arXiv:2604.02380v1 Announce Type: new Abstract: Trajectory inference is a critical problem in single-cell transcriptomics, which aims to reconstruct the dynamic process underlying a population of cells from sequencing data. Of particular interest is the reconstruction of differentiation trees. One way of doing this is by estimating the path distance between nodes — labeled by cells […]
DiFlowDubber: Discrete Flow Matching for Automated Video Dubbing via Cross-Modal Alignment and Synchronization
arXiv:2603.14267v4 Announce Type: replace-cross Abstract: Video dubbing requires content accuracy, expressive prosody, high-quality acoustics, and precise lip synchronization, yet existing approaches struggle on all four fronts. To address these issues, we propose DiFlowDubber, the first video dubbing framework built upon a discrete flow matching backbone with a novel two-stage training strategy. In the first stage, […]
Better Rigs, Not Bigger Networks: A Body Model Ablation for Gaussian Avatars
arXiv:2604.01447v2 Announce Type: replace-cross Abstract: Recent 3D Gaussian splatting methods built atop SMPL achieve remarkable visual fidelity while continually increasing the complexity of the overall training architecture. We demonstrate that much of this complexity is unnecessary: by replacing SMPL with the Momentum Human Rig (MHR), estimated via SAM-3D-Body, a minimal pipeline with no learned deformations […]
$lambda$-GELU: Learning Gating Hardness for Controlled ReLU-ization in Deep Networks
arXiv:2603.21991v2 Announce Type: replace-cross Abstract: Gaussian Error Linear Unit (GELU) is a widely used smooth alternative to Rectifier Linear Unit (ReLU), yet many deployment, compression, and analysis toolchains are most naturally expressed for piecewise-linear (ReLU-type) networks. We study a hardness-parameterized formulation of GELU, f(x;lambda)=xPhi(lambda x), where Phi is the Gaussian CDF and lambda in [1, […]
Interpretable Deep Reinforcement Learning for Element-level Bridge Life-cycle Optimization
arXiv:2604.02528v1 Announce Type: new Abstract: The new Specifications for the National Bridge Inventory (SNBI), in effect from 2022, emphasize the use of element-level condition states (CS) for risk-based bridge management. Instead of a general component rating, element-level condition data use an array of relative CS quantities (i.e., CS proportions) to represent the condition of a […]
Xpertbench: Expert Level Tasks with Rubrics-Based Evaluation
arXiv:2604.02368v1 Announce Type: new Abstract: As Large Language Models (LLMs) exhibit plateauing performance on conventional benchmarks, a pivotal challenge persists: evaluating their proficiency in complex, open-ended tasks characterizing genuine expert-level cognition. Existing frameworks suffer from narrow domain coverage, reliance on generalist tasks, or self-evaluation biases. To bridge this gap, we present XpertBench, a high-fidelity benchmark […]
Learning from Synthetic Data via Provenance-Based Input Gradient Guidance
arXiv:2604.02946v1 Announce Type: cross Abstract: Learning methods using synthetic data have attracted attention as an effective approach for increasing the diversity of training data while reducing collection costs, thereby improving the robustness of model discrimination. However, many existing methods improve robustness only indirectly through the diversification of training samples and do not explicitly teach the […]
LogicPoison: Logical Attacks on Graph Retrieval-Augmented Generation
arXiv:2604.02954v1 Announce Type: cross Abstract: Graph-based Retrieval-Augmented Generation (GraphRAG) enhances the reasoning capabilities of Large Language Models (LLMs) by grounding their responses in structured knowledge graphs. Leveraging community detection and relation filtering techniques, GraphRAG systems demonstrate inherent resistance to traditional RAG attacks, such as text poisoning and prompt injection. However, in this paper, we find […]
Competency Questions as Executable Plans: a Controlled RAG Architecture for Cultural Heritage Storytelling
arXiv:2604.02545v1 Announce Type: new Abstract: The preservation of intangible cultural heritage is a critical challenge as collective memory fades over time. While Large Language Models (LLMs) offer a promising avenue for generating engaging narratives, their propensity for factual inaccuracies or “hallucinations” makes them unreliable for heritage applications where veracity is a central requirement. To address […]
Beyond Isolated Tasks: A Framework for Evaluating Coding Agents on Sequential Software Evolution
arXiv:2604.03035v1 Announce Type: cross Abstract: Existing datasets for coding agents evaluate performance on isolated, single pull request (PR) tasks in a stateless manner, failing to capture the reality of real-world software development where code changes accumulate, technical debt accrues, and test suites grow over time. To bridge this gap, we introduce an automated coding task […]
Verbalizing LLMs’ assumptions to explain and control sycophancy
arXiv:2604.03058v1 Announce Type: cross Abstract: LLMs can be socially sycophantic, affirming users when they ask questions like “am I in the wrong?” rather than providing genuine assessment. We hypothesize that this behavior arises from incorrect assumptions about the user, like underestimating how often users are seeking information over reassurance. We present Verbalized Assumptions, a framework […]
Supply-Chain Poisoning Attacks Against LLM Coding Agent Skill Ecosystems
arXiv:2604.03081v1 Announce Type: cross Abstract: LLM-based coding agents extend their capabilities via third-party agent skills distributed through open marketplaces without mandatory security review. Unlike traditional packages, these skills are executed as operational directives with system-level privileges, so a single malicious skill can compromise the host. Prior work has not examined whether supply-chain attacks can directly […]