papers

Publications (40)

cs.LG2026

TwinRouterBench: Fast Static and Live Dynamic Evaluation for Realistic Agentic LLM Routing

Pei Yang, Wanyi Chen, Tongyun Yang +14

LLM routing matters most in long-horizon applications such as coding agents, deep research systems, and computer-use agents, where a single user request triggers many model calls.…

cs.LG2026

MARS: Unleashing the Power of Speculative Decoding via Margin-Aware Verification

Jingwei Song, Xinyu Wang, Hanbin Wang +6

Speculative Decoding (SD) accelerates autoregressive large language model (LLM) inference by decoupling generation and verification. While recent methods improve draft quality by t…

cs.CL2026

Nemotron 3 Ultra: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning

NVIDIA, :, Aaron Blakeman +571

We introduce Nemotron 3 Ultra, a 550 billion total and 55 billion active parameter Mixture-of-Experts Hybrid Mamba-Attention language model. We pre-trained Nemotron 3 Ultra on 20 t…

astro-ph.IM2025

Signal processing and data acquisition system for the BTO detectors onboard COSI

Shunsaku Nagasawa, Tadayuki Takahashi, Kazuhiro Nakazawa +15

The energy range from a few hundred keV to a few MeV includes important probes such as nuclear gamma-rays and the 511 keV annihilation line. However, compared to X-rays and GeV/TeV…

cs.CL2024

Context-Aware SQL Error Correction Using Few-Shot Learning -- A Novel Approach Based on NLQ, Error, and SQL Similarity

Divyansh Jain, Eric Yang

In recent years, the demand for automated SQL generation has increased significantly, driven by the need for efficient data querying in various applications. However, generating ac…

cs.CL2026

DynaWeb: Model-Based Reinforcement Learning of Web Agents

Hang Ding, Peidong Liu, Junqiao Wang +7

The development of autonomous web agents, powered by Large Language Models (LLMs) and reinforcement learning (RL), represents a significant step towards general-purpose AI assistan…

cs.CL2025

An AI-Based Behavioral Health Safety Filter and Dataset for Identifying Mental Health Crises in Text-Based Conversations

Benjamin W. Nelson, Celeste Wong, Matthew T. Silvestrini +6

Large language models often mishandle psychiatric emergencies, offering harmful or inappropriate advice and enabling destructive behaviors. This study evaluated the Verily behavior…

cs.LG2024

From Barriers to Tactics: A Behavioral Science-Informed Agentic Workflow for Personalized Nutrition Coaching

Eric Yang, Tomas Garcia, Hannah Williams +7

Effective management of cardiometabolic conditions requires sustained positive nutrition habits, often hindered by complex and individualized barriers. Direct human management is s…

cs.CL2026

EVM-QuestBench: An Execution-Grounded Benchmark for Natural-Language Transaction Code Generation

Pei Yang, Wanyi Chen, Ke Wang +3

Large language models are increasingly applied to various development scenarios. However, in on-chain transaction scenarios, even a minor error can cause irreversible loss for user…

cs.MA2026

Symphony-Coord: Adaptive Routing for Multi-Agent LLM Systems

Zhaoyang Guan, Huixi Cao, Ming Zhong +6

Multi-agent large language model systems can tackle complex multi-step tasks by decomposing work and coordinating specialized behaviors. However, current coordination mechanisms ty…

cs.AI2026

Multi-Agent Collaborative Reward Design for Enhancing Reasoning in Reinforcement Learning

Pei Yang, Ke Zhang, Ji Wang +5

We present CRM (Multi-Agent Collaborative Reward Model), a framework that replaces a single black-box reward model with a coordinated team of specialist evaluators to improve robus…

eess.IV2020

GloFlow: Global Image Alignment for Creation of Whole Slide Images for Pathology from Video

Viswesh Krishna, Anirudh Joshi, Philip L. Bulterys +3

The application of deep learning to pathology assumes the existence of digital whole slide images of pathology slides. However, slide digitization is bottlenecked by the high cost…

cs.AI2026

Combee: Scaling Prompt Learning for Self-Improving Language Model Agents

Hanchen Li, Runyuan He, Qizheng Zhang +11

Recent advances in prompt learning allow large language model agents to acquire task-relevant knowledge from inference-time context without parameter changes. For example, existing…

cs.RO2026

Alpamayo-R1: Bridging Reasoning and Action Prediction for Generalizable Autonomous Driving in the Long Tail

NVIDIA, :, Yan Wang +41

End-to-end architectures trained via imitation learning have advanced autonomous driving by scaling model size and data, yet performance remains brittle in safety-critical long-tai…

cs.LG2025

The Geometry of Queries: Query-Based Innovations in Retrieval-Augmented Generation for Healthcare QA

Eric Yang, Jonathan Amar, Jong Ha Lee +2

Deploying Large Language Models (LLMs) for healthcare question answering requires robust methods to ensure accuracy and reliability. This work introduces Query-Based Retrieval Augm…

cs.LG2026

ECHO-2: A Large-Scale Distributed Rollout Framework for Cost-Efficient Reinforcement Learning

Jingwei Song, Meng Chen, Jie Xiao +15

Reinforcement learning (RL) is a critical stage in post-training large language models (LLMs), involving repeated interaction between rollout generation, reward evaluation, and cen…

cs.CL2024

Event Detection from Social Media for Epidemic Prediction

Tanmay Parekh, Anh Mac, Jiarui Yu +8

Social media is an easy-to-access platform providing timely updates about societal trends and events. Discussions regarding epidemic-related events such as infections, symptoms, an…

cs.LG2026

Detecting Clinical Discrepancies in Health Coaching Agents: A Dual-Stream Memory and Reconciliation Architecture

Samuel L Pugh, Eric Yang, Alexander Muir Sutherland +1

As Large Language Model (LLM) agents transition from single-session tools to persistent systems managing longitudinal healthcare journeys, their memory architectures face a critica…

cs.CL2025

AI Agents for Conversational Patient Triage: Preliminary Simulation-Based Evaluation with Real-World EHR Data

Sina Rashidian, Nan Li, Jonathan Amar +7

Background: We present a Patient Simulator that leverages real world patient encounters which cover a broad range of conditions and symptoms to provide synthetic test subjects for…

cs.CY2025

What Can Youth Learn About Artificial Intelligence and Machine Learning in One Hour? Examining How Hour of Code Activities Address the Five Big Ideas of AI

Luis Morales-Navarro, Yasmin B. Kafai, Eric Yang +1

The prominence of artificial intelligence and machine learning in everyday life has led to efforts to foster AI literacy for all K-12 students. In this paper, we review how Hour of…

cs.DC2025

Parallax: Efficient LLM Inference Service over Decentralized Environment

Chris Tong, Youhe Jiang, Gufeng Chen +6

Deploying a large language model (LLM) inference service remains costly because centralized serving depends on specialized GPU clusters and high-bandwidth interconnects in datacent…

cs.LG2025

Echo: Decoupling Inference and Training for Large-Scale RL Alignment on Heterogeneous Swarms

Jie Xiao, Changyuan Fan, Qingnan Ren +6

Modern RL-based post-training for large language models (LLMs) co-locate trajectory sampling and policy optimisation on the same GPU cluster, forcing the system to switch between i…

cs.SE2024

CELI: Controller-Embedded Language Model Interactions

Jan-Samuel Wagner, Dave DeCaprio, Abishek Chiffon Muthu Raja +12

We introduce Controller-Embedded Language Model Interactions (CELI), a framework that integrates control logic directly within language model (LM) prompts, facilitating complex, mu…

math.CO2021

Cyclic Base Ordering of Graphs

Jessica Li, Eric Yang, William Zhang

A cyclic base ordering of a connected graph , is a cyclic ordering of such that every cyclically consecutive edges form a spanning tree. In this project, we st…

cs.RO2026

FLASH: Fast Learning via GPU-Accelerated Simulation for High-Fidelity Deformable Manipulation in Minutes

Siyuan Luo, Bingyang Zhou, Chong Zhang +9

Simulation frameworks such as Isaac Sim have enabled scalable robot learning for locomotion and rigid-body manipulation; however, contact-rich simulation remains a major bottleneck…

cs.LG2026

AOI: Turning Failed Trajectories into Training Signals for Autonomous Cloud Diagnosis

Pei Yang, Wanyi Chen, Asuka Yuxi Zheng +11

Large language model (LLM) agents offer a promising data-driven approach to automating Site Reliability Engineering (SRE), yet their enterprise deployment is constrained by three c…

cs.DC2025

Lattica: A Decentralized Cross-NAT Communication Framework for Scalable AI Inference and Training

Ween Yang, Jason Liu, Suli Wang +4

The rapid expansion of distributed Artificial Intelligence (AI) workloads beyond centralized data centers creates a demand for new communication substrates. These substrates must o…

cs.LG2026

MERA: Model Evolution and Routing with Skill Adaptation for Agentic Systems at Scale

Yuhang Yao, Zeyu Wang, Wanyi Chen +8

LLM agents execute heterogeneous sequences of model calls within a single task: some invocations require careful reasoning, while others are structured steps such as formatting or…

cs.CR2026

VeriLLM: A Lightweight Framework for Publicly Verifiable Decentralized Inference

Ke Wang, Zishuo Zhao, Xinyuan Song +7

Decentralized inference provides a scalable and resilient paradigm for serving large language models (LLMs), enabling fragmented global resource utilization and reducing reliance o…

cs.LG2025

Symphony: A Decentralized Multi-Agent Framework for Scalable Collective Intelligence

Ji Wang, Kashing Chen, Xinyuan Song +4

Most existing Large Language Model (LLM)-based agent frameworks rely on centralized orchestration, incurring high deployment costs, rigid communication topologies, and limited adap…

cs.LG2024

MPLite: Multi-Aspect Pretraining for Mining Clinical Health Records

Eric Yang, Pengfei Hu, Xiaoxue Han +1

The adoption of digital systems in healthcare has resulted in the accumulation of vast electronic health records (EHRs), offering valuable data for machine learning methods to pred…

cs.AI2026

STEER: Inference-Time Risk Control via Constrained Quality-Diversity Search

Eric Yang, Jong Ha Lee, Jonathan Amar +2

Large Language Models (LLMs) trained for average correctness often exhibit mode collapse, producing narrow decision behaviors on tasks where multiple responses may be reasonable. T…

cs.DC2025

Speculative Decoding in Decentralized LLM Inference: Turning Communication Latency into Computation Throughput

Jingwei Song, Wanyi Chen, Xinyuan Song +7

Speculative decoding accelerates large language model (LLM) inference by using a lightweight draft model to propose tokens that are later verified by a stronger target model. While…

cs.CV2026

iSight: Towards expert-AI co-assessment for improved immunohistochemistry staining interpretation

Jacob S. Leiby, Jialu Yao, Pan Lu +17

Immunohistochemistry (IHC) provides information on protein expression in tissue sections and is commonly used to support pathology diagnosis and disease triage. While AI models for…

cs.LG2026

Implicit Strategic Optimization: Rethinking Long-Horizon Decision-Making in Adversarial Poker Environments

Boyang Xia, Weiyou Tian, Qingnan Ren +7

Training large language model (LLM) agents for adversarial games is often driven by episodic objectives such as win rate. In long-horizon settings, however, payoffs are shaped by l…

cs.LG2024

Selective Fine-tuning on LLM-labeled Data May Reduce Reliance on Human Annotation: A Case Study Using Schedule-of-Event Table Detection

Bhawesh Kumar, Jonathan Amar, Eric Yang +2

Large Language Models (LLMs) have demonstrated their efficacy across a broad spectrum of tasks in healthcare applications. However, often LLMs need to be fine-tuned on task-specifi…

cs.CL2025

FHIR-AgentBench: Benchmarking LLM Agents for Realistic Interoperable EHR Question Answering

Gyubok Lee, Elea Bach, Eric Yang +5

The recent shift toward the Health Level Seven Fast Healthcare Interoperability Resources (HL7 FHIR) standard opens a new frontier for clinical AI, demanding LLM agents to navigate…

cs.LG2025

Sleepless Nights, Sugary Days: Creating Synthetic Users with Health Conditions for Realistic Coaching Agent Interactions

Taedong Yun, Eric Yang, Mustafa Safdari +13

We present an end-to-end framework for generating synthetic users for evaluating interactive agents designed to encourage positive behavior changes, such as in health and lifestyle…

cs.CV2020

The NVIDIA PilotNet Experiments

Mariusz Bojarski, Chenyi Chen, Joyjit Daw +22

Four years ago, an experimental system known as PilotNet became the first NVIDIA system to steer an autonomous car along a roadway. This system represents a departure from the clas…

cond-mat1993

Coulomb Gaps in a Strong Magnetic Field, S.-R

Eric Yang, A. H. MacDonald

We report on a study of interaction effects in the tunneling density-of-states of a disordered two-dimensional electron gas in the strong magnetic field limit where only the lowest…