# Research Papers — 2026-03 · bundle page 22 of 243

> Full-text markdown of papers #1051–1100 of 12123 published in 2026-03, newest first. AI-readable mirrors of the full 12123-paper 2026-03 archive (50 papers per file).

Canonical page: https://aipod.dev/papers/archive/2026-03/page/22
[← Previous bundle](https://aipod.dev/papers/archive/2026-03/page/21.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-03/page/23.md)

### LongCat-Next: Lexicalizing Modalities as Discrete Tokens

Authors: Meituan LongCat Team, Bin Xiao, Chao Wang, Chengjiang Li, Chi Zhang, Chong Peng, Hang Yu, Hao Yang, Haonan Yan, Haoze Sun, Haozhe Zhao, Hong Liu et al.
Published: 2026-03-29
Categories: cs.CV, cs.CL
arXiv: https://arxiv.org/abs/2603.27538v1

The prevailing Next-Token Prediction (NTP) paradigm has driven the success of large language models through discrete autoregressive modeling. However, contemporary multimodal systems remain language-centric, often treating non-linguistic modalities as external attachments, leading to fragmented architectures and suboptimal integration. To transcend this limitation, we introduce Discrete Native Autoregressive (DiNA), a unified framework that represents multimodal information within a shared discrete space, enabling a consistent and principled autoregressive modeling across modalities. A key innovation is the Discrete Native Any-resolution Visual Transformer (dNaViT), which performs tokenization and de-tokenization at arbitrary resolutions, transforming continuous visual signals into hierarchical discrete tokens. Building on this foundation, we develop LongCat-Next, a native multimodal model that processes text, vision, and audio under a single autoregressive objective with minimal modality-specific design. As an industrial-strength foundation model, it excels at seeing, painting, and talking within a single framework, achieving strong performance across a wide range of multimodal benchmarks. In particular, LongCat-Next addresses the long-standing performance ceiling of discrete vision modeling on understanding tasks and provides a unified approach to effectively reconcile the conflict between understanding and generation. As an attempt toward native multimodality, we open-source the LongCat-Next and its tokenizers, hoping to foster further research and development in the community. GitHub: https://github.com/meituan-longcat/LongCat-Next

---

### Dual-Stage LLM Framework for Scenario-Centric Semantic Interpretation in Driving Assistance

Authors: Jean Douglas Carvalho, Hugo Taciro Kenji, Ahmad Mohammad Saber, Glaucia Melo, Max Mauro Dias Santos, Deepa Kundur
Published: 2026-03-29
Categories: cs.AI
arXiv: https://arxiv.org/abs/2603.27536v1

Advanced Driver Assistance Systems (ADAS) increasingly rely on learning-based perception, yet safety-relevant failures often arise without component malfunction, driven instead by partial observability and semantic ambiguity in how risk is interpreted and communicated. This paper presents a scenario-centric framework for reproducible auditing of LLM-based risk reasoning in urban driving contexts. Deterministic, temporally bounded scenario windows are constructed from multimodal driving data and evaluated under fixed prompt constraints and a closed numeric risk schema, ensuring structured and comparable outputs across models. Experiments on a curated near-people scenario set compare two text-only models and one multimodal model under identical inputs and prompts. Results reveal systematic inter-model divergence in severity assignment, high-risk escalation, evidence use, and causal attribution. Disagreement extends to the interpretation of vulnerable road user presence, indicating that variability often reflects intrinsic semantic indeterminacy rather than isolated model failure. These findings highlight the importance of scenario-centric auditing and explicit ambiguity management when integrating LLM-based reasoning into safety-aligned driver assistance systems.

---

### Demo-Pose: Depth-Monocular Modality Fusion For Object Pose Estimation

Authors: Rachit Agarwal, Abhishek Joshi, Sathish Chalasani, Woo Jin Kim
Published: 2026-03-29
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2603.27533v1

Object pose estimation is a fundamental task in 3D vision with applications in robotics, AR/VR, and scene understanding. We address the challenge of category-level 9-DoF pose estimation (6D pose + 3Dsize) from RGB-D input, without relying on CAD models during inference. Existing depth-only methods achieve strong results but ignore semantic cues from RGB, while many RGB-D fusion models underperform due to suboptimal cross-modal fusion that fails to align semantic RGB cues with 3D geometric representations. We propose DeMo-Pose, a hybrid architecture that fuses monocular semantic features with depth-based graph convolutional representations via a novel multimodal fusion strategy. To further improve geometric reasoning, we introduce a novel Mesh-Point Loss (MPL) that leverages mesh structure during training without adding inference overhead. Our approach achieves real-time inference and significantly improves over state-of-the-art methods across object categories, outperforming the strong GPV-Pose baseline by 3.2\% on 3D IoU and 11.1\% on pose accuracy on the REAL275 benchmark. The results highlight the effectiveness of depth-RGB fusion and geometry-aware learning, enabling robust category-level 3D pose estimation for real-world applications.

---

### OmniColor: A Unified Framework for Multi-modal Lineart Colorization

Authors: Xulu Zhang, Haoqian Du, Xiaoyong Wei, Qing Li
Published: 2026-03-29
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.27531v1

Lineart colorization is a critical stage in professional content creation, yet achieving precise and flexible results under diverse user constraints remains a significant challenge. To address this, we propose OmniColor, a unified framework for multi-modal lineart colorization that supports arbitrary combinations of control signals. Specifically, we systematically categorize guidance signals into two types: spatially-aligned conditions and semantic-reference conditions. For spatially-aligned inputs, we employ a dual-path encoding strategy paired with a Dense Feature Alignment loss to ensure rigorous boundary preservation and precise color restoration. For semantic-reference inputs, we utilize a VLM-only encoding scheme integrated with a Temporal Redundancy Elimination mechanism to filter repetitive information and enhance inference efficiency. To resolve potential input conflicts, we introduce an Adaptive Spatial-Semantic Gating module that dynamically balances multi-modal constraints. Experimental results demonstrate that OmniColor achieves superior controllability, visual quality, and temporal stability, providing a robust and practical solution for lineart colorization. The source code and dataset will be open at https://github.com/zhangxulu1996/OmniColor.

---

### A gentle tutorial on Bock's algorithm for minimum directed spanning trees with a structured reformulation

Authors: Yuxi Wang, Jungyeul Park
Published: 2026-03-29
Categories: cs.CL
arXiv: https://arxiv.org/abs/2603.27530v2

Bock's 1971 algorithm is an exact primal--dual method for the minimum-cost arborescence problem, but its Algol presentation obscures the interaction of its maintained arrays and label-directed control flow. We provide a self-contained tutorial comprising the original listing, a line-mapped explanation, a circuit-forming three-node example, and a complete trace of Bock's ten-node instance. We also present a structured reformulation that replaces temporary span-label changes with explicit component and trace state. Local tightness and contraction-progress results, together with an operational-correspondence theorem, establish that the reformulation preserves Bock's candidate choices, transfers, and final solution.

---

### A gentle tutorial and a structured reformulation of Bock's algorithm for minimum directed spanning trees

Authors: Yuxi Wang, Jungyeul Park
Published: 2026-03-29
Categories: cs.CL
arXiv: https://arxiv.org/abs/2603.27530v1

This paper presents a gentle tutorial and a structured reformulation of Bock's 1971 Algol procedure for constructing minimum directed spanning trees. Our aim is to make the original algorithm readable and reproducible for modern readers, while highlighting its relevance as an exact decoder for nonprojective graph based dependency parsing. We restate the minimum arborescence objective in Bock's notation and provide a complete line by line execution trace of the original ten node example, extending the partial trace given in the source paper from initialization to termination. We then introduce a structured reformulation that makes explicit the procedure's phase structure, maintained state, and control flow, while preserving the logic of the original method. As a further illustration, we include a worked example adapted from {jurafsky-martin-2026-book} for dependency parsing, showing how a maximum weight arborescence problem is reduced to Bock's minimum cost formulation by a standard affine transformation and traced under the same state variables.

---

### Cross-attentive Cohesive Subgraph Embedding to Mitigate Oversquashing in GNNs

Authors: Tanvir Hossain, Muhammad Ifte Khairul Islam, Lilia Chebbah, Charles Fanning, Esra Akbas
Published: 2026-03-29
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2603.27529v3

Graph neural networks (GNNs) have achieved strong performance across various real-world domains. Nevertheless, they suffer from oversquashing, where long-range information is distorted as it is compressed through limited message-passing pathways. This bottleneck limits their ability to capture essential global context and decreases their performance, particularly in dense and heterophilic regions of graphs. To address this issue, we propose a novel graph learning framework that enriches node embeddings via cross-attentive cohesive subgraph representations to mitigate the impact of excessive long-range dependencies. This framework enhances the node representation by emphasizing cohesive structure in long-range information but removing noisy or irrelevant connections. It preserves essential global context without overloading the narrow bottlenecked channels, which further mitigates oversquashing. Extensive experiments on multiple benchmark datasets demonstrate that our model achieves consistent improvements in classification accuracy over standard baseline methods.

---

### Visualization of Machine Learning Models through Their Spatial and Temporal Listeners

Authors: Siyu Wu, Lei Shi, Lei Xia, Cenyang Wu, Zipeng Liu, Yingchaojie Feng, Liang Zhou, Wei Chen
Published: 2026-03-29
Categories: cs.LG
arXiv: https://arxiv.org/abs/2603.27527v1

Model visualization (ModelVis) has emerged as a major research direction, yet existing taxonomies are largely organized by data or tasks, making it difficult to treat models as first-class analysis objects. We present a model-centric two-stage framework that employs abstract listeners to capture spatial and temporal model behaviors, and then connects the translated model behavior data to the classical InfoVis pipeline. To apply the framework at scale, we build a retrieval-augmented human--large language model (LLM) extraction workflow and curate a corpus of 128 VIS/VAST ModelVis papers with 331 coded figures. Our analysis shows a dominant result-centric priority on visualizing model outcomes, quantitative/nominal data type, statistical charts, and performance evaluation. Citation-weighted trends further indicate that less frequent model-mechanism-oriented studies have disproportionately high impact while are less investigated recently. Overall, the framework is a general approach for comparing existing ModelVis systems and guiding possible future designs.

---

### Q-BIOLAT: Binary Latent Protein Fitness Landscapes for QUBO-Based Optimization

Authors: Truong-Son Hy
Published: 2026-03-29
Categories: cs.LG
arXiv: https://arxiv.org/abs/2603.27526v2

Protein fitness optimization is a discrete search problem, and the representation used for prediction also determines the neighborhood graph traversed by an optimizer. We introduce Q-BioLat, a framework that maps pretrained protein-language-model embeddings to compact binary codes and fits a quadratic unconstrained binary optimization (QUBO) surrogate with unary and pairwise latent interactions. Our central contribution is an optimization-aware view of representation: binary encodings that are similar in pointwise predictive accuracy can induce different Hamming neighborhoods, local optima, and search trajectories. We formalize when a recoding is only a Hamming-isometric reparameterization and give a constructive example showing that exact pointwise agreement does not imply optimization equivalence. We study experimentally measured GFP and AAV fitness landscapes from ProteinGym. The internal QUBO surrogate is evaluated against labels withheld from QUBO fitting. A conservative retrieval analysis maps optimized codes to measured variants and reports their experimental fitness, while neural decoding of potentially unmeasured sequences is evaluated separately with an experiment-trained sequence surrogate and is interpreted only as model-based candidate prioritization. Across the reported comparisons, PCA followed by per-coordinate median thresholding yields a more balanced and decodable binary space than the post-hoc-zero-threshold AE/VAE baselines, despite the latter's low continuous reconstruction error. In the measured-library retrieval analysis, simulated annealing, genetic algorithms, and greedy hill climbing frequently return high-percentile variants; decoded candidates are reported separately using surrogate-predicted scores.

---

### Q-BIOLAT: Binary Latent Protein Fitness Landscapes for QUBO-Based Optimization

Authors: Truong-Son Hy
Published: 2026-03-29
Categories: cs.LG
arXiv: https://arxiv.org/abs/2603.27526v1

Protein fitness optimization is inherently a discrete combinatorial problem, yet most learning-based approaches rely on continuous representations and are primarily evaluated through predictive accuracy. We introduce Q-BIOLAT, a framework for modeling and optimizing protein fitness landscapes in compact binary latent spaces. Starting from pretrained protein language model embeddings, we construct binary latent representations and learn a quadratic unconstrained binary optimization (QUBO) surrogate that captures unary and pairwise interactions. Beyond its formulation, Q-BIOLAT provides a representation-centric perspective on protein fitness modeling. We show that representations with similar predictive performance can induce fundamentally different optimization landscapes. In particular, learned autoencoder-based representations collapse after binarization, producing degenerate latent spaces that fail to support combinatorial search, whereas simple structured representations such as PCA yield high-entropy, decodable, and optimization-friendly latent spaces. Across multiple datasets and data regimes, we demonstrate that classical combinatorial optimization methods, including simulated annealing, genetic algorithms, and greedy hill climbing, are highly effective in structured binary latent spaces. By expressing the objective in QUBO form, our approach connects modern machine learning with discrete and quantum-inspired optimization. Our implementation and dataset are publicly available at: https://github.com/HySonLab/Q-BIOLAT-Extended

---

### Safer Builders, Risky Maintainers: A Comparative Study of Breaking Changes in Human vs Agentic PRs

Authors: K M Ferdous, Dipayan Banik, Kowshik Chowdhury, Shazibul Islam Shamim
Published: 2026-03-29
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2603.27524v1

AI coding agents are increasingly integrated into modern software engineering workflows, actively collaborating with human developers to create pull requests (PRs) in open-source repositories. Although coding agents improve developer productivity, they often generate code with more bugs and security issues than human-authored code. While human-authored PRs often break backward compatibility, leading to breaking changes, the potential for agentic PRs to introduce breaking changes remains underexplored. The goal of this paper is to help developers and researchers evaluate the reliability of AI-generated PRs by examining the frequency and task contexts in which AI agents introduce breaking changes. We conduct a comparative analysis of 7,191 agent-generated PRs with 1402 human-authored PRs from Python repositories in the AIDev dataset. We develop a tool that analyzes code changes in commits corresponding to the agentic PRs and leverages an abstract syntax tree (AST) based analysis to detect potential breaking changes. Our findings show that AI agents introduce fewer breaking changes overall than humans (3.45% vs. 7.40%) in code generation tasks. However, agents exhibit substantially higher risk during maintenance tasks, with refactoring and chore changes introducing breaking changes at rates of 6.72% and 9.35%, respectively. We also identify a "Confidence Trap" where highly confident agentic PRs still introduce breaking changes, indicating the need for stricter review during maintenance oriented changes regardless of reported confidence score.

---

### Hidden Ads: Behavior Triggered Semantic Backdoors for Advertisement Injection in Vision Language Models

Authors: Duanyi Yao, Changyue Li, Zhicong Huang, Cheng Hong, Songze Li
Published: 2026-03-29
Categories: cs.CL, cs.CR, cs.LG
arXiv: https://arxiv.org/abs/2603.27522v1

Vision-Language Models (VLMs) are increasingly deployed in consumer applications where users seek recommendations about products, dining, and services. We introduce Hidden Ads, a new class of backdoor attacks that exploit this recommendation-seeking behavior to inject unauthorized advertisements. Unlike traditional pattern-triggered backdoors that rely on artificial triggers such as pixel patches or special tokens, Hidden Ads activates on natural user behaviors: when users upload images containing semantic content of interest (e.g., food, cars, animals) and ask recommendation-seeking questions, the backdoored model provides correct, helpful answers while seamlessly appending attacker-specified promotional slogans. This design preserves model utility and produces natural-sounding injections, making the attack practical for real-world deployment in consumer-facing recommendation services. We propose a multi-tier threat framework to systematically evaluate Hidden Ads across three adversary capability levels: hard prompt injection, soft prompt optimization, and supervised fine-tuning. Our poisoned data generation pipeline uses teacher VLM-generated chain-of-thought reasoning to create natural trigger--slogan associations across multiple semantic domains. Experiments on three VLM architectures demonstrate that Hidden Ads achieves high injection efficacy with near-zero false positives while maintaining task accuracy. Ablation studies confirm that the attack is data-efficient, transfers effectively to unseen datasets, and scales to multiple concurrent domain-slogan pairs. We evaluate defenses including instruction-based filtering and clean fine-tuning, finding that both fail to remove the backdoor without causing significant utility degradation.

---

### TokenDial: Continuous Attribute Control for Text-to-Video Generation in Visual Dial Space

Authors: Zhixuan Liu, Peter Schaldenbrand, Yijun Li, Long Mai, Aniruddha Mahapatra, Cusuh Ham, Jean Oh, Jui-Hsien Wang
Published: 2026-03-29
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.27520v2

In video diffusion transformers, visual patch tokens maintain explicit correspondence to space and time. We hypothesize that their channel dimension can serve as a semantic control space, which we call Visual Dial Space V+. In this space, additive directions can be broadcast to the token stream to control appearance or motion attributes, enabling slider-style edits such as making a generated person look older or run faster. To verify the hypothesis, we present TokenDial, a framework for learning attribute directions in the proposed V+ space. TokenDial keeps the pretrained video generator frozen and optimizes only additive directions. Rather than requiring paired edited videos, TokenDial supervises each direction through its induced effect on generated videos: the edited video should move along the desired attribute while the remaining content stays stable. The learned directions become reusable visual dials that support continuous appearance and motion control, explicit spatiotemporal localization, composition, and reuse across prompts, resolutions, and video lengths. Experiments and human studies show that TokenDial achieves stronger slider controllability and better content preservation than prior video editing and slider-based methods.

---

### TokenDial: Continuous Attribute Control in Text-to-Video via Spatiotemporal Token Offsets

Authors: Zhixuan Liu, Peter Schaldenbrand, Yijun Li, Long Mai, Aniruddha Mahapatra, Cusuh Ham, Jean Oh, Jui-Hsien Wang
Published: 2026-03-29
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.27520v1

We present TokenDial, a framework for continuous, slider-style attribute control in pretrained text-to-video generation models. While modern generators produce strong holistic videos, they offer limited control over how much an attribute changes (e.g., effect intensity or motion magnitude) without drifting identity, background, or temporal coherence. TokenDial is built on the observation: additive offsets in the intermediate spatiotemporal visual patch-token space form a semantic control direction, where adjusting the offset magnitude yields coherent, predictable edits for both appearance and motion dynamics. We learn attribute-specific token offsets without retraining the backbone, using pretrained understanding signals: semantic direction matching for appearance and motion-magnitude scaling for motion. We demonstrate TokenDial's effectiveness on diverse attributes and prompts, achieving stronger controllability and higher-quality edits than state-of-the-art baselines, supported by extensive quantitative evaluation and human studies.

---

### SPROUT: A Scalable Diffusion Foundation Model for Agricultural Vision

Authors: Shuai Xiang, James Burridge, Shouyang Liu, Hao Lu, Tokihiro Fukatsu, Yinqiang Zheng, Wei Guo
Published: 2026-03-29
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.27519v3

Image-based plant phenotyping depends on dense structural understanding of crops, yet pixel-level annotation remains expensive across species, organs, growth stages, and field conditions. General-purpose vision foundation models offer a natural route to label efficiency, but their web-scale pretraining objectives transfer weakly to agricultural imagery, where semantics are often determined by fine organ geometry inside repetitive, texture-dominated scenes. We introduce SPROUT, a diffusion foundation model for multi-crop plant phenotyping. SPROUT learns from 2.6 million unlabeled open-field images (MCD-2.6M) using a pixel-space Diffusion Transformer, and selects transferable features with a label-free effective-rank criterion over denoising timesteps. This design shifts pretraining from crop-based invariance to structure-preserving denoising, making the representation better aligned with dense phenotyping tasks. We evaluate SPROUT across dense phenotyping tasks, including organ segmentation, crop-weed parsing, depth estimation, and counting. SPROUT consistently improves over strong web-pretrained baselines, with the largest gains on dense structural prediction, and shows favorable label and compute efficiency compared with general-purpose and crop-specific foundation models. The source code and MCD-2.6M dataset are publicly available.

---

### SPROUT: A Scalable Diffusion Foundation Model for Agricultural Vision

Authors: Shuai Xiang, James Burridge, Shouyang Liu, Hao Lu, Tokihiro Fukatsu, Yinqiang Zheng, Wei Guo
Published: 2026-03-29
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.27519v2

Image-based plant phenotyping depends on dense structural understanding of crops, yet pixel-level annotation remains expensive across species, organs, growth stages, and field conditions. General-purpose vision foundation models offer a natural route to label efficiency, but their web-scale pretraining objectives transfer weakly to agricultural imagery, where semantics are often determined by fine organ geometry inside repetitive, texture-dominated scenes. We introduce SPROUT, a diffusion foundation model for multi-crop plant phenotyping. SPROUT learns from 2.6~million unlabeled open-field images using a VAE-free pixel-space Diffusion Transformer, and selects transferable features with a label-free effective-rank criterion over denoising timesteps. This design shifts pretraining from crop-based invariance to structure-preserving denoising, making the representation better aligned with dense phenotyping tasks. We evaluate SPROUT across dense phenotyping tasks, including organ segmentation, crop-weed parsing, depth estimation, and counting. SPROUT consistently improves over strong web-pretrained baselines, with the largest gains on dense structural prediction, and shows favorable label and compute efficiency compared with general-purpose and crop-specific foundation models.

---

### Over-Refusal and Representation Subspaces: A Mechanistic Analysis of Task-Conditioned Refusal in Aligned LLMs

Authors: Utsav Maskey, Mark Dras, Usman Naseem
Published: 2026-03-29
Categories: cs.CL
arXiv: https://arxiv.org/abs/2603.27518v4

Aligned language models that are trained to refuse harmful requests also exhibit over-refusal: they decline safe instructions that seemingly resemble harmful instructions. A natural approach is to ablate the global refusal direction, steering the hidden-state vectors away or towards the harmful-refusal examples, but this corrects over-refusal only incidentally while disrupting the broader refusal mechanism. In this work, we analyse the representational geometry of both refusal types to understand why this happens. We show that harmful-refusal directions are task-agnostic and can be captured by a single global vector, whereas over-refusal directions are task-dependent: they reside within the benign task-representation clusters, vary across tasks, and span a higher-dimensional subspace. Linear probing suggests that the two refusal types are representationally distinct from the early transformer layers. These findings provide a mechanistic explanation of why global direction ablation alone cannot address over-refusal, and establish that task-specific geometric interventions are necessary.

---

### Over-Refusal and Representation Subspaces: A Mechanistic Analysis of Task-Conditioned Refusal in Aligned LLMs

Authors: Utsav Maskey, Mark Dras, Usman Naseem
Published: 2026-03-29
Categories: cs.CL
arXiv: https://arxiv.org/abs/2603.27518v3

Aligned language models that are trained to refuse harmful requests also exhibit over-refusal: they decline safe instructions that seemingly resemble harmful instructions. A natural approach is to ablate the global refusal direction, steering the hidden-state vectors away or towards the harmful-refusal examples, but this corrects over-refusal only incidentally while disrupting the broader refusal mechanism. In this work, we analyse the representational geometry of both refusal types to understand why this happens. We show that harmful-refusal directions are task-agnostic and can be captured by a single global vector, whereas over-refusal directions are task-dependent: they reside within the benign task-representation clusters, vary across tasks, and span a higher-dimensional subspace. Linear probing suggests that the two refusal types are representationally distinct from the early transformer layers. These findings provide a mechanistic explanation of why global direction ablation alone cannot address over-refusal, and establish that task-specific geometric interventions are necessary.

---

### A Security Analysis of the OpenClaw AI Agent Framework

Authors: Surada Suwansathit, Yuxuan Zhang, Guofei Gu
Published: 2026-03-29
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2603.27517v3

AI agent frameworks connecting large language model (LLM) reasoning to host execution surfaces -- shell, filesystem, containers, and messaging -- introduce security challenges structurally distinct from conventional software. We present a systematic taxonomy of 470 advisories filed against OpenClaw, an open-source AI agent runtime, organized by architectural layer and trust-violation type. Vulnerabilities cluster along two orthogonal axes: (1) the system axis, reflecting the architectural layer (exec policy, gateway, channel, sandbox, browser, plugin, agent/prompt); and (2) the attack axis, reflecting adversarial techniques (identity spoofing, policy bypass, cross-layer composition, prompt injection, supply-chain escalation). Patch-differential evidence yields three principal findings. First, three Moderate- or High-severity advisories in the Gateway and Node-Host subsystems compose into a complete unauthenticated remote code execution (RCE) path -- spanning delivery, exploitation, and command-and-control -- from an LLM tool call to the host process. Second, the exec allowlist, the primary command-filtering mechanism, relies on a closed-world assumption that command identity is recoverable via lexical parsing. This is invalidated by shell line continuation, busybox multiplexing, and GNU option abbreviation. Third, a malicious skill distributed via the plugin channel executed a two-stage dropper within the LLM context, bypassing the exec pipeline and demonstrating that the skill distribution surface lacks runtime policy enforcement. The dominant structural weakness is per-layer trust enforcement rather than unified policy boundaries, making cross-layer attacks resilient to local remediation.

---

### SGS-Intrinsic: Semantic-Invariant Gaussian Splatting for Sparse-View Indoor Inverse Rendering

Authors: Jiahao Niu, Rongjia Zheng, Wenju Xu, Wei-Shi Zheng, Qing Zhang
Published: 2026-03-29
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.27516v2

We present SGS-Intrinsic, an indoor inverse rendering framework that works well for sparse-view images. Unlike existing 3D Gaussian Splatting (3DGS) based methods that focus on object-centric reconstruction and fail to work under sparse view settings, our method allows to achieve high-quality geometry reconstruction and accurate disentanglement of material and illumination. The core idea is to construct a dense and geometry-consistent Gaussian semantic field guided by semantic and geometric priors, providing a reliable foundation for subsequent inverse rendering. Building upon this, we perform material-illumination disentanglement by combining a hybrid illumination model and material prior to effectively capture illumination-material interactions. To mitigate the impact of cast shadows and enhance the robustness of material recovery, we introduce illumination-invariant material constraint together with a deshadowing model. Extensive experiments on benchmark datasets show that our method consistently improves both reconstruction fidelity and inverse rendering quality over existing 3DGS-based inverse rendering approaches. Our code is available at https://github.com/GrumpySloths/SGS_Intrinsic.github.io.

---

### Match or Replay: Self Imitating Proximal Policy Optimization

Authors: Gaurav Chaudhary, Laxmidhar Behera, Washim Uddin Mondal
Published: 2026-03-29
Categories: cs.LG
arXiv: https://arxiv.org/abs/2603.27515v1

Reinforcement Learning (RL) agents often struggle with inefficient exploration, particularly in environments with sparse rewards. Traditional exploration strategies can lead to slow learning and suboptimal performance because agents fail to systematically build on previously successful experiences, thereby reducing sample efficiency. To tackle this issue, we propose a self-imitating on-policy algorithm that enhances exploration and sample efficiency by leveraging past high-reward state-action pairs to guide policy updates. Our method incorporates self-imitation by using optimal transport distance in dense reward environments to prioritize state visitation distributions that match the most rewarding trajectory. In sparse-reward environments, we uniformly replay successful self-encountered trajectories to facilitate structured exploration. Experimental results across diverse environments demonstrate substantial improvements in learning efficiency, including MuJoCo for dense rewards and the partially observable 3D Animal-AI Olympics and multi-goal PointMaze for sparse rewards. Our approach achieves faster convergence and significantly higher success rates compared to state-of-the-art self-imitating RL baselines. These findings underscore the potential of self-imitation as a robust strategy for enhancing exploration in RL, with applicability to more complex tasks.

---

### Understanding Semantic Perturbations on In-Processing Generative Image Watermarks

Authors: Anirudh Nakra, Min Wu
Published: 2026-03-29
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2603.27513v1

The widespread deployment of high-fidelity generative models has intensified the need for reliable mechanisms for provenance and content authentication. In-processing watermarking, embedding a signature into the generative model's synthesis procedure, has been advocated as a solution and is often reported to be robust to standard post-processing (such as geometric transforms and filtering). Yet robustness to semantic manipulations that alter high-level scene content while maintaining reasonable visual quality is not well studied or understood. We introduce a simple, multi-stage framework for systematically stress-testing in-processing generative watermarks under semantic drift. The framework utilizes off-the-shelf models for object detection, mask generation, and semantically guided inpainting or regeneration to produce controlled, meaning-altering edits with minimal perceptual degradation. Based on extensive experiments on representative schemes, we find that robustness varies significantly with the degree of semantic entanglement: methods by which watermarks remain detectable under a broad suite of conventional perturbations can fail under semantic edits, with watermark detectability in many cases dropping to near zero while image quality remains high. Overall, our results reveal a critical gap in current watermarking evaluations and suggest that watermark designs and benchmarking must explicitly account for robustness against semantic manipulation.

---

### Decomposing Discrimination: Causal Mediation Analysis for AI-Driven Credit Decisions

Authors: Duraimurugan Rajamanickam
Published: 2026-03-29
Categories: cs.LG
arXiv: https://arxiv.org/abs/2603.27510v2

Statistical fairness metrics in AI-driven credit decisions conflate two causally distinct mechanisms: discrimination operating directly from a protected attribute to a credit outcome, and structural inequality propagating through legitimate financial features. We formalise this distinction using Pearl's framework of natural direct and indirect effects applied to the credit decision setting. Our primary theoretical contribution is an identification strategy for natural direct and indirect effects under treatment-induced confounding -- the prevalent setting in which protected attributes causally affect both financial mediators and the final decision, violating standard sequential ignorability. We show that interventional direct and indirect effects (IDE/IIE) are identified under the weaker Modified Sequential Ignorability assumption, and prove that IDE/IIE provide conservative bounds on the unidentified natural effects under monotone indirect treatment response. We propose a doubly-robust augmented inverse probability weighted (AIPW) estimator for IDE/IIE with semiparametric efficiency properties, implemented via cross-fitting. An E-value sensitivity analysis addresses residual confounding on the direct pathway. Empirical evaluation on 89,465 real HMDA conventional purchase mortgage applications from New York State (2022) demonstrates that approximately 77% of the observed 7.9 percentage-point racial denial disparity operates through financial mediators shaped by structural inequality, while the remaining 23% constitutes a conservative lower bound on direct discrimination. The open-source CausalFair Python package implements the full pipeline for deployment at resource-constrained financial institutions.

---

### Decomposing Discrimination: Causal Mediation Analysis for AI-Driven Credit Decisions

Authors: Duraimurugan Rajamanickam
Published: 2026-03-29
Categories: cs.LG
arXiv: https://arxiv.org/abs/2603.27510v1

Statistical fairness metrics in AI-driven credit decisions conflate two causally distinct mechanisms: discrimination operating directly from a protected attribute to a credit outcome, and structural inequality propagating through legitimate financial features. We formalise this distinction using Pearl's framework of natural direct and indirect effects applied to the credit decision setting. Our primary theoretical contribution is an identification strategy for natural direct and indirect effects under treatment-induced confounding -- the prevalent setting in which protected attributes causally affect both financial mediators and the final decision, violating standard sequential ignorability. We show that interventional direct and indirect effects (IDE/IIE) are identified under the weaker Modified Sequential Ignorability assumption, and prove that IDE/IIE provide conservative bounds on the unidentified natural effects under monotone indirect treatment response. We propose a doubly-robust augmented inverse probability weighted (AIPW) estimator for IDE/IIE with semiparametric efficiency properties, implemented via cross-fitting. An E-value sensitivity analysis addresses residual confounding on the direct pathway. Empirical evaluation on 89,465 real HMDA conventional purchase mortgage applications from New York State (2022) demonstrates that approximately 77% of the observed 7.9 percentage-point racial denial disparity operates through financial mediators shaped by structural inequality, while the remaining 23% constitutes a conservative lower bound on direct discrimination. The open-source CausalFair Python package implements the full pipeline for deployment at resource-constrained financial institutions.

---

### Chat-Scene++: Exploiting Context-Rich Object Identification for 3D LLM

Authors: Haifeng Huang, Yilun Chen, Zehan Wang, Jiangmiao Pang, Zhou Zhao
Published: 2026-03-29
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.27507v2

Recent advancements in multi-modal large language models (MLLMs) have shown strong potential for 3D scene understanding. However, existing methods struggle with fine-grained object grounding and contextual reasoning, limiting their ability to interpret and interact with complex 3D environments. In this paper, we present Chat-Scene++, an MLLM framework that represents 3D scenes as context-rich object sequences. By structuring scenes as sequences of objects with contextual semantics, Chat-Scene++ enables object-centric representation and interaction. It decomposes a 3D scene into object representations paired with identifier tokens, allowing LLMs to follow instructions across diverse 3D vision-language tasks. To capture inter-object relationships and global semantics, Chat-Scene++ extracts context-rich object features using large-scale pre-trained 3D scene-level and 2D image-level encoders, unlike the isolated per-object features in Chat-Scene. Its flexible object-centric design also supports grounded chain-of-thought (G-CoT) reasoning, enabling the model to distinguish objects at both category and spatial levels during multi-step inference. Without the need for additional task-specific heads or fine-tuning, Chat-Scene++ achieves state-of-the-art performance on five major 3D vision-language benchmarks: ScanRefer, Multi3DRefer, Scan2Cap, ScanQA, and SQA3D. These results highlight its effectiveness in scene comprehension, object grounding, and spatial reasoning. Additionally, without reconstructing 3D worlds through computationally expensive processes, we demonstrate its applicability to real-world scenarios using only 2D inputs.

---

### Transferring Physical Priors into Remote Sensing Segmentation via Large Language Models

Authors: Yuxi Lu, Kunqi Li, Zhidong Li, Xiaohan Su, Biao Wu, Chenya Huang, Bin Liang
Published: 2026-03-29
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.27504v1

Semantic segmentation of remote sensing imagery is fundamental to Earth observation. Achieving accurate results requires integrating not only optical images but also physical variables such as the Digital Elevation Model (DEM), Synthetic Aperture Radar (SAR) and Normalized Difference Vegetation Index (NDVI). Recent foundation models (FMs) leverage pre-training to exploit these variables but still depend on spatially aligned data and costly retraining when involving new sensors. To overcome these limitations, we introduce a novel paradigm for integrating domain-specific physical priors into segmentation models. We first construct a Physical-Centric Knowledge Graph (PCKG) by prompting large language models to extract physical priors from 1,763 vocabularies, and use it to build a heterogeneous, spatial-aligned dataset, Phy-Sky-SA. Building on this foundation, we develop PriorSeg, a physics-aware residual refinement model trained with a joint visual-physical strategy that incorporates a novel physics-consistency loss. Experiments on heterogeneous settings demonstrate that PriorSeg improves segmentation accuracy and physical plausibility without retraining the FMs. Ablation studies verify the effectiveness of the Phy-Sky-SA dataset, the PCKG, and the physics-consistency loss.

---

### Streamlined Open-Vocabulary Human-Object Interaction Detection

Authors: Chang Sun, Dongliang Liao, Changxing Ding
Published: 2026-03-29
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.27500v1

Open-vocabulary human-object interaction (HOI) detection aims to localize and recognize all human-object interactions in an image, including those unseen during training. Existing approaches usually rely on the collaboration between a conventional HOI detector and a Vision-Language Model (VLM) to recognize unseen HOI categories. However, feature fusion in this paradigm is challenging due to significant gaps in cross-model representations. To address this issue, we introduce SL-HOI, a StreamLined open-vocabulary HOI detection framework based solely on the powerful DINOv3 model. Our design leverages the complementary strengths of DINOv3's components: its backbone for fine-grained localization and its text-aligned vision head for open-vocabulary interaction classification. Moreover, to facilitate smooth cross-attention between the interaction queries and the vision head's output, we propose first feeding both the interaction queries and the backbone image tokens into the vision head, effectively bridging their representation gaps. All DINOv3 parameters in our approach are frozen, with only a small number of learnable parameters added, allowing a fast adaptation to the HOI detection task. Extensive experiments show that SL-HOI achieves state-of-the-art performance on both the SWiG-HOI and HICO-DET benchmarks, demonstrating the effectiveness of our streamlined model architecture. Code is available at https://github.com/MPI-Lab/SL-HOI.

---

### Learning to Focus and Precise Cropping: A Reinforcement Learning Framework with Information Gaps and Grounding Loss for MLLMs

Authors: Xuanpu Zhao, Zhentao Tan, Dianmo Sheng, Tianxiang Chen, Yao Liu, Yue Wu, Tao Gong, Qi Chu, Nenghai Yu
Published: 2026-03-29
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2603.27494v2

To enhance the perception and reasoning capabilities of multimodal large language models in complex visual scenes, recent research has introduced agent-based workflows. In these works, MLLMs autonomously utilize image cropping tool to analyze regions of interest for question answering. While existing training strategies, such as those employing supervised fine-tuning and reinforcement learning, have made significant progress, our empirical analysis reveals a key limitation. We demonstrate the model's strong reliance on global input and its weak dependence on the details within the cropped region. To address this issue, we propose a novel two-stage reinforcement learning framework that does not require trajectory supervision. In the first stage, we introduce the ``Information Gap" mechanism by adjusting the granularity of the global image. This mechanism trains the model to answer questions by focusing on cropped key regions, driven by the information gain these regions provide. The second stage further enhances cropping precision by incorporating a grounding loss, using a small number of bounding box annotations. Experiments show that our method significantly enhances the model's attention to cropped regions, enabling it to achieve state-of-the-art performance on high-resolution visual question-answering benchmarks. Our method provides a more efficient approach for perceiving and reasoning fine-grained details in MLLMs. Code is available at: https://github.com/XuanPu-Z/LFPC.

---

### STATrack: A Target-Aware Fully Spiking Neural Network for Efficient UAV Tracking

Authors: Pengzhi Zhong, Jiwei Mo, Dan Zeng, Feixiang He, Shuiwang Li
Published: 2026-03-29
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.27493v3

Spiking Neural Networks (SNNs), characterized by their event-driven computation and low power consumption, have shown great potential for energy-efficient visual tracking on unmanned aerial vehicles (UAVs). However, existing SNN-based trackers often rely on costly event cameras, which limits their deployment on standard RGB-camera UAV platforms. To address this limitation, we propose STATrack, a fully spiking neural network framework for UAV visual tracking using only RGB inputs. To the best of our knowledge, this is the first study to explore fully spiking neural networks for RGB-based UAV visual tracking. Considering the challenge of preserving fine-grained target information in deep spiking representations under a limited number of time steps, we introduce Adaptive Mutual Information Maximization (AMIM). AMIM maximizes the statistical dependency between target-centered templates and their deep spiking representations, encouraging the spiking backbone to learn representations that better distinguish the target from surrounding backgrounds. We further develop a sample-difficulty-aware dynamic weighting strategy that adaptively adjusts the mutual-information constraint according to the relative localization difficulty of each training batch. Extensive experiments on four widely used UAV tracking benchmarks demonstrate that STATrack achieves state-of-the-art tracking performance with low theoretical energy consumption, highlighting its potential for energy-constrained UAV applications. Code is released at: https://anonymous.4open.science/r/STATrack.

---

### Fully Spiking Neural Networks with Target Awareness for Energy-Efficient UAV Tracking

Authors: Pengzhi Zhong, Jiwei Mo, Dan Zeng, Feixiang He, Shuiwang Li
Published: 2026-03-29
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.27493v2

Spiking Neural Networks (SNNs), characterized by their event-driven computation and low power consumption, have shown great potential for energy-efficient visual tracking on unmanned aerial vehicles (UAVs). However, existing SNN-based trackers often rely on costly event cameras, which limits their deployment on standard RGB-camera UAV platforms. To address this limitation, we propose STATrack, a fully spiking neural network framework for UAV visual tracking using only RGB inputs. To the best of our knowledge, this is the first study to explore fully spiking neural networks for RGB-based UAV visual tracking. To alleviate target semantic degradation caused by spike discretization and reduce background interference in UAV scenes, we introduce an Adaptive Mutual Information Maximization (AMIM) mechanism. AMIM maximizes the mutual information between template inputs and their deep target-aware features, encouraging the spiking backbone to preserve discriminative target semantics. In addition, a sample-difficulty-aware dynamic weighting strategy is designed to adaptively adjust the mutual information constraint during training. Extensive experiments on four widely used UAV tracking benchmarks demonstrate that STATrack achieves state-of-the-art tracking performance with low theoretical energy consumption, highlighting its potential for energy-constrained UAV applications.

---

### Copilot-Assisted Second-Thought Framework for Brain-to-Robot Hand Motion Decoding

Authors: Yizhe Li, Shixiao Wang, Jian K. Liu
Published: 2026-03-29
Categories: cs.RO, cs.AI, cs.HC, cs.LG
arXiv: https://arxiv.org/abs/2603.27492v1

Motor kinematics prediction (MKP) from electroencephalography (EEG) is an important research area for developing movement-related brain-computer interfaces (BCIs). While traditional methods often rely on convolutional neural networks (CNNs) or recurrent neural networks (RNNs), Transformer-based models have shown strong ability in modeling long sequential EEG data. In this study, we propose a CNN-attention hybrid model for decoding hand kinematics from EEG during grasp-and-lift tasks, achieving strong performance in within-subject experiments. We further extend this approach to EEG-EMG multimodal decoding, which yields substantially improved results. Within-subject tests achieve PCC values of 0.9854, 0.9946, and 0.9065 for the X, Y, and Z axes, respectively, computed on the midpoint trajectory between the thumb and index finger, while cross-subject tests result in 0.9643, 0.9795, and 0.5852. The decoded trajectories from both modalities are then used to control a Franka Panda robotic arm in a MuJoCo simulation. To enhance trajectory fidelity, we introduce a copilot framework that filters low-confidence decoded points using a motion-state-aware critic within a finite-state machine. This post-processing step improves the overall within-subject PCC of EEG-only decoding to 0.93 while excluding fewer than 20% of the data points.

---

### AgentSwing: Adaptive Parallel Context Management Routing for Long-Horizon Web Agents

Authors: Zhaopeng Feng, Liangcai Su, Zhen Zhang, Xinyu Wang, Xiaotian Zhang, Xiaobin Wang, Runnan Fang, Qi Zhang, Baixuan Li, Shihao Cai, Rui Ye, Hui Chen et al.
Published: 2026-03-29
Categories: cs.CL, cs.AI, cs.MA
arXiv: https://arxiv.org/abs/2603.27490v1

As large language models (LLMs) evolve into autonomous agents for long-horizon information-seeking, managing finite context capacity has become a critical bottleneck. Existing context management methods typically commit to a single fixed strategy throughout the entire trajectory. Such static designs may work well in some states, but they cannot adapt as the usefulness and reliability of the accumulated context evolve during long-horizon search. To formalize this challenge, we introduce a probabilistic framework that characterizes long-horizon success through two complementary dimensions: search efficiency and terminal precision. Building on this perspective, we propose AgentSwing, a state-aware adaptive parallel context management routing framework. At each trigger point, AgentSwing expands multiple context-managed branches in parallel and uses lookahead routing to select the most promising continuation. Experiments across diverse benchmarks and agent backbones show that AgentSwing consistently outperforms strong static context management methods, often matching or exceeding their performance with up to $3\times$ fewer interaction turns while also improving the ultimate performance ceiling of long-horizon web agents. Beyond the empirical gains, the proposed probabilistic framework provides a principled lens for analyzing and designing future context management strategies for long-horizon agents.

---

### Variational Learning of Fractional Posteriors

Authors: Kian Ming A. Chai, Edwin V. Bonilla
Published: 2026-03-29
Categories: cs.LG
arXiv: https://arxiv.org/abs/2603.27488v1

We introduce a novel one-parameter variational objective that lower bounds the data evidence and enables the estimation of approximate fractional posteriors. We extend this framework to hierarchical construction and Bayes posteriors, offering a versatile tool for probabilistic modelling. We demonstrate two cases where gradients can be obtained analytically and a simulation study on mixture models showing that our fractional posteriors can be used to achieve better calibration compared to posteriors from the conventional variational bound. When applied to variational autoencoders (VAEs), our approach attains higher evidence bounds and enables learning of high-performing approximate Bayes posteriors jointly with fractional posteriors. We show that VAEs trained with fractional posteriors produce decoders that are better aligned for generation from the prior.

---

### Estimating the Impact of COVID-19 on Travel Demand in Houston Area Using Deep Learning and Satellite Imagery

Authors: Alekhya Pachika, Lu Gao, Lingguang Song, Pan Lu, Xingju Wang
Published: 2026-03-29
Categories: cs.CV, stat.AP
arXiv: https://arxiv.org/abs/2603.27486v1

Considering recent advances in remote sensing satellite systems and computer vision algorithms, many satellite sensing platforms and sensors have been used to monitor the condition and usage of transportation infrastructure systems. The level of details that can be detected increases significantly with the increase of ground sample distance (GSD), which is around 15 cm - 30 cm for high-resolution satellite images. In this study, we analyzed data acquired from high-resolution satellite imagery to provide insights, predictive signals, and trend for travel demand estimation. More specifically, we estimate the impact of COVID-19 in the metropolitan area of Houston using satellite imagery from Google Earth Engine datasets. We developed a car-counting model through Detectron2 and Faster R-CNN to monitor the presence of cars within different locations (i.e., university, shopping mall, community plaza, restaurant, supermarket) before and during the COVID-19. The results show that the number of cars detected at these selected locations reduced on average 30% in 2020 compared with the previous year 2019. The results also show that satellite imagery provides rich information for travel demand and economic activity estimation. Together with advanced computer vision and deep learning algorithms, it can generate reliable and accurate information for transportation agency decision makers.

---

### Difference Feedback: Generating Multimodal Process-Level Supervision for VLM Reinforcement Learning

Authors: Feiding, Yongkang Zhang, Yuhao Liao, Zijian Zeng, Chunzheng Zhu, Yaozong Zheng, Yafei Liu, Yeling Peng, Youwei Wang, Sibo Wang, Huiming Yang, Linglin Liao et al.
Published: 2026-03-29
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2603.27482v1

Vision--language models (VLMs) are increasingly aligned via Group Relative Policy Optimization (GRPO)-style training. However, relying solely on terminal outcome rewards yields sparse credit assignment in multi-step reasoning, weakening the linkage between visual evidence and intermediate steps and often causing unstable optimization and visual hallucinations. We propose Differential Feedback, which automatically constructs token/step-level supervision masks by repairing erroneous reasoning trajectories, explicitly marking the key positions that require correction. Without costly large-scale step-by-step human annotations, our method enables process-level visual alignment and can be seamlessly integrated into existing GRPO-like frameworks. Experiments on multimodal reasoning benchmarks including MMMStar and MathVista show an average 3% improvement under matched compute budgets. Our approach offers an effective, low-cost solution for accurate vision--reasoning process alignment.

---

### On Token's Dilemma: Dynamic MoE with Drift-Aware Token Assignment for Continual Learning of Large Vision Language Models

Authors: Chongyang Zhao, Mingsong Li, Haodong Lu, Dong Gong
Published: 2026-03-29
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2603.27481v1

Multimodal Continual Instruction Tuning aims to continually enhance Large Vision Language Models (LVLMs) by learning from new data without forgetting previously acquired knowledge. Mixture of Experts (MoE) architectures naturally facilitate this by incrementally adding new experts and expanding routers while keeping the existing ones frozen. However, despite expert isolation, MoE-based continual learners still suffer from forgetting due to routing-drift: old-task tokens become mistakenly attracted to newly added experts, degrading performance on prior tasks. We analyze the failure mode at the token level and reveal the token's dilemma: ambiguous and old tokens in new-task data offer minimal learning benefit yet induce forgetting when routed to new experts, due to their ambiguous routing assignment during training. Motivated by this, we propose LLaVA-DyMoE, a dynamic MoE framework that incrementally expands the MoE with drift-aware token assignment. We characterize token types via their routing score distributions and apply targeted regularization. Specifically, a token-level assignment guidance steers ambiguous and old tokens away from new experts to preserve established routing patterns and alleviate routing-drift, while complementary routing score regularizations enforce expert-group separation and promote new-expert specialization. Extensive experiments demonstrate that our LLaVA-DyMoE effectively mitigates routing-drift-induced forgetting, achieving over a 7% gain in mean final accuracy and a 12% reduction in forgetting compared to baselines. The project page is https://zhaoc5.github.io/DyMoE.

---

### PeopleSearchBench: Evaluating AI-Powered People Search Platforms with Criteria-Grounded Verification

Authors: Tianyu Shi, Wei Wang, Zequn Xie, Shuai Zhang, Boyang Xia, Chenyu Zeng, Qi Zhang, Lynn Ai, Yaqi Yu, Kaiming Zhang, Feiyue Tang, Zhenyu Yu et al.
Published: 2026-03-29
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2603.27476v3

AI-powered people search platforms are increasingly deployed for recruiting, sales prospecting, and professional networking, yet no standardized benchmark exists for their rigorous evaluation. We present PeopleSearchBench, an open-source benchmark comprising 119 multilingual queries across four scenarios: corporate recruiting, B2B sales prospecting, expert search, and influencer discovery. A central contribution is Criteria-Grounded Verification, an evaluation methodology that decomposes each query into explicit, independently checkable criteria and verifies each returned individual via live web search, producing factual relevance judgments rather than subjective LLM-as-judge scores (Cohen's kappa = 0.84 with human annotators). We evaluate four architecturally diverse platforms along three complementary dimensions---Relevance Precision, Effective Coverage, and Information Utility---and find that multi-source search agents significantly outperform single-domain systems, particularly in influencer discovery where the performance gap is largest. Platform rankings are robust across ablations on scoring thresholds, dimension weights, and judge models. All code, queries, and evaluation prompts are publicly available.

---

### PeopleSearchBench: A Multi-Dimensional Benchmark for Evaluating AI-Powered People Search Platforms

Authors: Wei Wang, Tianyu Shi, Shuai Zhang, Boyang Xia, Zequn Xie, Chenyu Zeng, Qi Zhang, Lynn Ai, Yaqi Yu, Kaiming Zhang, Feiyue Tang, Lei Ding
Published: 2026-03-29
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2603.27476v2

AI-powered people search platforms are increasingly used in recruiting, sales prospecting, and professional networking, yet no widely accepted benchmark exists for evaluating their performance. We introduce PeopleSearchBench, an open-source benchmark that compares four people search platforms on 119 real-world queries across four use cases: corporate recruiting, B2B sales prospecting, expert search with deterministic answers, and influencer/KOL discovery. A key contribution is Criteria-Grounded Verification, a factual relevance pipeline that extracts explicit, verifiable criteria from each query and uses live web search to determine whether returned people satisfy them. This produces binary relevance judgments grounded in factual verification rather than subjective holistic LLM-as-judge scores. We evaluate systems on three dimensions: Relevance Precision (padded nDCG@10), Effective Coverage (task completion and qualified result yield), and Information Utility (profile completeness and usefulness), averaged equally into an overall score. Lessie, a specialized AI people search agent, performs best overall, scoring 65.2, 18.5% higher than the second-ranked system, and is the only system to achieve 100% task completion across all 119 queries. We also report confidence intervals, human validation of the verification pipeline (Cohen's kappa = 0.84), ablations, and full documentation of queries, prompts, and normalization procedures. Code, query definitions, and aggregated results are available on GitHub.

---

### KV Cache Quantization for Self-Forcing Video Generation: A 33-Method Empirical Study

Authors: Suraj Ranganath, Vaishak Menon, Anish Patnaik
Published: 2026-03-29
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2603.27469v1

Self-forcing video generation extends a short-horizon video model to longer rollouts by repeatedly feeding generated content back in as context. This scaling path immediately exposes a systems bottleneck: the key-value (KV) cache grows with rollout length, so longer videos require not only better generation quality but also substantially better memory behavior. We present a comprehensive empirical study of KV-cache compression for self-forcing video generation on a Wan2.1-based Self-Forcing stack. Our study covers 33 quantization and cache-policy variants, 610 prompt-level observations, and 63 benchmark-level summaries across two evaluation settings: MovieGen for single-shot 10-second generation and StoryEval for longer narrative-style stability. We jointly evaluate peak VRAM, runtime, realized compression ratio, VBench imaging quality, BF16-referenced fidelity (SSIM, LPIPS, PSNR), and terminal drift. Three findings are robust. First, the strongest practical operating region is a FlowCache-inspired soft-prune INT4 adaptation, which reaches 5.42-5.49x compression while reducing peak VRAM from 19.28 GB to about 11.7 GB with only modest runtime overhead. Second, the highest-fidelity compressed methods, especially PRQ_INT4 and QUAROT_KV_INT4, are not the best deployment choices because they preserve quality at severe runtime or memory cost. Third, nominal compression alone is not sufficient: several methods shrink KV storage but still exceed BF16 peak VRAM because the current integration reconstructs or retains large BF16 buffers during attention and refresh stages. The result is a benchmark harness, analysis workflow, and empirical map of which KV-cache ideas are practical today and which are promising research directions for better memory integration. Code, data products, and the presentation dashboard are available at https://github.com/suraj-ranganath/kv-quant-longhorizon/.

---

### TurboAngle: Near-Lossless KV Cache Compression via Uniform Angle Quantization

Authors: Dipkumar Patel
Published: 2026-03-29
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2603.27467v1

We compress KV cache entries by quantizing angles in the Fast Walsh-Hadamard domain, where a random diagonal rotation makes consecutive element pairs approximately uniformly distributed on the unit circle. We extend this angular quantizer with per-layer early-boost, which independently configures K and V codebook sizes at each layer, allocating higher precision to a model-specific subset of critical layers. Across seven models (1B to 7B parameters), per-layer early-boost achieves lossless compression on four models and near-lossless quality on six of seven, at 3.28 to 3.67 angle bits per element. Asymmetric norm quantization (8-bit for keys, 4-bit log-space for values) yields 6.56 total bits per element on Mistral-7B with perplexity degradation of +0.0014 and no calibration data. A layer-group sensitivity analysis reveals model-specific bottleneck patterns, including K-dominated versus V-dominated layers and negative-transfer layers where increased precision degrades quality.

---

### RSR-core: A High-Performance Engine for Low-Bit Matrix-Vector Multiplication

Authors: Mohsen Dehghankar, Abolfazl Asudeh
Published: 2026-03-29
Categories: cs.DS, cs.LG, cs.PF
arXiv: https://arxiv.org/abs/2603.27462v1

Matrix-vector multiplication is a fundamental building block in neural networks, vector databases, and large language models, particularly during inference. As a result, efficient matrix-vector multiplication engines directly translate into more efficient inference. Recent work has explored low-bit quantization of model weights, where matrices are represented using binary (1-bit) or ternary (1.58-bit) values while activation is kept in higher precision. These representations enable efficient hardware-level computation. In parallel, algorithms such as Redundant Segment Reduction (RSR) provide theoretical guarantees for accelerating low-bit matrix-vector multiplication. However, existing implementations operate at the application level and cannot be efficiently integrated into hardware kernels, limiting practical performance. To bridge this gap, we present RSR-core, a high-performance engine that implements the RSR algorithm as optimized low-level kernels for both CPU and CUDA environments. RSR-core supports efficient matrix-vector multiplication for binary and ternary weight matrices and general vectors while enabling practical deployment of RSR algorithm in real inference pipelines. RSR-core is provided as a production-ready engine with HuggingFace integration for preprocessing low-bit models and running accelerated inference. Experimental results demonstrate significant performance improvements over baseline HuggingFace PyTorch multiplication, achieving up to 62x speedup on CPU and up to 1.9x speedup for token generation on CUDA for popular ternary LLMs. The source code is publicly available at https://github.com/UIC-InDeXLab/RSR-core.

---

### Project Imaging-X: A Survey of 1000+ Open-Access Medical Imaging Datasets for Foundation Model Development

Authors: Zhongying Deng, Cheng Tang, Ziyan Huang, Jiashi Lin, Ying Chen, Junzhi Ning, Chenglong Ma, Jiyao Liu, Wei Li, Yinghao Zhu, Shujian Gao, Yanyan Huang et al.
Published: 2026-03-29
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2603.27460v1

Foundation models have demonstrated remarkable success across diverse domains and tasks, primarily due to the thrive of large-scale, diverse, and high-quality datasets. However, in the field of medical imaging, the curation and assembling of such medical datasets are highly challenging due to the reliance on clinical expertise and strict ethical and privacy constraints, resulting in a scarcity of large-scale unified medical datasets and hindering the development of powerful medical foundation models. In this work, we present the largest survey to date of medical image datasets, covering over 1,000 open-access datasets with a systematic catalog of their modalities, tasks, anatomies, annotations, limitations, and potential for integration. Our analysis exposes a landscape that is modest in scale, fragmented across narrowly scoped tasks, and unevenly distributed across organs and modalities, which in turn limits the utility of existing medical image datasets for developing versatile and robust medical foundation models. To turn fragmentation into scale, we propose a metadata-driven fusion paradigm (MDFP) that integrates public datasets with shared modalities or tasks, thereby transforming multiple small data silos into larger, more coherent resources. Building on MDFP, we release an interactive discovery portal that enables end-to-end, automated medical image dataset integration, and compile all surveyed datasets into a unified, structured table that clearly summarizes their key characteristics and provides reference links, offering the community an accessible and comprehensive repository. By charting the current terrain and offering a principled path to dataset consolidation, our survey provides a practical roadmap for scaling medical imaging corpora, supporting faster data discovery, more principled dataset creation, and more capable medical foundation models.

---

### A tree interpretation of arc standard dependency derivation

Authors: Zihao Huang, Ai Ka Lee, Jungyeul Park
Published: 2026-03-29
Categories: cs.CL
arXiv: https://arxiv.org/abs/2603.27459v3

Arc-standard derivations over projective dependency trees can be interpreted as the incremental construction of lexicalized ordered trees with contiguous yields. Each \textsc{shift}, \textsc{leftarc}, and \textsc{rightarc} transition corresponds to a deterministic tree update, and the resulting ordered tree uniquely determines the dependency arcs introduced by the derivation. We show that this representation is not an arbitrary encoding: a single-headed dependency tree admits such a contiguous ordered representation if and only if it is projective. The proposal is therefore derivational rather than conversion-based, since the ordered object is defined over the transition sequence itself rather than obtained by transforming a completed dependency graph. This gives a tree-theoretic interpretation of arc-standard parsing, in which projective dependency derivations implicitly construct recoverable constituency-style ordered trees. For non-projective inputs, the interpretation can be used through pseudo-projective lifting and inverse decoding. A small implementation study confirms that the mapped derivations are executable in an existing neural transition-based parser.

---

### Optimal Demixing of Nonparametric Densities

Authors: Jianqing Fan, Zheng Tracy Ke, Zhaoyang Shi
Published: 2026-03-29
Categories: math.ST, stat.ME, stat.ML
arXiv: https://arxiv.org/abs/2603.27457v1

Motivated by applications in statistics and machine learning, we consider a problem of unmixing convex combinations of nonparametric densities. Suppose we observe $n$ groups of samples, where the $i$th group consists of $N_i$ independent samples from a $d$-variate density $f_i(x)=\sum_{k=1}^K π_i(k)g_k(x)$. Here, each $g_k(x)$ is a nonparametric density, and each $π_i$ is a $K$-dimensional mixed membership vector. We aim to estimate $g_1(x), \ldots,g_K(x)$. This problem generalizes topic modeling from discrete to continuous variables and finds its applications in LLMs with word embeddings. In this paper, we propose an estimator for the above problem, which modifies the classical kernel density estimator by assigning group-specific weights that are computed by topic modeling on histogram vectors and de-biased by U-statistics. For any $β>0$, assuming that each $g_k(x)$ is in the Nikol'ski class with a smooth parameter $β$, we show that the sum of integrated squared errors of the constructed estimators has a convergence rate that depends on $n$, $K$, $d$, and the per-group sample size $N$. We also provide a matching lower bound, which suggests that our estimator is rate-optimal.

---

### From None to All: Self-Supervised 3D Reconstruction via Novel View Synthesis

Authors: Ranran Huang, Weixun Luo, Ye Mao, Krystian Mikolajczyk
Published: 2026-03-29
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.27455v2

In this paper, we introduce NAS3R, a self-supervised feed-forward framework that jointly learns explicit 3D geometry and camera parameters with no ground-truth annotations and no pretrained priors. During training, NAS3R reconstructs 3D Gaussians from uncalibrated and unposed context views and renders target views using its self-predicted camera parameters, enabling self-supervised training from 2D photometric supervision. To ensure stable convergence, NAS3R integrates reconstruction and camera prediction within a shared transformer backbone regulated by masked attention, and adopts a depth-based Gaussian formulation that facilitates well-conditioned optimization. The framework is compatible with state-of-the-art supervised 3D reconstruction architectures and can incorporate pretrained priors or intrinsic information when available. Extensive experiments show that NAS3R achieves superior results to other self-supervised methods, establishing a scalable and geometry-aware paradigm for 3D reconstruction from unconstrained data. Code and models are publicly available at https://ranrhuang.github.io/nas3r/.

---

### Multi-Agent Dialectical Refinement for Enhanced Argument Classification

Authors: Jakub Bąba, Jarosław A. Chudziak
Published: 2026-03-29
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2603.27451v1

Argument Mining (AM) is a foundational technology for automated writing evaluation, yet traditional supervised approaches rely heavily on expensive, domain-specific fine-tuning. While Large Language Models (LLMs) offer a training-free alternative, they often struggle with structural ambiguity, failing to distinguish between similar components like Claims and Premises. Furthermore, single-agent self-correction mechanisms often suffer from sycophancy, where the model reinforces its own initial errors rather than critically evaluating them. We introduce MAD-ACC (Multi-Agent Debate for Argument Component Classification), a framework that leverages dialectical refinement to resolve classification uncertainty. MAD-ACC utilizes a Proponent-Opponent-Judge model where agents defend conflicting interpretations of ambiguous text, exposing logical nuances that single-agent models miss. Evaluation on the UKP Student Essays corpus demonstrates that MAD-ACC achieves a Macro F1 score of 85.7%, significantly outperforming single-agent reasoning baselines, without requiring domain-specific training. Additionally, unlike "black-box" classifiers, MAD-ACC's dialectical approach offers a transparent and explainable alternative by generating human-readable debate transcripts that explain the reasoning behind decisions.

---

### FlowRL: A Taxonomy and Modular Framework for Reinforcement Learning with Diffusion Policies

Authors: Chenxiao Gao, Edward Chen, Tianyi Chen, Bo Dai
Published: 2026-03-29
Categories: cs.LG
arXiv: https://arxiv.org/abs/2603.27450v2

Thanks to their remarkable flexibility, diffusion models and flow models have emerged as promising candidates for policy representation. However, efficient reinforcement learning (RL) upon these policies remains a challenge due to the lack of explicit log-probabilities for vanilla policy gradient estimators. While numerous attempts have been proposed to address this, the field lacks a unified perspective to reconcile these seemingly disparate methods, thus hampering ongoing development. In this paper, we bridge this gap by introducing a comprehensive taxonomy for RL algorithms with diffusion/flow policies. To support reproducibility and agile prototyping, we introduce a modular, JAX-based open-source codebase that leverages JIT-compilation for high-throughput training. Finally, we provide systematic and standardized benchmarks across Gym-Locomotion, DeepMind Control Suite, and IsaacLab, offering a rigorous side-by-side comparison of diffusion-based methods and guidance for practitioners to choose proper algorithms based on the application. Our work establishes a clear foundation for understanding and algorithm design, a high-efficiency toolkit for future research in the field, and an algorithmic guideline for practitioners in generative models and robotics. Our code is available at https://github.com/typoverflow/flow-rl.

---

### Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses

Authors: Xiao Li, Xiang Zheng, Yifeng Gao, Xinyu Xia, Yixu Wang, Xin Wang, Ye Sun, Yunhan Zhao, Ming Wen, Jiayu Li, Zixing Chen, Xun Gong et al.
Published: 2026-03-28
Categories: cs.CR, cs.AI, cs.CV, cs.RO
arXiv: https://arxiv.org/abs/2605.02900v2

Embodied Artificial Intelligence (Embodied AI) integrates perception, cognition, planning, and interaction into agents that operate in open-world, safety-critical environments. As these systems gain autonomy and enter domains such as transportation, healthcare, and industrial or assistive robotics, ensuring their safety becomes both technically challenging and socially indispensable. Unlike digital AI systems, embodied agents must act under uncertain sensing, incomplete knowledge, and dynamic human-robot interactions, where failures can directly lead to physical harm. This survey provides a comprehensive and structured review of safety research in embodied AI, examining attacks and defenses across the full embodied pipeline, from perception and cognition to planning, action and interaction, and agentic system. We introduce a multi-level taxonomy that unifies fragmented lines of work and connects embodied-specific safety findings with broader advances in vision, language, and multimodal foundation models. Our review synthesizes insights from over 500 papers spanning adversarial, backdoor, jailbreak, and hardware-level attacks; attack detection, safe training and robust inference; and risk-aware human-agent interaction. This analysis reveals several overlooked challenges, including the fragility of multimodal perception fusion, the instability of planning under jailbreak attacks, and the trustworthiness of human-agent interaction in open-ended scenarios. By organizing the field into a coherent framework and identifying critical research gaps, this survey provides a roadmap for building embodied agents that are not only capable and autonomous but also safe, robust, and reliable in real-world deployment.

---

### Towards High-Quality Machine Translation for Kokborok: A Low-Resource Tibeto-Burman Language of Northeast India

Authors: Badal Nyalang, Biman Debbarma
Published: 2026-03-28
Categories: cs.CL
arXiv: https://arxiv.org/abs/2604.19778v1

We present KokborokMT, a high-quality neural machine translation (NMT) system for Kokborok (ISO 639-3), a Tibeto-Burman language spoken primarily in Tripura, India with approximately 1.5 million speakers. Despite its status as an official language of Tripura, Kokborok has remained severely under-resourced in the NLP community, with prior machine translation attempts limited to systems trained on small Bible-derived corpora achieving BLEU scores below 7. We fine-tune the NLLB-200-distilled-600M model on a multi-source parallel corpus comprising 36,052 sentence pairs: 9,284 professionally translated sentences from the SMOL dataset, 1,769 Bible-domain sentences from WMT shared task data, and 24,999 synthetic back-translated pairs generated via Gemini Flash from Tatoeba English source sentences. We introduce as a new language token for Kokborok in the NLLB framework. Our best system achieves BLEU scores of 17.30 and 38.56 on held-out test sets, representing substantial improvements over prior published results. Human evaluation by three annotators yields mean adequacy of 3.74/5 and fluency of 3.70/5, with substantial agreement between trained evaluators.

---

### Self-Describing Structured Data with Dual-Layer Guidance: A Lightweight Alternative to RAG for Precision Retrieval in Large-Scale LLM Knowledge Navigation

Authors: Hung Ming Liu
Published: 2026-03-28
Categories: cs.CL, cs.AI, cs.IR
arXiv: https://arxiv.org/abs/2604.19777v1

Large Language Models (LLMs) exhibit a well-documented positional bias when processing long input contexts: information in the middle of a context window receives substantially less attention than content at the boundaries, a phenomenon termed the Lost-in-the-Middle effect (Liu et al., 2024). This limits knowledge-retrieval applications that embed large structured knowledge bases directly in the LLM context. Retrieval-Augmented Generation (RAG) addresses scalability by retrieving only relevant fragments, but introduces substantial infrastructure overhead and is ill-suited to libraries whose semantic boundaries are human-defined rather than statistically learned. We propose Self-Describing Structured Retrieval (SDSR), a lightweight framework in which structured data files embed human-authored navigational metadata at the file's primacy position, thereby exploiting rather than fighting the LLM's primacy bias. We further propose a Dual-Layer Guidance strategy combining in-file metadata with explicit routing rules in the system prompt. We validate SDSR through a four-round benchmark using a 190-skill library expanded from 36 to 119 categories via adversarial distractor injection. Four conditions are tested: (A) no guidance, (B) in-file summary only, (C) prompt hint only, (D) both combined. Version D achieves 100% primary routing accuracy (20/20) at 119 categories versus 65% for the no-guidance baseline. We identify a fundamental asymmetry: primary routing is solvable by explicit rules, while secondary cross-category routing requires architectural intent explicitly encoded in the data structure. We further extend SDSR to semi-structured corpora, showing how cross-reference encoding enables operation without vector databases in domains with recoverable document structure.

---