37 citations · 251 across the 96 of their papers we have counts for
101 papers
Multi-Turn Semantic Caching for Low-Cost LLM Serving
Baran Atalar, Selly Beyene, Xutong Liu +1
Semantic caching lowers the cost of serving large language models (LLMs) by reusing stored responses for similar requests. In multi-turn conversations, whether a cached response is…
Resilience Beyond Stationary Client Unavailability: Unlocking Efficient and Unbiased Federated Learning
Ming Xiang, Stratis Ioannidis, Edmund Yeh +2
Due to resource constraints or external and internal uncertainties, clients in real-world federated learning systems are often intermittently available edge devices. In highly dyna…
GCA: Global Centroid Alignment in Federated Learning
Jong-Ik Park, Harry Jiang, Logan Blakely +3
Autoencoder (AE)-based federated learning (FL) is attractive for anomaly detection when clients have limited local data. However, conventional FL exchanges AE parameters or gradien…
FedLNS: Leverage LayerNorm Signature Modeling to Mitigate Adversarial Manipulation in Federated LLMs
Kai Li, Jong-Ik Park, Carlee Joe-Wong +2
Federated training enables language models to learn from distributed private text, but the server cannot directly verify the local supervision or optimization process that produces…
MultiPathFormer: Towards a Foundation Model for Multipath Wireless Propagation
Blessed Guda, Kayley Sze, Carlee Joe-Wong
Recent advances in machine learning have enabled training of wireless foundation models, which aim to support tasks such as channel estimation, beam prediction, and localization ba…
Auditing Emergent LLM-Agent Collaboration through Cooperation-Obligation Coupling
Zuyuan Zhang, Hanqing Yang, Carlee Joe-Wong +1
LLM-agent systems can solve complex tasks through dynamic self-organization and emergent cooperation. Auditing this process is essential because plausible intermediate or final out…
Representation Matters in Randomized Smoothing for Audio Classification
Jong-Ik Park, Shreyas Chaudhari, José M. F. Moura +1
Randomized smoothing (RS) certifies robustness in the vector space where Gaussian noise is added. In audio classification, this space is often not uniquely defined as standard pipe…
FedSteer: Taming Extreme Gradient Staleness in Federated Learning with Corrective Projections and Caching
Haoran Zhang, Cainã Figueiredo Pereira, Marie Siew +3
Federated learning (FL) is often subject to aggregation variance if clients do not consistently participate in training rounds. While reusing stale model updates from inactive clie…
RRISE: Robust Radius Inference via a Surrogate Estimator
Jong-Ik Park, Shreyas Chaudhari, Carlee Joe-Wong +1
Randomized smoothing (RS) uses a smoothed classifier to provide architecture-agnostic certificates of classification robustness, but its dependence on per-input Monte Carl…
Matrix-Space Reinforcement Learning for Reusing Local Transition Geometry
Zuyuan Zhang, Carlee Joe-Wong, Tian Lan
Compositional generalization in sequential decision-making requires identifying which parts of prior rollouts remain useful for new tasks. Existing methods reuse skills or predicti…
Emergent and Subliminal Misalignment Through the Lens of Data-Mediated Transfer
Baris Askin, Muhammed Ustaomeroglu, Anupam Nayak +3
Fine-tuning LLMs on narrow harmful datasets can induce Emergent Misalignment (EM), where models exhibit misaligned behavior far beyond the fine-tuning distribution. We argue that e…
Cost-Ordered Feasibility for Multi-Armed Bandits with Cost Subsidy
Ishank Juneja, Carlee Joe-Wong, Osman Yağan
The classic multi-armed bandit (MAB) problem tackles the challenge of accruing maximum reward while making decisions under uncertainty. However, in applications, often the goal is…
Trustworthy Agent Network: Trust in Agent Networks Must Be Baked In, Not Bolted On
Yixiang Yao, Yuhang Yao, Xinyi Fan +5
The rapid advancement of Large Language Models has given rise to autonomous LLM-based agents capable of complex reasoning and execution. As these agents transition from isolated op…
Continuous Semantic Caching for Low-Cost LLM Serving
Baran Atalar, Xutong Liu, Jinhang Zuo +3
As Large Language Models (LLMs) become increasingly popular, caching responses so that they can be reused by users with semantically similar queries has become a vital strategy for…
PubSwap: Public-Data Off-Policy Coordination for Federated RLVR
Anupam Nayak, Baris Askin, Muhammed Ustaomeroglu +2
Reasoning post-training with reinforcement learning from verifiable rewards (RLVR) is typically studied in centralized settings, yet many realistic applications involve decentraliz…
COOP: Defining, Observing, and Repairing Cooperation in LLM Multi-Agent Systems
Hanqing Yang, Narjes Nourzad, Shiyu Chen +3
Many complex tasks require extended effort, diverse capabilities, or coordinated actions beyond what a single agent can provide. However, simply adding more agents does not guarant…
DIG to Heal: Scaling General-purpose Agent Collaboration via Explainable Dynamic Decision Paths
Hanqing Yang, Hyungwoo Lee, Yuhang Yao +4
The increasingly popular agentic AI paradigm promises to harness the power of multiple, general-purpose large language model (LLM) agents to collaboratively complete complex tasks.…
Memory-Based Advantage Shaping for LLM-Guided Reinforcement Learning
Narjes Nourzad, Carlee Joe-Wong
In environments with sparse or delayed rewards, reinforcement learning (RL) incurs high sample complexity due to the large number of interactions needed for learning. This limitati…
MIRA: Memory-Integrated Reinforcement Learning Agent with Limited LLM Guidance
Narjes Nourzad, Carlee Joe-Wong
Reinforcement learning (RL) agents often suffer from high sample complexity in sparse or delayed reward settings due to limited prior structure. Large language models (LLMs) can pr…
The Five Ws of Multi-Agent Communication: Who Talks to Whom, When, What, and Why -- A Survey from MARL to Emergent Language and LLMs
Jingdi Chen, Hanqing Yang, Zongjun Liu +1
Multi-agent sequential decision-making powers many real-world systems, from autonomous vehicles and robotics to collaborative AI assistants. In dynamic, partially observable enviro…
Federate the Router: Learning Language Model Routers with Sparse and Decentralized Evaluations
Baris Askin, Shivam Patel, Anupam Nayak +4
Large language models (LLMs) are increasingly accessed as remotely hosted services by edge and enterprise clients that cannot run frontier models locally. Since models vary widely…
GLUE: Gradient-free Learning to Unify Experts
Jong-Ik Park, Shreyas Chaudhari, Srinivasa Pranav +2
In many deployed systems (multilingual ASR, cross-hospital imaging, region-specific perception), multiple pretrained specialist models coexist. Yet, new target domains often requir…
M3Net: A Multi-Metric Mixture of Experts Network Digital Twin with Graph Neural Networks
Blessed Guda, Carlee Joe-Wong
The rise of 5G/6G network technologies promises to enable applications like autonomous vehicles and virtual reality, resulting in a significant increase in connected devices and ne…
Quantifying and Mitigating Selection Bias in LLMs: A Transferable LoRA Fine-Tuning and Efficient Majority Voting Approach
Blessed Guda, Lawrence Francis, Gabrial Zencha Ashungafac +2
Multiple Choice Question (MCQ) answering is a widely used method for evaluating the performance of Large Language Models (LLMs). However, LLMs often exhibit selection bias in MCQ t…