arXiv:2509.06350v2 Announce Type: replace-cross Abstract: Jailbreak attacks on Large Language Models (LLMs) have demonstrated various successful methods whereby attackers manipulate models into generating harmful responses that they are designed to avoid. Among these, Greedy Coordinate Gradient (GCG) has emerged as a general and effective approach that optimizes the tokens in a suffix to generate jailbreakable […]
Mechanism of Task-oriented Information Removal in In-context Learning
arXiv:2509.21012v3 Announce Type: replace-cross Abstract: In-context Learning (ICL) is an emerging few-shot learning paradigm based on modern Language Models (LMs), yet its inner mechanism remains unclear. In this paper, we investigate the mechanism through a novel perspective of information removal. Specifically, we demonstrate that in the zero-shot scenario, LMs encode queries into non-selective representations in […]
Reasoning in the Dark: Interleaved Vision-Text Reasoning in Latent Space
arXiv:2510.12603v2 Announce Type: replace-cross Abstract: Multimodal reasoning aims to enhance the capabilities of MLLMs by incorporating intermediate reasoning steps before reaching the final answer. It has evolved from text-only reasoning to the integration of visual information, enabling the thought process to be conveyed through both images and text. Despite its effectiveness, current multimodal reasoning methods […]
Tracing Mathematical Proficiency Through Problem-Solving Processes
arXiv:2512.00311v2 Announce Type: replace-cross Abstract: Knowledge Tracing (KT) aims to model student’s knowledge state and predict future performance to enable personalized learning in Intelligent Tutoring Systems. However, traditional KT methods face fundamental limitations in explainability, as they rely solely on the response correctness, neglecting the rich information embedded in students’ problem-solving processes. To address this […]
Fail Fast, Win Big: Rethinking the Drafting Strategy in Speculative Decoding via Diffusion LLMs
arXiv:2512.20573v3 Announce Type: replace-cross Abstract: Diffusion Large Language Models (dLLMs) offer fast, parallel token generation, but their standalone use is plagued by an inherent efficiency-quality tradeoff. We show that, if carefully applied, the attributes of dLLMs can actually be a strength for drafters in speculative decoding with autoregressive (AR) verifiers. Our core insight is that […]
VLM-CAD: VLM-Optimized Collaborative Agent Design Workflow for Analog Circuit Sizing
arXiv:2601.07315v3 Announce Type: replace-cross Abstract: Analog mixed-signal circuit sizing involves complex trade-offs within high-dimensional design spaces. Existing automatic analog circuit sizing approaches rely solely on netlists, ignoring the circuit schematic, which hinders the cognitive link between the schematic and its performance. Furthermore, the black-box nature of machine learning methods and hallucination risks in large language […]
Spatiotemporal Semantic V2X Framework for Cooperative Collision Prediction
arXiv:2601.17216v2 Announce Type: replace-cross Abstract: Intelligent Transportation Systems (ITS) demand real-time collision prediction to ensure road safety and reduce accident severity. Conventional approaches rely on transmitting raw video or high-dimensional sensory data from roadside units (RSUs) to vehicles, which is impractical under vehicular communication bandwidth and latency constraints. In this work, we propose a semantic […]
Breaking Bad Molecules: Are MLLMs Ready for Structure-Level Molecular Detoxification?
arXiv:2506.10912v3 Announce Type: replace Abstract: Toxicity remains a leading cause of early-stage drug development failure. Despite advances in molecular design and property prediction, the task of molecular toxicity repair, generating structurally valid molecular alternatives with reduced toxicity, has not yet been systematically defined or benchmarked. To fill this gap, we introduce ToxiMol, the first benchmark […]
LLaTTE: Scaling Laws for Multi-Stage Sequence Modeling in Large-Scale Ads Recommendation
arXiv:2601.20083v1 Announce Type: cross Abstract: We present LLaTTE (LLM-Style Latent Transformers for Temporal Events), a scalable transformer architecture for production ads recommendation. Through systematic experiments, we demonstrate that sequence modeling in recommendation systems follows predictable power-law scaling similar to LLMs. Crucially, we find that semantic features bend the scaling curve: they are a prerequisite for […]
NCSAM Noise-Compensated Sharpness-Aware Minimization for Noisy Label Learning
arXiv:2601.19947v1 Announce Type: cross Abstract: Learning from Noisy Labels (LNL) presents a fundamental challenge in deep learning, as real-world datasets often contain erroneous or corrupted annotations, textite.g., data crawled from Web. Current research focuses on sophisticated label correction mechanisms. In contrast, this paper adopts a novel perspective by establishing a theoretical analysis the relationship between […]
DAUNet: A Lightweight UNet Variant with Deformable Convolutions and Parameter-Free Attention for Medical Image Segmentation
arXiv:2512.07051v2 Announce Type: replace-cross Abstract: Medical image segmentation plays a pivotal role in automated diagnostic and treatment planning systems. In this work, we present DAUNet, a novel lightweight UNet variant that integrates Deformable V2 Convolutions and Parameter-Free Attention (SimAM) to improve spatial adaptability and context-aware feature fusion without increasing model complexity. DAUNet’s bottleneck employs dynamic […]
CURVE: Learning Causality-Inspired Invariant Representations for Robust Scene Understanding via Uncertainty-Guided Regularization
arXiv:2601.20355v1 Announce Type: cross Abstract: Scene graphs provide structured abstractions for scene understanding, yet they often overfit to spurious correlations, severely hindering out-of-distribution generalization. To address this limitation, we propose CURVE, a causality-inspired framework that integrates variational uncertainty modeling with uncertainty-guided structural regularization to suppress high-variance, environment-specific relations. Specifically, we apply prototype-conditioned debiasing to disentangle […]