arXiv:2603.10504v1 Announce Type: cross Abstract: Generative AI systems increasingly expose powerful reasoning and image refinement capabilities through user-facing chatbot interfaces. In this work, we show that the na”ive exposure of such capabilities fundamentally undermines modern deepfake detectors. Rather than proposing a new image manipulation technique, we study a realistic and already-deployed usage scenario in which […]
Detecting and Eliminating Neural Network Backdoors Through Active Paths with Application to Intrusion Detection
arXiv:2603.10641v1 Announce Type: cross Abstract: Machine learning backdoors have the property that the machine learning model should work as expected on normal inputs, but when the input contains a specific $textittrigger$, it behaves as the attacker desires. Detecting such triggers has been proven to be extremely difficult. In this paper, we present a novel and […]
Revisiting Sharpness-Aware Minimization: A More Faithful and Effective Implementation
arXiv:2603.10048v1 Announce Type: cross Abstract: Sharpness-Aware Minimization (SAM) enhances generalization by minimizing the maximum training loss within a predefined neighborhood around the parameters. However, its practical implementation approximates this as gradient ascent(s) followed by applying the gradient at the ascent point to update the current parameters. This practice can be justified as approximately optimizing the […]
BD-Merging: Bias-Aware Dynamic Model Merging with Evidence-Guided Contrastive Learning
arXiv:2603.03920v2 Announce Type: replace-cross Abstract: Model Merging (MM) has emerged as a scalable paradigm for multi-task learning (MTL), enabling multiple task-specific models to be integrated without revisiting the original training data. Despite recent progress, the reliability of MM under test-time distribution shift remains insufficiently understood. Most existing MM methods typically assume that test data are […]
SBOMs into Agentic AIBOMs: Schema Extensions, Agentic Orchestration, and Reproducibility Evaluation
arXiv:2603.10057v1 Announce Type: cross Abstract: Software supply-chain security requires provenance mechanisms that support reproducibility and vulnerability assessment under dynamic execution conditions. Conventional Software Bills of Materials (SBOMs) provide static dependency inventories but cannot capture runtime behaviour, environment drift, or exploitability context. This paper introduces agentic Artificial Intelligence Bills of Materials (AIBOMs), extending SBOMs into active […]
Reinforcement Learning with Conditional Expectation Reward
arXiv:2603.10624v1 Announce Type: cross Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has proven effective in enhancing the reasoning capabilities of large language models, particularly in domains such as mathematics where reliable rule-based verifiers can be constructed. However, the reliance on handcrafted, domain-specific verification rules substantially limits the applicability of RLVR to general reasoning domains with […]
HTMuon: Improving Muon via Heavy-Tailed Spectral Correction
arXiv:2603.10067v1 Announce Type: cross Abstract: Muon has recently shown promising results in LLM training. In this work, we study how to further improve Muon. We argue that Muon’s orthogonalized update rule suppresses the emergence of heavy-tailed weight spectra and over-emphasizes the training along noise-dominated directions. Motivated by the Heavy-Tailed Self-Regularization (HT-SR) theory, we propose HTMuon. […]
BrandFusion: A Multi-Agent Framework for Seamless Brand Integration in Text-to-Video Generation
arXiv:2603.02816v2 Announce Type: replace-cross Abstract: The rapid advancement of text-to-video (T2V) models has revolutionized content creation, yet their commercial potential remains largely untapped. We introduce, for the first time, the task of seamless brand integration in T2V: automatically embedding advertiser brands into prompt-generated videos while preserving semantic fidelity to user intent. This task confronts three […]
Marginals Before Conditionals
arXiv:2603.10074v1 Announce Type: cross Abstract: We construct a minimal task that isolates conditional learning in neural networks: a surjective map with K-fold ambiguity, resolved by a selector token z, so H(A | B) = log K while H(A | B, z) = 0. The model learns the marginal P(A | B) first, producing a plateau […]
Recover to Predict: Progressive Retrospective Learning for Variable-Length Trajectory Prediction
arXiv:2603.10597v1 Announce Type: cross Abstract: Trajectory prediction is critical for autonomous driving, enabling safe and efficient planning in dense, dynamic traffic. Most existing methods optimize prediction accuracy under fixed-length observations. However, real-world driving often yields variable-length, incomplete observations, posing a challenge to these methods. A common strategy is to directly map features from incomplete observations […]
KernelSkill: A Multi-Agent Framework for GPU Kernel Optimization
arXiv:2603.10085v1 Announce Type: cross Abstract: Improving GPU kernel efficiency is crucial for advancing AI systems. Recent work has explored leveraging large language models (LLMs) for GPU kernel generation and optimization. However, existing LLM-based kernel optimization pipelines typically rely on opaque, implicitly learned heuristics within the LLMs to determine optimization strategies. This leads to inefficient trial-and-error […]
AMLRIS: Alignment-aware Masked Learning for Referring Image Segmentation
arXiv:2602.22740v2 Announce Type: replace-cross Abstract: Referring Image Segmentation (RIS) aims to segment the object in an image uniquely referred to by a natural language expression. However, RIS training often contains hard-to-align and instance-specific visual signals; optimizing on such pixels injects misleading gradients and drives the model in the wrong direction. By explicitly estimating pixel-level vision-language […]