5 citations · 10 across the 32 of their papers we have counts for
11 papers · 1 filter
How Data Scales in Agentic Reinforcement Learning: Laws and Synthesis Strategies
Bowei He, Yankai Chen, Xiaokun Zhang +4
Pretraining scaling laws treat training data as a one-dimensional quantity: a token count. Agentic reinforcement learning (RL) inherits this scalar abstraction, but modern synthesi…
Discrete Diffusion Models: A Unified Framework from Tokenization to Generation
Ye Yuan, Weien Li, Rui Song +20
Discrete denoising diffusion models (DDMs) have recently emerged as a compelling alternative to autoregressive (AR) modeling for discrete data, offering parallel generation and ite…
Branching Policy Optimization: Sandbox-Native Language Agent Reinforcement Learning
Bowei He, Yankai Chen, Xiaokun Zhang +1
Reinforcement learning has emerged as the dominant paradigm for training large language model (LLM) agents that interact with executable sandboxes. State-of-the-art algorithms such…
Distributionally Robust Set Representation Learning Under Inference-Time Element Corruption
Yankai Chen, Hanrong Zhang, Bowei He +2
Standard Set Representation Learning methods typically excel on curated data but often overlook the challenge of inference-time element corruption. This refers to scenarios where d…
Support-Proximity Augmented Diffusion Estimation for Offline Black-Box Optimization
Yonghan Yang, Ye Yuan, Zipeng Sun +5
Offline black-box optimization aims to discover novel designs with high property scores using only a static dataset, a task fundamentally challenged by the out-of-distribution (OOD…
MINER: Mining Multimodal Internal Representation for Efficient Retrieval
Weien Li, Rui Song, Zeyu Li +8
Visual document retrieval has become essential for accessing information in visually rich documents. Existing approaches fall into two camps. Late-interaction retrievers achieve st…
The Workload-Router-Pool Architecture for LLM Inference Optimization: A Vision Paper from the vLLM Semantic Router Project
Huamin Chen, Xunzhuo Liu, Bowei He +5
Over the past year, the vLLM Semantic Router project has released a series of work spanning: (1) core routing mechanisms -- signal-driven routing, context-length pool routing, rout…
From Inference Routing to Agent Orchestration: Declarative Policy Compilation with Cross-Layer Verification
Huamin Chen, Xunzhuo Liu, Bowei He +1
The Semantic Router DSL is a non-Turing-complete policy language deployed in production for per-request LLM inference routing: content signals (embedding similarity, PII detection,…
Conflict-Free Policy Languages for Probabilistic ML Predicates: A Framework and Case Study with the Semantic Router DSL
Xunzhuo Liu, Hao Wu, Huamin Chen +2
Conflict detection in policy languages is a solved problem -- as long as every rule condition is a crisp Boolean predicate. BDDs, SMT solvers, and NetKAT all exploit that assumptio…
Outcome-Aware Tool Selection for Semantic Routers: Latency-Constrained Learning Without LLM Inference
Huamin Chen, Xunzhuo Liu, Junchen Jiang +2
Semantic routers in LLM inference gateways select tools in the critical request path, where every millisecond of added latency compounds across millions of requests. We propose Out…
Attention-Aware GNN-based Input Defense against Multi-Turn LLM Jailbreak
Zixuan Huang, Kecheng Huang, Lihao Yin +4
Large Language Models (LLMs) have gained significant traction in various applications, yet their capabilities present risks for both constructive and malicious exploitation. Despit…