8822 papers
This paper investigates the adversarial robustness of partitioned quantum classifiers by demonstrating that perturbations targeting circuit partitioning techniques, such as wire cutting or teleportation, are equivalent to implementing adversarial gates within intermediate layers, a relationship analyzed through both theoretical and experimental perspectives.
This paper provides a comprehensive survey of music generation research by categorizing systems across single-modal, cross-modal, and multi-modal perspectives, while examining key aspects such as representation, data alignment, datasets, evaluation methods, current challenges, and future directions.
FindAnything is an efficient, open-world mapping framework that integrates vision-language features into object-centric volumetric submaps to enable real-time, open-vocabulary semantic understanding of large-scale environments on resource-constrained robots.
This paper investigates the inherent forecasting capabilities of large language models (LLMs) by controlling for tokenizer bias through large-scale pre-training, revealing that while LLM backbones show some promise, they still struggle to consistently outperform models specifically trained on large-scale time series data.
This position paper argues that anthropomorphizing intermediate token generation as "reasoning traces" or "thoughts" is a dangerous misconception that obscures the true nature of language models, hinders their effective use, and leads to flawed research, urging the community to abandon such metaphors.
This paper adopts a survivor-centered approach to expose how a "malicious technical ecosystem" of accessible tools enables the creation of AI-generated non-consensual intimate images, while demonstrating that current governance frameworks, such as the NIST AI 100-4 report, fail to effectively regulate this landscape due to flawed underlying assumptions.
This survey provides a comprehensive overview of Federated Learning, detailing its architecture and lifecycle while addressing key challenges like data heterogeneity and privacy, exploring emerging trends and applications, and outlining future research directions for scalable and trustworthy collaborative intelligence.
This paper introduces HCT-QA, a comprehensive benchmark comprising thousands of real-world and synthetic human-centric tables with natural language question-answer pairs, designed to evaluate and improve the performance of Large Language Models and Vision Language Models in querying complex tabular data.
This paper introduces FourierSpecNet, a hybrid deep learning framework that integrates the Fourier spectral method to efficiently approximate the Boltzmann collision operator, achieving resolution-invariant learning, zero-shot super-resolution, and significant computational savings while maintaining accuracy across elastic and inelastic collision regimes.
The paper introduces Reasoning Reward Models (ReasRMs), specifically the RM-R1 family, which reformulate reward modeling as a reasoning task using a chain-of-rubrics mechanism and a two-stage training pipeline to achieve superior interpretability and performance compared to existing large-scale models.
This paper presents a comprehensive survey of 178 benchmarks for Code Large Language Models and Agents through a tiered Software Development Life Cycle (SDLC) framework, revealing a significant imbalance that heavily favors the implementation phase while neglecting requirements and design, alongside critical gaps in anti-contamination strategies that necessitate future research to bridge the gap between theoretical capabilities and practical effectiveness.
This paper introduces EVA, a novel event-by-event asynchronous-to-synchronous (A2S) framework inspired by language modeling that generates highly expressive features, outperforming prior methods in recognition tasks and achieving state-of-the-art results in detection for event-based vision.
This paper proposes K-CAST, a novel fine-grained conditional activation steering method that dynamically mitigates content biases in large language models, significantly improving formal reasoning accuracy by up to 15% while maintaining robustness across prompts and languages.
This paper introduces AdAEM, a novel self-extensible evaluation framework that automatically generates adaptive test questions by probing the internal value boundaries of diverse LLMs to overcome the limitations of static benchmarks and provide more informative, distinguishable insights into models' value differences and alignment dynamics.
The paper introduces ESGenius, the first comprehensive benchmark comprising a curated corpus of authoritative ESG documents and a rigorously validated question-answer dataset, which reveals that while large language models exhibit moderate zero-shot performance in sustainability domains, their accuracy significantly improves when grounded in retrieval-augmented generation (RAG) using the provided source materials.
The paper introduces KramaBench, a comprehensive benchmark featuring 104 real-world data-to-insight challenges across diverse domains, which reveals that current AI systems struggle to orchestrate end-to-end data pipelines over data lakes, achieving a maximum of only 55% accuracy despite strong performance in isolated tasks.
This paper introduces VisioMath, a benchmark of 1,800 K-12 mathematics problems featuring visually similar diagrams, to reveal that current Large Multimodal Models struggle with fine-grained comparative reasoning due to image-text misalignment and to demonstrate that alignment-oriented strategies can significantly improve performance.
This paper critiques existing evaluations of LLM moral competence for over-relying on simplified scenarios and proposes a novel five-dimensional framework that reveals models often outperform humans in structured tasks but significantly underperform when required to discern moral relevance from noisy information, suggesting current assessments substantially overestimate their true moral reasoning capabilities.
This paper introduces ContextBench, a benchmark for evaluating methods that generate fluent inputs to trigger specific latent features in language models, and demonstrates that enhanced Evolutionary Prompt Optimization variants achieve state-of-the-art performance in balancing elicitation strength with linguistic fluency.
The paper introduces Sysformer, a novel approach that safeguards frozen large language models by learning to adapt system prompts in the embedding space to significantly improve safety robustness against harmful inputs and jailbreaking attacks without requiring costly model fine-tuning.