, trained entirely on synthetic degradation, generalizes to unseen real sensor noise and improves downstream object detection under challenging conditions.

---

### Min-$k$ Sampling: Decoupling Truncation from Temperature Scaling via Relative Logit Dynamics

Authors: Yuanhao Ding, Meimingwei Li, Esteban Garces Arias, Matthias Aßenmacher, Christian Heumann, Chongsheng Zhang
Published: 2026-04-13
Categories: cs.AI, cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2604.11012v1

The quality of text generated by large language models depends critically on the decoding sampling strategy. While mainstream methods such as Top-$k$, Top-$p$, and Min-$p$ achieve a balance between diversity and accuracy through probability-space truncation, they share an inherent limitation: extreme sensitivity to the temperature parameter. Recent logit-space approaches like Top-$nσ$ achieve temperature invariance but rely on global statistics that are susceptible to long-tail noise, failing to capture fine-grained confidence structures among top candidates. We propose \textbf{Min-$k$ Sampling}, a novel dynamic truncation strategy that analyzes the local shape of the sorted logit distribution to identify "semantic cliffs": sharp transitions from high-confidence core tokens to uncertain long-tail tokens. By computing a position-weighted relative decay rate, Min-$k$ dynamically determines truncation boundaries at each generation step. We formally prove that Min-$k$ achieves strict temperature invariance and empirically demonstrate its low sensitivity to hyperparameter choices. Experiments on multiple reasoning benchmarks, creative writing tasks, and human evaluation show that Min-$k$ consistently improves text quality, maintaining robust performance even under extreme temperature settings where probability-based methods collapse. We make our code, models, and analysis tools publicly available.

---