arXiv subjects

Hongwu Peng

Publications and source records attributed to Hongwu Peng.

At least 19 recordsLinked to original sources

arXiv2026

ES-VP : Energy-Shaped Dynamic Visual Prompting for Efficient Model Adaptation

Visual prompting (VP) has emerged as a parameter-efficient method for adapting pre-trained models to downstream tasks. However, existing approaches encounter a trade-off between flexibility and efficiency. Some methods apply a fixed prompt to all images, ignoring individual image characteristics, while others introduce auxiliary networks to generate diverse prompts. Although the latter can improve performance, it also significantly increases parameter usage and the potential for overfitting to specific datasets. Furthermore, the auxiliary networks, combined with inherent biases in pre-trained models, limit scalability and generalization. In this paper, we propose Energy-Shaped Visual Prompting (ES-VP), a novel approach that generates image-specific prompts using low-rank initialization and energy-guided dynamic adaptation, achieving superior performance with fewer parameters compared to single-prompt methods. ES-VP directly utilizes the pre-trained model for adaptive prompt generation, ensuring both parameter efficiency and improved generalization. Extensive experiments conducted on five architectures across fifteen datasets demonstrate that ES-VP consistently outperforms current state-of-the-art (SOTA) single and diverse VP methods. For instance, using the CLIP architecture across four datasets, ES-VP outperforms the SOTA method DAM-VP by an average of 2.6\% in accuracy while utilizing 590$\times$ fewer VP parameters, thereby establishing a new benchmark for efficient and generalizable model adaptation.

cs.CV↗

arXiv2026

Latent Reward Steering: An Adaptive Inference-Time Framework that Implicitly Promotes Cognitive Behaviors in Reasoning LLMs

Strong reasoning depends not only on model knowledge but also on how effectively cognitive behaviors are deployed during generation. Existing methods often rely on explicit behavior-level control, making them insufficiently adaptive when failures and required corrections vary across reasoning states, tasks, and models. To this end, we propose Latent Reward Steering (LRS), an adaptive inference-time framework that promotes cognitive behaviors by optimizing the sparse-autoencoder (SAE) latent states that implicitly carry them. Rather than relying on predefined cognitive behaviors or steering directions derived from them, LRS trains a latent reward model on reasoning traces by final answer correctness to estimate the quality of intermediate latent states. During inference, reward gradients provide state-specific correction directions for fragile latent states, while a reward and confidence gate restricts intervention to states the reward signal flags as fragile. Experiments on multiple reasoning LLM backbones and benchmarks show that \ours consistently improves performance over various baselines, and post-hoc analyses further indicate that \ours implicitly promotes good cognitive behaviors that fix the original reasoning errors. Code is available at: https://github.com/jiakanglee/Latent-Reward-Steering.

cs.AI↗

arXiv2026

Complete-muE: Optimal Hyperparameter Transfer and Scaling for MoE Models

We propose Complete-muE, a framework which targets hyperparameter transfer across dense FFN and any Mixture-of-Experts (MoE) setups in transformer blocks. Existing tools such as $\mu$P (requires fixed architectue) or SDE (requires fixed per-step token count) cannot directly solve the hyperparameter transfer problem in MoE setups because Dense to MoE transfer or MoE total experts scaling changes both architecture and tokens per expert. Complete-muE solves this challenge with a two-bridge system: Bridge~I maps between dense FFN and Dense MoE by active-width $\mu$P with a normalized router scale. Bridge~II maps between Dense MoE and sparse MoE by activated-expert scaling, where the first-order SDE LR/WD correction cancels while a bounded residual $\sigma_0$ shift remains. The resulting transfer rule, which we term as Complete muE, covers changes in activated experts, total capacity, granularity, and shared/group-balanced hybrids for MoE models as well as network width/depth, batch size, and duration changes for general Transformer models. Extensive language model and diffusion model pretraining experiments confirm that complete-muE yields relatively stable hyperparameter optima across model architectures and parameter counts -- with only minor drift consistent with the non-strict SDE behavior of Bridge~II. In practice this drift is small enough that hyperparameters tuned on a single dense reference transfer near-optimally to all MoE configurations -- \emph{tune dense once, transfer to all} is the practical recipe at the core of Complete-muE. This enables MoE models to achieve accelerated convergence speedup over dense models when scaling model capacity without costly hyperparameter search.

cs.LG↗

arXiv2026

Multi-Head Low-Rank Attention

Long-context inference in large language models is bottlenecked by Key--Value (KV) cache loading during the decoding stage, where the sequential nature of generation requires repeatedly transferring the KV cache from off-chip High-Bandwidth Memory (HBM) to on-chip Static Random-Access Memory (SRAM) at each step. While Multi-Head Latent Attention (MLA) significantly reduces the total KV cache size, it suffers from a sharding bottleneck during distributed decoding via Tensor Parallelism (TP). Since its single latent head cannot be partitioned, each device is forced to redundantly load the complete KV cache for every token, consuming excessive memory traffic and diminishing TP benefits like weight sharding. In this work, we propose Multi-Head Low-Rank Attention (MLRA), which enables partitionable latent states for efficient 4-way TP decoding. Extensive experiments show that MLRA achieves state-of-the-art perplexity and downstream task performance, while also delivering a 2.8$\times$ decoding speedup over MLA. Code is available at https://github.com/SongtaoLiu0823/MLRA. Pretrained weights, along with the training and evaluation data, are available at https://huggingface.co/Soughing/MLRA.

cs.LG↗

arXiv2026

Reasoning over Precedents Alongside Statutes: Case-Augmented Deliberative Alignment for LLM Safety

Ensuring that Large Language Models (LLMs) adhere to safety principles without refusing benign requests remains a significant challenge. While OpenAI introduces deliberative alignment (DA) to enhance the safety of its o-series models through reasoning over detailed ``code-like'' safety rules, the effectiveness of this approach in open-source LLMs, which typically lack advanced reasoning capabilities, is understudied. In this work, we systematically evaluate the impact of explicitly specifying extensive safety codes versus demonstrating them through illustrative cases. We find that referencing explicit codes inconsistently improves harmlessness and systematically degrades helpfulness, whereas training on case-augmented simple codes yields more robust and generalized safety behaviors. By guiding LLMs with case-augmented reasoning instead of extensive code-like safety rules, we avoid rigid adherence to narrowly enumerated rules and enable broader adaptability. Building on these insights, we propose CADA, a case-augmented deliberative alignment method for LLMs utilizing reinforcement learning on self-generated safety reasoning chains. CADA effectively enhances harmlessness, improves robustness against attacks, and reduces over-refusal while preserving utility across diverse benchmarks, offering a practical alternative to rule-only DA for improving safety while maintaining helpfulness.

cs.AI↗

arXiv2025

DTop-p MoE: Sparsity-Controlled Dynamic Top-p MoE for Foundation Model Pre-training

Sparse Mixture-of-Experts architectures are essential for scaling model capacity efficiently, yet the standard Top-$k$ routing imposes a rigid sparsity pattern that ignores the intrinsic variance in token difficulty and layer-specific computational needs. Top-$p$ routing is more adaptive because it selects experts until their cumulative routing probability reaches a threshold, allowing confident tokens to use fewer experts and ambiguous tokens to recruit more. However, we demonstrate that existing naive Top-$p$ implementations with fixed global probability thresholds provide only marginal gains over Top-$k$, suffer from hyperparameter sensitivity, and result in uncontrolled computational costs. In this paper, we propose **DTop-$p$**, a sparsity-controllable dynamic routing mechanism that learns the Top-$p$ probability threshold with a Proportional-Integral controller and uses dynamic routing normalization to support layer-wise expert selection under a global sparsity constraint. Extensive experiments on Large Language Models and Diffusion Transformers demonstrate that **DTop-$p$** consistently outperforms both Top-$k$ and fixed Top-$p$ baselines while matching the average FLOPs of Top-$k$ MoE. Our analysis confirms that **DTop-$p$** exhibits strong scaling properties across expert granularity, total expert capacity, model size, and dataset size, offering a robust and efficient MoE framework for foundation model pre-training.

cs.AI↗

arXiv2025

GROOT: Graph Edge Re-growth and Partitioning for the Verification of Large Designs in Logic Synthesis

Traditional verification methods in chip design are highly time-consuming and computationally demanding, especially for large scale circuits. Graph neural networks (GNNs) have gained popularity as a potential solution to improve verification efficiency. However, there lacks a joint framework that considers all chip design domain knowledge, graph theory, and GPU kernel designs. To address this challenge, we introduce GROOT, an algorithm and system co-design framework that contains chip design domain knowledge and redesigned GPU kernels, to improve verification efficiency. More specifically, we create node features utilizing the circuit node types and the polarity of the connections between the input edges to nodes in And-Inverter Graphs (AIGs). We utilize a graph partitioning algorithm to divide the large graphs into smaller sub-graphs for fast GPU processing and develop a graph edge re-growth algorithm to recover verification accuracy. We carefully profile the EDA graph workloads and observe the uniqueness of their polarized distribution of high degree (HD) nodes and low degree (LD) nodes. We redesign two GPU kernels (HD-kernel and LD-kernel), to fit the EDA graph learning workload on a single GPU. We compare the results with state-of-the-art (SOTA) methods: GAMORA, a GNN-based approach, and the traditional ABC framework. Results show that GROOT achieves a significant reduction in memory footprint (59.38 %), with high accuracy (99.96%) for a very large CSA multiplier, i.e. 1,024 bits with a batch size of 16, which consists of 134,103,040 nodes and 268,140,544 edges. We compare GROOT with GPU-based GPU Kernel designs SOTAs such as cuSPARSE, MergePath-SpMM, and GNNAdvisor. We achieve up to 1.104x, 5.796x, and 1.469x improvement in runtime, respectively.

cs.LG↗

arXiv2025

LLM-VeriPPA: Power, Performance, and Area Optimization aware Verilog Code Generation with Large Language Models

Large Language Models (LLMs) are gaining prominence in various fields, thanks to their ability to generate high- quality content from human instructions. This paper delves into the field of chip design using LLMs, specifically in Power- Performance-Area (PPA) optimization and the generation of accurate Verilog codes for circuit designs. We introduce a novel framework VeriPPA designed to optimize PPA and generate Verilog code using LLMs. Our method includes a two-stage process where the first stage focuses on improving the functional and syntactic correctness of the generated Verilog codes, while the second stage focuses on optimizing the Verilog codes to meet PPA constraints of circuit designs, a crucial element of chip design. Our framework achieves an 81.37% success rate in syntactic correctness and 62.06% in functional correctness for code genera- tion, outperforming current state-of-the-art (SOTA) methods. On the RTLLM dataset. On the VerilogEval dataset, our framework achieves 99.56% syntactic correctness and 43.79% functional correctness, also surpassing SOTA, which stands at 92.11% for syntactic correctness and 33.57% for functional correctness. Furthermore, Our framework able to optimize the PPA of the designs. These results highlight the potential of LLMs in handling complex technical areas and indicate an encouraging development in the automation of chip design processes.

cs.AR↗

arXiv2025

DR-CircuitGNN: Training Acceleration of Heterogeneous Circuit Graph Neural Network on GPUs

The increasing scale and complexity of integrated circuit design have led to increased challenges in Electronic Design Automation (EDA). Graph Neural Networks (GNNs) have emerged as a promising approach to assist EDA design as circuits can be naturally represented as graphs. While GNNs offer a foundation for circuit analysis, they often fail to capture the full complexity of EDA designs. Heterogeneous Graph Neural Networks (HGNNs) can better interpret EDA circuit graphs as they capture both topological relationships and geometric features. However, the improved representation capability comes at the cost of even higher computational complexity and processing cost due to their serial module-wise message-passing scheme, creating a significant performance bottleneck. In this paper, we propose DR-CircuitGNN, a fast GPU kernel design by leveraging row-wise sparsity-aware Dynamic-ReLU and optimizing SpMM kernels during heterogeneous message-passing to accelerate HGNNs training on EDA-related circuit graph datasets. To further enhance performance, we propose a parallel optimization strategy that maximizes CPU-GPU concurrency by concurrently processing independent subgraphs using multi-threaded CPU initialization and GPU kernel execution via multiple cudaStreams. Our experiments show that on three representative CircuitNet designs (small, medium, large), the proposed method can achieve up to 3.51x and 4.09x speedup compared to the SOTA for forward and backward propagation, respectively. On full-size CircuitNet and sampled Mini-CircuitNet, our parallel design enables up to 2.71x speed up over the official DGL implementation cuSPARSE with negligible impact on correlation scores and error rates.

cs.LG↗

arXiv2025

AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning

Test-time scaling strategies for Large Language Models predominantly rely on either reinforcement learning with sparse outcome rewards or search-based methods guided by static Process Reward Models. However, outcome-based RL often suffers from training instability and sample inefficiency, while static PRMs require expensive step-wise supervision and are susceptible to reward hacking due to distributional shifts. In this paper, we introduce AIRL-S, a unified framework that integrates Adversarial Inverse Reinforcement Learning with Group Relative Policy Optimization. By inferring a dense, step-wise reward model directly from reference trajectories, AIRL-S eliminates the dependency on labeled process data and uses the same learned PRM as both a training signal and a verifier for search-based TTS. Extensive evaluations across eight benchmarks in mathematics, science, and code generation demonstrate that our policy model improves average performance by 9\% over the base model, matching GPT-4o. We further analyze how the AIRL and GRPO objectives complement each other and how the learned PRM transfers across generators and search algorithms, establishing a robust and cost-effective methodology for scaling test-time computation in complex reasoning tasks.

cs.LG↗

arXiv2025

Two Heads are Better Than One: Test-time Scaling of Multi-agent Collaborative Reasoning

Test-Time Scaling has emerged as a powerful method to extend the reasoning capabilities of Large Language Models. However, single-agent TTS faces significant scalability bottlenecks, as excessively long reasoning traces lead to increased inference costs and stability issues caused by context management failures. To address these limitations, we propose leveraging Multi-Agent Systems as a structural upgrade to standard TTS. By decomposing monolithic reasoning chains into distinct, manageable contexts across multiple agents, MAS offers a more robust framework for scaling reasoning. We validate this approach by introducing M500, a dataset comprising 500 high-quality multi-agent, multi-turn collaborative reasoning traces generated via DeepSeek-R1. Through Supervised Fine-Tuning on M500, we enable open-source models to internalize collaborative reasoning patterns and show improved TTS performance in MAS. Furthermore, we propose an adaptive scaling strategy incorporating a ``CEO'' agent to dynamically guide the reasoning process and optimize collaboration depth. Extensive experiments within the AgentVerse framework demonstrate that our fine-tuned models, Qwen2.5-32B-MAS and Phi4-14B-MAS, significantly outperform their base counterparts. Codes are available at https://github.com/jincan333/MAS-TTS.

cs.AI↗

arXiv2025

RankFlow: A Multi-Role Collaborative Reranking Workflow Utilizing Large Language Models

In an Information Retrieval (IR) system, reranking plays a critical role by sorting candidate passages according to their relevance to a specific query. This process demands a nuanced understanding of the variations among passages linked to the query. In this work, we introduce RankFlow, a multi-role reranking workflow that leverages the capabilities of Large Language Models (LLMs) and role specializations to improve reranking performance. RankFlow enlists LLMs to fulfill four distinct roles: the query Rewriter, the pseudo Answerer, the passage Summarizer, and the Reranker. This orchestrated approach enables RankFlow to: (1) accurately interpret queries, (2) draw upon LLMs' extensive pre-existing knowledge, (3) distill passages into concise versions, and (4) assess passages in a comprehensive manner, resulting in notably better reranking results. Our experimental results reveal that RankFlow outperforms existing leading approaches on widely recognized IR benchmarks, such as TREC-DL, BEIR, and NovelEval. Additionally, we investigate the individual contributions of each role in RankFlow.

cs.IR↗

arXiv2024

RTop-K: Ultra-Fast Row-Wise Top-K Selection for Neural Network Acceleration on GPUs

Top-k selection algorithms are fundamental in a wide range of applications, including high-performance computing, information retrieval, big data processing, and neural network model training. In this paper, we present RTop-K, a highly efficient parallel row-wise top-k selection algorithm specifically designed for GPUs. RTop-K leverages a binary search-based approach to optimize row-wise top-k selection, providing a scalable and accelerated solution. We conduct a detailed analysis of early stopping in our algorithm, showing that it effectively maintains the testing accuracy of neural network models while substantially improving performance. Our GPU implementation of RTop-K demonstrates superior performance over state-of-the-art row-wise top-k GPU implementations, achieving an average speed-up of up to 11.49$\times$ with early stopping and 7.29$\times$ without early stopping. Moreover, RTop-K accelerates the overall training workflow of MaxK-GNNs, delivering speed-ups ranging from 11.97% to 33.29% across different models and datasets.

cs.DC↗

arXiv2024

APEER: Automatic Prompt Engineering Enhances Large Language Model Reranking

Large Language Models (LLMs) have significantly enhanced Information Retrieval (IR) across various modules, such as reranking. Despite impressive performance, current zero-shot relevance ranking with LLMs heavily relies on human prompt engineering. Existing automatic prompt engineering algorithms primarily focus on language modeling and classification tasks, leaving the domain of IR, particularly reranking, underexplored. Directly applying current prompt engineering algorithms to relevance ranking is challenging due to the integration of query and long passage pairs in the input, where the ranking complexity surpasses classification tasks. To reduce human effort and unlock the potential of prompt optimization in reranking, we introduce a novel automatic prompt engineering algorithm named APEER. APEER iteratively generates refined prompts through feedback and preference optimization. Extensive experiments with four LLMs and ten datasets demonstrate the substantial performance improvement of APEER over existing state-of-the-art (SoTA) manual prompts. Furthermore, we find that the prompts generated by APEER exhibit better transferability across diverse tasks and LLMs.

cs.AI↗

arXiv2024

SSNet: A Lightweight Multi-Party Computation Scheme for Practical Privacy-Preserving Machine Learning Service in the Cloud

As privacy-preserving becomes a pivotal aspect of deep learning (DL) development, multi-party computation (MPC) has gained prominence for its efficiency and strong security. However, the practice of current MPC frameworks is limited, especially when dealing with large neural networks, exemplified by the prolonged execution time of 25.8 seconds for secure inference on ResNet-152. The primary challenge lies in the reliance of current MPC approaches on additive secret sharing, which incurs significant communication overhead with non-linear operations such as comparisons. Furthermore, additive sharing suffers from poor scalability on party size. In contrast, the evolving landscape of MPC necessitates accommodating a larger number of compute parties and ensuring robust performance against malicious activities or computational failures. In light of these challenges, we propose SSNet, which for the first time, employs Shamir's secret sharing (SSS) as the backbone of MPC-based ML framework. We meticulously develop all framework primitives and operations for secure DL models tailored to seamlessly integrate with the SSS scheme. SSNet demonstrates the ability to scale up party numbers straightforwardly and embeds strategies to authenticate the computation correctness without incurring significant performance overhead. Additionally, SSNet introduces masking strategies designed to reduce communication overhead associated with non-linear operations. We conduct comprehensive experimental evaluations on commercial cloud computing infrastructure from Amazon AWS, as well as across diverse prevalent DNN models and datasets. SSNet demonstrates a substantial performance boost, achieving speed-ups ranging from 3x to 14x compared to SOTA MPC frameworks. Moreover, SSNet also represents the first framework that is evaluated on a five-party computation setup, in the context of secure DL inference.

cs.CR↗

arXiv2024

Learning from Teaching Regularization: Generalizable Correlations Should be Easy to Imitate

Generalization remains a central challenge in machine learning. In this work, we propose Learning from Teaching (LoT), a novel regularization technique for deep neural networks to enhance generalization. Inspired by the human ability to capture concise and abstract patterns, we hypothesize that generalizable correlations are expected to be easier to imitate. LoT operationalizes this concept to improve the generalization of the main model with auxiliary student learners. The student learners are trained by the main model and, in turn, provide feedback to help the main model capture more generalizable and imitable correlations. Our experimental results across several domains, including Computer Vision, Natural Language Processing, and methodologies like Reinforcement Learning, demonstrate that the introduction of LoT brings significant benefits compared to training models on the original dataset. The results suggest the effectiveness and efficiency of LoT in identifying generalizable information at the right scales while discarding spurious data correlations, thus making LoT a valuable addition to current machine learning. Code is available at https://github.com/jincan333/LoT.

cs.LG↗

arXiv2024

Zero-Space Cost Fault Tolerance for Transformer-based Language Models on ReRAM

Resistive Random Access Memory (ReRAM) has emerged as a promising platform for deep neural networks (DNNs) due to its support for parallel in-situ matrix-vector multiplication. However, hardware failures, such as stuck-at-fault defects, can result in significant prediction errors during model inference. While additional crossbars can be used to address these failures, they come with storage overhead and are not efficient in terms of space, energy, and cost. In this paper, we propose a fault protection mechanism that incurs zero space cost. Our approach includes: 1) differentiable structure pruning of rows and columns to reduce model redundancy, 2) weight duplication and voting for robust output, and 3) embedding duplicated most significant bits (MSBs) into the model weight. We evaluate our method on nine tasks of the GLUE benchmark with the BERT model, and experimental results prove its effectiveness.

cs.LG↗

arXiv2024

Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads

Large Language Models (LLMs) employ auto-regressive decoding that requires sequential computation, with each step reliant on the previous one's output. This creates a bottleneck as each step necessitates moving the full model parameters from High-Bandwidth Memory (HBM) to the accelerator's cache. While methods such as speculative decoding have been suggested to address this issue, their implementation is impeded by the challenges associated with acquiring and maintaining a separate draft model. In this paper, we present Medusa, an efficient method that augments LLM inference by adding extra decoding heads to predict multiple subsequent tokens in parallel. Using a tree-based attention mechanism, Medusa constructs multiple candidate continuations and verifies them simultaneously in each decoding step. By leveraging parallel processing, Medusa substantially reduces the number of decoding steps required. We present two levels of fine-tuning procedures for Medusa to meet the needs of different use cases: Medusa-1: Medusa is directly fine-tuned on top of a frozen backbone LLM, enabling lossless inference acceleration. Medusa-2: Medusa is fine-tuned together with the backbone LLM, enabling better prediction accuracy of Medusa heads and higher speedup but needing a special training recipe that preserves the backbone model's capabilities. Moreover, we propose several extensions that improve or expand the utility of Medusa, including a self-distillation to handle situations where no training data is available and a typical acceptance scheme to boost the acceptance rate while maintaining generation quality. We evaluate Medusa on models of various sizes and training procedures. Our experiments demonstrate that Medusa-1 can achieve over 2.2x speedup without compromising generation quality, while Medusa-2 further improves the speedup to 2.3-3.6x.

cs.LG↗