Multi-agent LLM systems (MALS) introduce a privacy-leakage problem that conventional sensitivity-based defenses miss, since information disclosed to one authorized agent can propagate through routine coordination to an unauthorized one, without compromise or malicious behavior. This motivates topology-aware enforcement...
Sunday Oyinlola Ogundoyin, Muhammad Ikram· 0 citations
E-commerce user preferences evolve dynamically within sessions, exhibiting concurrent and multi-centric interest distributions. While existing multimodal sequential recommendation methods leverage global attention to compress historical interactions, they inadequately capture the concurrent nature of multi-interest beh...
Reinforcement learning improves tool-use agents, yet fine-grained credit assignment remains challenging even with step-level feedback. An observed error may be inherited from an earlier decision, while multiple responsible decisions may share the same downstream consequence or participate in later recovery. We introduc...
Xingjian Diao, Tianyu Yang, Wenjun Huang et al.· 0 citations
Layer-wise post-training quantization methods let each layer compensate for the quantization error inherited from earlier layers. We ask under what assumptions such compensation guarantees a network output error no larger than without it. For linear networks of any depth, with the required calibration Gram matrices inv...
Tian-Hao Guo· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
This paper presents AutoSec-RAN, a specification-grounded large language model (LLM) framework for automated security triage of Open Radio Access Network (O-RAN) testing. Unlike approaches relying on static rule sets or privileged access to raw packet captures, AutoSec-RAN fine-tunes Mistral-7B-Instruct through two Low...
Anoop Mishra, Joshua Moore, Aly Sabri Abdalla et al.· 0 citations
This paper investigates a new role of randomness in stochastic policies--as a medium for embedding and communicating information. Specifically, we consider an agent interacting with an environment according to a prescribed stochastic policy. By carefully modulating the random action realizations of the policy, informat...
Emergent misalignment (EM) occurs when fine-tuning a language model to a narrow task makes it misaligned on unrelated ones. Because organizations now routinely fine-tune models on their own data, it matters which kinds of training data cause EM. So far, studies have induced EM with data containing recognized safety fai...
Alex Mart\'i Guiu, Nicolas Zumarraga, Kevin O'Sullivan et al.· 0 citations
This paper proposes an novel framework that couples software-level scanning with hardware-level microprocessor activity monitoring to achieve efficient ransomware detection and mitigation and provides trace-level interpretability that explains the underlying decision process.
Salma Aboelmagd, Md Rakibul Ahasan, Zhi-Xin Pan et al.· 0 citations
Computing equilibria in high-dimensional continuous games requires learning and representing rich, multi-modal strategy distributions, something conventional neural policies struggle to achieve. Diffusion models offer a natural solution, but standard diffusion training requires direct samples from a fixed target distri...
Hai-Chuan Wang, Anagha Satish, Jia-Le Zheng et al.· 0 citations
Agent environments are essential for large language model (LLM) development. They use programmatic verifiers to turn complex outcomes into rewards. Verifiers can be attacked into awarding full credit to cheating agents without completing the intended task, causing inaccurate evaluation and misalignment in training. As...
Chong-Fang Zeng, Zi-Qian Zhong, Ke-Xun Zhang et al.· 2 citations
RINO (Renormalization Group DIstillation with NO Labels) is proposed, which exploits the fundamentally multi-scale renormalization group structure of high-energy jet formation as a physically grounded source of SSL views and defines teacher-student representations across energy scales using different levels of hierarch...
Zichun Hao, R. Kansal, A. Gandrakota et al.· 0 citations
We present Gen Through the Lens, a camera-controllable image-to-video generation framework that synthesizes videos from a given reference image while enabling realistic and physically consistent camera operations. Unlike previous models that treat camera motion as abstract conditioning or rely on a single coordinate sy...
Shuai Li, Jinxu Xiang, Xinyuan Li et al.· 0 citations
