Related papers: DeepContext: Stateful Real-Time Detection of Multi…
Large Language Models (LLMs) can enhance reasoning capabilities through test-time scaling by generating multiple traces. However, the combination of lengthy reasoning traces with multiple sampling introduces substantial computation and high…
Long-term memory systems enable conversational agents based on large language models (LLMs) to retain, retrieve, and apply user-specific information across multi-session interactions. However, existing evaluations mainly assess…
Although modern vulnerability detection tools enable developers to efficiently identify numerous security flaws, indiscriminate remediation efforts often lead to superfluous development expenses. This is particularly true given that a…
Transformer LMs show emergent reasoning that resists mechanistic understanding. We offer a statistical physics framework for continuous-time chain-of-thought reasoning dynamics. We model sentence-level hidden state trajectories as a…
Given the paramount importance of safety in the aviation industry, even minor operational anomalies can have significant consequences. Comprehensive documentation of incidents and accidents serves to identify root causes and propose safety…
A new generation of language models reasons entirely in continuous hidden states, producing no tokens and leaving no audit trail. We show that this silence creates a fundamentally new attack surface. ThoughtSteer perturbs a single embedding…
To break the context limits of large language models (LLMs) that bottleneck reasoning accuracy and efficiency, we propose the Thread Inference Model (TIM), a family of LLMs trained for recursive and decompositional problem solving, and…
Large language model (LLM) agents are vulnerable to prompt-injection attacks that propagate through multi-step workflows, tool interactions, and persistent context, making input-output filtering alone insufficient for reliable protection.…
Large (vision-)language models exhibit remarkable capability but remain highly susceptible to jailbreaking. Existing safety training approaches aim to have the model learn a refusal boundary between safe and unsafe, based on the user's…
We propose RecaLLM, a set of reasoning language models post-trained to make effective use of long-context information. In-context retrieval, which identifies relevant evidence from context, and reasoning are deeply intertwined: retrieval…
Large Language Models (LLMs) demonstrate substantial potential across a diverse array of domains via request serving. However, as trends continue to push for expanding context sizes, the autoregressive nature of LLMs results in highly…
Transformer-based large language models face severe scalability challenges in long-context generation due to the computational and memory costs of full-context attention. Under practical computation and memory constraints, many…
Evaluating the value alignment of large language models (LLMs) has traditionally relied on single-sentence adversarial prompts, which directly probe models with ethically sensitive or controversial questions. However, with the rapid…
Network Intrusion Detection Systems (NIDS) have progressively shifted from signature-based techniques toward machine learning and, more recently, deep learning methods. Meanwhile, the widespread adoption of encryption has reduced payload…
Intent-Based Networking (IBN) simplifies network management, but its reliability is challenged by "intent drift", where the network's state gradually deviates from its intended goal, often leading to silent failures. Conventional approaches…
This study investigates the adoption of open-access, locally deployable causal large language models (LLMs) for travel mode choice prediction and introduces LiTransMC, the first fine-tuned causal LLM developed for this task. We…
In high-conflict mixed-traffic scenarios involving human-driven and autonomous vehicles, most existing autonomous driving systems default to overly conservative behaviors, lack proactive interaction, and consequently suffer from limited…
In recent years, large language models (LLMs) have had great success in tasks such as casual conversation, contributing to significant advancements in domains like virtual assistance. However, they often generate responses that are not…
Large Language Models (LLMs) often produce fluent yet factually incorrect statements-a phenomenon known as hallucination-posing serious risks in high-stakes domains. We present Layer-wise Semantic Dynamics (LSD), a geometric framework for…
Large Language Models (LLMs) are increasingly vulnerable to a sophisticated form of adversarial prompting known as camouflaged jailbreaking. This method embeds malicious intent within seemingly benign language to evade existing safety…