arXiv:2601.18973v2 Announce Type: replace-cross Abstract: Quantum hardware suffers from intrinsic device heterogeneity and environmental drift, forcing practitioners to choose between suboptimal non-adaptive controllers or costly per-device recalibration. We derive a scaling law lower bound for meta-learning showing that the adaptation gain (expected fidelity improvement from task-specific gradient steps) saturates exponentially with gradient steps and scales […]
Language Models Might Not Understand You: Evaluating Theory of Mind via Story Prompting
arXiv:2506.19089v4 Announce Type: replace-cross Abstract: We introduce $textttStorySim$, a programmable framework for synthetically generating stories to evaluate the theory of mind (ToM) and world modeling (WM) capabilities of large language models (LLMs). Unlike prior benchmarks that may suffer from contamination in pretraining data, $textttStorySim$ produces novel, compositional story prompts anchored by a highly controllable $textttStoryboard$, […]
Dynamic Target Attack
arXiv:2510.02422v3 Announce Type: replace-cross Abstract: Existing gradient-based jailbreak attacks typically optimize an adversarial suffix to induce a fixed affirmative response, e.g., “Sure, here is…”. However, this fixed target usually resides in an extremely low-density region of a safety-aligned LLM’s output distribution. Due to the substantial discrepancy between the fixed target and the output distribution, existing […]
SafeSearch: Automated Red-Teaming of LLM-Based Search Agents
arXiv:2509.23694v4 Announce Type: replace Abstract: Search agents connect LLMs to the Internet, enabling them to access broader and more up-to-date information. However, this also introduces a new threat surface: unreliable search results can mislead agents into producing unsafe outputs. Real-world incidents and our two in-the-wild observations show that such failures can occur in practice. To […]
Low-redundancy Distillation for Continual Learning
arXiv:2309.16117v2 Announce Type: replace-cross Abstract: Continual learning (CL) aims to learn new tasks without erasing previous knowledge. However, current CL methods primarily emphasize improving accuracy while often neglecting training efficiency, which consequently restricts their practical application. Drawing inspiration from the brain’s contextual gating mechanism, which selectively filters neural information and continuously updates past memories, we […]
Dynamics Reveals Structure: Challenging the Linear Propagation Assumption
arXiv:2601.21601v1 Announce Type: cross Abstract: Neural networks adapt through first-order parameter updates, yet it remains unclear whether such updates preserve logical coherence. We investigate the geometric limits of the Linear Propagation Assumption (LPA), the premise that local updates coherently propagate to logical consequences. To formalize this, we adopt relation algebra and study three core operations […]
Thinking Out of Order: When Output Order Stops Reflecting Reasoning Order in Diffusion Language Models
arXiv:2601.22035v1 Announce Type: cross Abstract: Autoregressive (AR) language models enforce a fixed left-to-right generation order, creating a fundamental limitation when the required output structure conflicts with natural reasoning (e.g., producing answers before explanations due to presentation or schema constraints). In such cases, AR models must commit to answers before generating intermediate reasoning, and this rigid […]
Thinking Broad, Acting Fast: Latent Reasoning Distillation from Multi-Perspective Chain-of-Thought for E-Commerce Relevance
arXiv:2601.21611v1 Announce Type: cross Abstract: Effective relevance modeling is crucial for e-commerce search, as it aligns search results with user intent and enhances customer experience. Recent work has leveraged large language models (LLMs) to address the limitations of traditional relevance models, especially for long-tail and ambiguous queries. By incorporating Chain-of-Thought (CoT) reasoning, these approaches improve […]
d3LLM: Ultra-Fast Diffusion LLM using Pseudo-Trajectory Distillation
arXiv:2601.07568v2 Announce Type: replace-cross Abstract: Diffusion large language models (dLLMs) offer capabilities beyond those of autoregressive (AR) LLMs, such as parallel decoding and random-order generation. However, realizing these benefits in practice is non-trivial, as dLLMs inherently face an accuracy-parallelism trade-off. Despite increasing interest, existing methods typically focus on only one-side of the coin, targeting either […]
The Algorithmic Gaze: An Audit and Ethnography of the LAION-Aesthetics Predictor Model
arXiv:2601.09896v2 Announce Type: replace-cross Abstract: Visual generative AI models are trained using a one-size-fits-all measure of aesthetic appeal. However, what is deemed “aesthetic” is inextricably linked to personal taste and cultural values, raising the question of whose taste is represented in visual generative AI models. In this work, we study an aesthetic evaluation model–LAION Aesthetic […]
Representation-Regularized Convolutional Audio Transformer for Audio Understanding
arXiv:2601.21612v1 Announce Type: cross Abstract: Bootstrap-based Self-Supervised Learning (SSL) has achieved remarkable progress in audio understanding. However, existing methods typically operate at a single level of granularity, limiting their ability to model the diverse temporal and spectral structures inherent in complex audio signals. Furthermore, bootstrapping representations from scratch is computationally expensive, often requiring extensive training […]
Deep GraphRAG: A Balanced Approach to Hierarchical Retrieval and Adaptive Integration
arXiv:2601.11144v3 Announce Type: replace-cross Abstract: Graph-based Retrieval-Augmented Generation (GraphRAG) frameworks face a trade-off between the comprehensiveness of global search and the efficiency of local search. Existing methods are often challenged by navigating large-scale hierarchical graphs, optimizing retrieval paths, and balancing exploration-exploitation dynamics, frequently lacking robust multi-stage re-ranking. To overcome these deficits, we propose Deep GraphRAG, […]