14 papers
Hierarchical Credit Assignment for RLVR on Fused Gromov-Wasserstein Geometry
Qi Yu, Ruizhong Qiu, Zhichen Zeng +6
Reinforcement learning with verifiable rewards (RLVR) has been shown to improve the reasoning capability of large language models (LLMs) across diverse reasoning tasks. However, gr…
EvoHarness-RL: Learning Runtime Harness Coordination for Self-Evolving Agents
Xuying Ning, Dongqi Fu, Tianxin Wei +17
Long-horizon LLM agents increasingly rely on external execution support to maintain state, track progress, recover from failures, and reuse experience across extended interactions.…
KVEraser: Learning to Steer KV Cache for Efficient Localized Context Erasing
Mufei Li, Shikun Liu, Dongqi Fu +5
Post-hoc context erasing over the KV cache is challenging because a local edit has a global consequence: once a span has been processed, its influence propagates into the cached st…
Structuring and Tokenizing Distributed User Interest Context for Generative Recommendation
Ruizhong Qiu, Yinglong Xia, Dongqi Fu +6
Generative recommendation is an emerging paradigm that has shown promise in industrial recommendation systems, aiming to predict users' next interactions from their historical beha…
Protein Representation Learning with Secondary-Structure and Energy-Filtered Hydrogen-Bond Graphs
Mohamed Mouhajir, Limei Wang, El Houcine Bergou +3
Graph-based representations are widely used in protein modeling, yet many existing approaches rely primarily on sequence adjacency or geometric proximity, which only partially refl…
Towards Direct Latent-Space Synthesis for Parallel Branches in LLM-Agent Workflows
Shikun Liu, Mufei Li, Dongqi Fu +5
Large language models increasingly serve as execution engines for agentic systems, yet they still consume context through a sequential text interface. This creates a mismatch with…
ChronoID: Infusing Explicit Temporal Signals into Semantic IDs for Generative Recommendation
Dongdong Nian, Dongqi Fu, Chenliang Xu +4
Semantic IDs are crucial in generative recommendation, but with a fundamental limitation: temporal information is not well incorporated into semantic IDs. Instead, time influences…
DAG-MoE: From Simple Mixture to Structural Aggregation in Mixture-of-Experts
Jiarui Feng, Hanqing Zeng, Karish Grover +11
Mixture-of-Experts (MoE) models have become a leading approach for decoupling parameter count from computational cost in large language models, yet effectively scaling MoE performa…
Efficient Retrieval Scaling with Hierarchical Indexing for Large Scale Recommendation
Dongqi Fu, Kaushik Rangadurai, Haiyu Lu +13
The increase in data volume, computational resources, and model parameters during training has led to the development of numerous large-scale industrial retrieval models for recomm…
ReMix: Reinforcement routing for mixtures of LoRAs in LLM finetuning
Ruizhong Qiu, Hanqing Zeng, Yinglong Xia +15
Low-rank adapters (LoRAs) are a parameter-efficient finetuning technique that injects trainable low-rank matrices into pretrained models to adapt them to new tasks. Mixture-of-LoRA…
Haystack Engineering: Context Engineering for Heterogeneous and Agentic Long-Context Evaluation
Mufei Li, Dongqi Fu, Limei Wang +10
Modern long-context large language models (LLMs) perform well on synthetic "needle-in-a-haystack" (NIAH) benchmarks, but such tests overlook how noisy contexts arise from biased re…
BACKTIME: Backdoor Attacks on Multivariate Time Series Forecasting
Xiao Lin, Zhining Liu, Dongqi Fu +2
Multivariate Time Series (MTS) forecasting is a fundamental task with numerous real-world applications, such as transportation, climate, and epidemiology. While a myriad of powerfu…
Learning Graph Quantized Tokenizers
Limei Wang, Kaveh Hassani, Si Zhang +7
Transformers serve as the backbone architectures of Foundational Models, where domain-specific tokenizers allow them to adapt to various domains. Graph Transformers (GTs) have rece…
How to Make LMs Strong Node Classifiers?
Zhe Xu, Kaveh Hassani, Si Zhang +7
Language Models (LMs) are increasingly challenging the dominance of domain-specific models, such as Graph Neural Networks (GNNs) and Graph Transformers (GTs), in graph learning tas…