相关论文: Recall Isn't Enough: Bounding Commitments in Perso…

The growing number of individual generating units, hybrid resources, and security constraints has significantly increased the computational burden of network-constrained unit commitment (UC), where most solution time is spent exploring…

We introduce self-invoking code generation, a new task designed to evaluate the progressive reasoning and problem-solving capabilities of LLMs. In this task, models are presented with a base problem and a related, more complex problem. They…

This paper presents a system combining symbolic execution (KLEE) with a 4-agent multi-LLM architecture for detecting memory vulnerabilities in Rust unsafe code. A central challenge we address is the incomplete-code problem: CVE database…

Large language models (LLMs) with extended context windows enable powerful downstream applications but impose significant memory overhead, as caching all key-value (KV) states scales linearly with sequence length and batch size. Existing…

Large audio language models (LALMs) process both speech and environmental acoustic cues, yet struggle to retain non-speech information across multi-turn interactions. The performance gap between semantic (speech) and acoustic (non-speech)…

Large Language Models (LLMs) can produce surprisingly sophisticated estimates of their own uncertainty. However, it remains unclear to what extent this expressed confidence is tied to the reasoning, knowledge, or decision making of the…

Concept Bottleneck Models (CBMs) map the black-box visual representations extracted by deep neural networks onto a set of interpretable concepts and use the concepts to make predictions, enhancing the transparency of the decision-making…

Debugging CUDA programs has long been challenging because failures often arise from subtle interactions among hardware behavior, compiler decisions, memory hierarchy, and asynchronous execution. More importantly, with the rapid expansion of…

Mechanistic interpretability aims to reverse-engineer the internal computations of Large Language Models (LLMs), yet separating sparse semantic signals from high-dimensional polysemantic noise remains a significant challenge. This paper…

Code-driven auditing fails when correctness depends on what the specification requires rather than how the code is written. Production blockchain networks expose this directly: byzantine consensus runs many independent clients of a shared…

Hallucinations, generating responses inconsistent with the visual input, remain a critical limitation of large vision-language models (LVLMs), especially in open-ended tasks such as image captioning and visual reasoning. In this work, we…

Multi-turn tool-calling LLMs (models capable of invoking external APIs or tools across several user turns) have emerged as a key feature in modern AI assistants, enabling extended dialogues from benign tasks to critical business, medical,…

Large language models (LLMs) possess impressive linguistic capabilities but often fail to faithfully retain factual knowledge, leading to hallucinations and unreliable outputs. Understanding LLMs' knowledge deficiencies by exhaustively…

Vision language action (VLA) models enable generalist robotic agents but often exhibit language ignorance, relying on visual shortcuts and remaining insensitive to instruction changes. We present Prospective Grounding and Alignment VLA…

Traditional neural network models for intent inference rely heavily on observable states and struggle to generalize across diverse tasks and dynamic environments. Recent advances in Vision Language Models (VLMs) and Vision Language Action…

Biomedical question answering often requires decisions from retrieved literature whose relevance, quality, and support for candidate answers are uneven. Most retrieval-augmented large language model (LLM) methods feed this literature to the…

The potential of large language models (LLMs) in specialized domains such as legal risk analysis remains underexplored. In response to growing interest in locally deploying open-source LLMs for legal tasks while preserving data…

Vision-Language-Action (VLA) models fail systematically on long-horizon manipulation tasks despite strong short-horizon performance. We show that this failure is not resolved by extending context length alone in the current reactive…

As reasoning LLMs increasingly trade tokens for accuracy through deliberation, search, and self-correction, a single accuracy score can no longer tell whether those tokens buy useful reasoning, recovery from hard instances, or unnecessary…

In Large Language Model (LLM) inference, Key-Value (KV) caches (KV-caches) are essential for reducing time complexity. However, they result in a linear increase in GPU memory as the context length grows. While recent work explores KV-cache…