11 citations · 46 across the 24 of their papers we have counts for
31 papers
CascadeLedger: Counterfactual Auditing of Information and Resource Integrity in LLM Cascades
Miaobo Hu, Shuhao Hu, Xiaobo Guo +4
We introduce CascadeLedger, a counterfactual execution-audit framework for budgeted language-model cascades. The protocol enforces call-before-read semantics, binds successful read…
FedRIC: Heterogeneity-Aware Federated Learning with Hard Deadline Constraints in Open RAN
Adhwaa Al-Chaab, Ayman Younis, Dario Pompili
Open Radio Access Networks (O-RANs) bring intelligence to disaggregated RANs through virtualized platforms and open interfaces, but the stringent latency budgets of the RAN Intelli…
Quantizer Redundancy and Exact Index Recoding in a Frozen Neural Audio Codec
Youssef Hemimy
Residual scalar quantization can produce highly dependent indices when successive stages reuse identical, unscaled grids. This case study examines that behavior in a frozen neural…
FSPO: Policy-Consistent Risk and Pareto-Feasible Control for Budgeted LLM RL Post-Training
Miaobo Hu, Shuhao Hu, Xiaobo Guo +4
Adaptive LLM reinforcement-learning post-training changes multiple training actuators online, including rollout temperature, group size, clipping, KL regularization, verifier alloc…
ROUTEAUDIT: Interaction-Aware Identification for Budgeted Multi-Verifier Routing
Miaobo Hu, Shuhao Hu, Xiaobo Guo +5
Adaptive multi-verifier systems are commonly compared through endpoint quality-cost gaps, even when the verifier catalog, availability, accounting, information filtration, or score…
VStress: Correlation-Aware Auditing and Adaptive Budget Allocation for Repeated Verifiers
Miaobo Hu, Shuhao Hu, Xiaobo Guo +5
Repeated verifier calls are useful only when they contribute conditional information. We introduce VStress, an auditable replay contract, and VStress-CA, a correlation-aware alloca…
SCOPE and SCION: A Benchmark and an Auditable Reference Pipeline for Schema Induction and Fusion from Text
Miaobo Hu, Xiaobo Guo, Shuhao Hu +5
Schema graphs are an upstream bottleneck of schema-grounded information extraction and knowledge graph construction, yet most extraction systems assume the schema is already availa…
ECPO: Evidence-Coupled Policy Optimization for Verifier-Audited Candidate Ranking
Miaobo Hu, Shuhao Hu, BoKun Wang +5
Ranking systems used for decision support should expose evidence that can be audited independently of the model's ranking scores. We study a closed-roster setting in which a policy…
AGPO: Adaptive Group Policy Optimization with Dual Statistical Feedback
Miaobo Hu, Shuhao Hu, Bokun Wang +5
Reinforcement learning improves LLM reasoning, but PPO/GRPO typically use fixed clipping and decoding temperature, which makes training brittle and tuning-heavy. We propose Adaptiv…
SAVER: Selective As-Needed Vision Evidence for Multimodal Information Extraction
Miaobo Hu, Shuhao Hu, Bokun Wang +5
Multimodal IE in social media is difficult because a post may attach multiple images that are weakly related, redundant, or even misleading with respect to the text. In this settin…
DARE: Diffusion Language Model Activation Reuse for Efficient Inference
Natalia Frumkin, Bokun Wang, Hung-Yueh Chiang +3
Diffusion Large Language Models (dLLMs) have emerged as a promising alternative to auto-regressive (AR) models, offering greater expressive capacity and potential for parallel gene…
Video Compression Meets Video Generation: Latent Inter-Frame Pruning with Attention Recovery
Dennis Menn, Yuedong Yang, Bokun Wang +6
Current video generation models suffer from high computational latency, making real-time applications prohibitively costly. In this paper, we address this limitation by exploiting…
A Geometry-Aware Efficient Algorithm for Compositional Entropic Risk Minimization
Xiyuan Wei, Linli Zhou, Bokun Wang +2
This paper studies optimization for a family of problems termed , in which each data's loss is formulated as a Log-Expectation-Ex…
ELANA: A Simple Energy and Latency Analyzer for LLMs
Hung-Yueh Chiang, Bokun Wang, Diana Marculescu
The latency and power consumption of large language models (LLMs) are major constraints when serving them across a wide spectrum of hardware platforms, from mobile edge devices to…
Stochastic Momentum Methods for Non-smooth Non-Convex Finite-Sum Coupled Compositional Optimization
Xingyu Chen, Bokun Wang, Ming Yang +2
Finite-sum Coupled Compositional Optimization (FCCO), characterized by its coupled compositional objective structure, emerges as an important optimization paradigm for addressing a…
Stochastic Primal-Dual Double Block-Coordinate for Two-way Partial AUC Maximization
Linli Zhou, Bokun Wang, My T. Thai +1
Two-way partial AUC (TPAUC) is a critical performance metric for binary classification with imbalanced data, as it focuses on specific ranges of the true positive rate (TPR) and fa…
Discovering Global False Negatives On the Fly for Self-supervised Contrastive Learning
Vicente Balmaseda, Bokun Wang, Ching-Long Lin +1
In self-supervised contrastive learning, negative pairs are typically constructed using an anchor image and a sample drawn from the entire dataset, excluding the anchor. However, t…
On Discriminative Probabilistic Modeling for Self-Supervised Representation Learning
Bokun Wang, Yunwen Lei, Yiming Ying +1
We study the discriminative probabilistic modeling on a continuous domain for the data prediction task of (multimodal) self-supervised representation learning. To address the chall…
Towards Federated Learning with On-device Training and Communication in 8-bit Floating Point
Bokun Wang, Axel Berg, Durmus Alp Emre Acar +1
Recent work has shown that 8-bit floating point (FP8) can be used for efficiently training neural networks with reduced computational cost compared to training in FP32/FP16. In thi…
A Near-Optimal Single-Loop Stochastic Algorithm for Convex Finite-Sum Coupled Compositional Optimization
Bokun Wang, Tianbao Yang
This paper studies a class of convex Finite-sum Coupled Compositional Optimization (cFCCO) problems with applications including group distributionally robust optimization (GDRO) an…
Everything Perturbed All at Once: Enabling Differentiable Graph Attacks
Haoran Liu, Bokun Wang, Jianling Wang +3
As powerful tools for representation learning on graphs, graph neural networks (GNNs) have played an important role in applications including social networks, recommendation system…
Provable Multi-instance Deep AUC Maximization with Stochastic Pooling
Dixian Zhu, Bokun Wang, Zhi Chen +4
This paper considers a novel application of deep AUC maximization (DAM) for multi-instance learning (MIL), in which a single class label is assigned to a bag of instances (e.g., mu…
GraphFM: Improving Large-Scale GNN Training via Feature Momentum
Haiyang Yu, Limei Wang, Bokun Wang +3
Training of graph neural networks (GNNs) for large-scale node classification is challenging. A key difficulty lies in obtaining accurate hidden node representations while avoiding…
When AUC meets DRO: Optimizing Partial AUC for Deep Learning with Non-Convex Convergence Guarantee
Dixian Zhu, Gang Li, Bokun Wang +2
In this paper, we propose systematic and efficient gradient-based methods for both one-way and two-way partial AUC (pAUC) maximization that are applicable to deep learning. We prop…