Researcher profile

Jiashu Zhao

Jiashu Zhao contributes to research discovery and scholarly infrastructure.

ResearcherAffiliation not importedOpen to collaborate

Information Retrieval Artificial Intelligence Computation and Language Computer Vision Distributed, Parallel, and Cluster Computing Machine Learning

Trust snapshot

Quick read

Trust 21 - EmergingVerification L1Unclaimed author

11works

0followers

6topics

4close collaborators

Actions

Decide how to stay connected

Follow researcher0

Claiming links this public author record to a researcher profile and unlocks direct collaboration workflows.

Direct collaboration

Open a focused conversation when the fit is right

Claim this author entity first to unlock direct invitations.

Inspect adjacent work, topics, institutions and collaborators without jumping out to a separate graph page.

Building this graph slice

BZPEER is loading the nearby papers, people, topics and institutions for this page.

preprint2026arXiv

Beyond Monolithic Architectures: A Multi-Agent Search and Knowledge Optimization Framework for Agentic Search

Agentic search has emerged as a promising paradigm for complex information seeking by enabling Large Language Models (LLMs) to interleave reasoning with tool use. However, prevailing systems rely on monolithic agents that suffer from structural bottlenecks, including unconstrained reasoning outputs that inflate trajectories, sparse outcome-level rewards that complicate credit assignment, and stochastic search noise that destabilizes learning. To address these challenges, we propose \textbf{M-ASK} (Multi-Agent Search and Knowledge), a framework that explicitly decouples agentic search into two complementary roles: Search Behavior Agents, which plan and execute search actions, and Knowledge Management Agents, which aggregate, filter, and maintain a compact internal context. This decomposition allows each agent to focus on a well-defined subtask and reduces interference between search and context construction. Furthermore, to enable stable coordination, M-ASK employs turn-level rewards to provide granular supervision for both search decisions and knowledge updates. Experiments on multi-hop QA benchmarks demonstrate that M-ASK outperforms strong baselines, achieving not only superior answer accuracy but also significantly more stable training dynamics.\footnote{The source code for M-ASK is available at https://github.com/chenyiqun/M-ASK.}

preprint2026arXiv

EndPrompt: Efficient Long-Context Extension via Terminal Anchoring

Extending the context window of large language models typically requires training on sequences at the target length, incurring quadratic memory and computational costs that make long-context adaptation expensive and difficult to reproduce. We propose EndPrompt, a method that achieves effective context extension using only short training sequences. The core insight is that exposing a model to long-range relative positional distances does not require constructing full-length inputs: we preserve the original short context as an intact first segment and append a brief terminal prompt as a second segment, assigning it positional indices near the target context length. This two-segment construction introduces both local and long-range relative distances within a short physical sequence while maintaining the semantic continuity of the training text--a property absent in chunk-based simulation approaches that split contiguous context. We provide a theoretical analysis grounded in Rotary Position Embedding and the Bernstein inequality, showing that position interpolation induces a rigorous smoothness constraint over the attention function, with shared Transformer parameters further suppressing unstable extrapolation to unobserved intermediate distances. Applied to LLaMA-family models extending the context window from 8K to 64K, EndPrompt achieves an average RULER score of 76.03 and the highest average on LongBench, surpassing LCEG (72.24), LongLoRA (72.95), and full-length fine-tuning (69.23) while requiring substantially less computation. These results demonstrate that long-context generalization can be induced from sparse positional supervision, challenging the prevailing assumption that dense long-sequence training is necessary for reliable context-window extension. The code is available at https://github.com/clx1415926/EndPrompt.

preprint2026arXiv

FlexSpec: Frozen Drafts Meet Evolving Targets in Edge-Cloud Collaborative LLM Speculative Decoding

Deploying large language models (LLMs) in mobile and edge computing environments is constrained by limited on-device resources, scarce wireless bandwidth, and frequent model evolution. Although edge-cloud collaborative inference with speculative decoding (SD) can reduce end-to-end latency by executing a lightweight draft model at the edge and verifying it with a cloud-side target model, existing frameworks fundamentally rely on tight coupling between the two models. Consequently, repeated model synchronization introduces excessive communication overhead, increasing end-to-end latency, and ultimately limiting the scalability of SD in edge environments. To address these limitations, we propose FlexSpec, a communication-efficient collaborative inference framework tailored for evolving edge-cloud systems. The core design of FlexSpec is a shared-backbone architecture that allows a single and static edge-side draft model to remain compatible with a large family of evolving cloud-side target models. By decoupling edge deployment from cloud-side model updates, FlexSpec eliminates the need for edge-side retraining or repeated model downloads, substantially reducing communication and maintenance costs. Furthermore, to accommodate time-varying wireless conditions and heterogeneous device constraints, we develop a channel-aware adaptive speculation mechanism that dynamically adjusts the speculative draft length based on real-time channel state information and device energy budgets. Extensive experiments demonstrate that FlexSpec achieves superior performance compared to conventional SD approaches in terms of inference efficiency.

preprint2026arXiv

Measuring Maximum Activations in Open Large Language Models

The dynamic range of activations is a first-order constraint for low-bit quantization, activation scaling, and stable LLM inference. Prior work characterized outlier features and massive activations on pre-2024 LLaMA-style models, and the downstream activation-quantization stack inherits that picture without revisiting it for the post-LLaMA open-model boom. We ask the deployment-oriented question: how large can activations get in modern open LLMs, and how does this magnitude vary across families, generations, and training stages? Under a unified pipeline (5,000-sample multi-domain corpus, family-specific tokenization, identical hooks across embeddings, hidden states, attention, MLP/MoE, SwiGLU gates, and final norm), we measure global and layerwise maxima on 27 checkpoints from 8 open families spanning dense, MoE, vision-language, intermediate-training, and instruction-tuned variants. We find that (i) global maxima span over nearly four orders of magnitude at comparable parameter counts, with Qwen3.5 and MoE checkpoints in the 10^2 to 10^3 range and Gemma3-27B-it reaching ~7 x 10^5; (ii) cross-family and cross-generation comparisons break simple monotonic scaling; and (iii) MoE checkpoints exhibit 14.0-23.4x lower peaks than matched-scale dense counterparts, while the residual stream carries the global maximum in 22/24 checkpoints. A lightweight INT-8 sanity check shows that measured maxima co-vary with low-bit reconstruction error via activation-scale selection. We conclude that maximum activation magnitude is a model property tied to family, architecture, and training stage - not a simple byproduct of size - and should be measured and reported alongside any open-weight release before low-bit deployment. The code is publicly available at https://github.com/clx1415926/Max_act_llm.

preprint2024arXiv

Text-Video Retrieval via Variational Multi-Modal Hypergraph Networks

Text-video retrieval is a challenging task that aims to identify relevant videos given textual queries. Compared to conventional textual retrieval, the main obstacle for text-video retrieval is the semantic gap between the textual nature of queries and the visual richness of video content. Previous works primarily focus on aligning the query and the video by finely aggregating word-frame matching signals. Inspired by the human cognitive process of modularly judging the relevance between text and video, the judgment needs high-order matching signal due to the consecutive and complex nature of video contents. In this paper, we propose chunk-level text-video matching, where the query chunks are extracted to describe a specific retrieval unit, and the video chunks are segmented into distinct clips from videos. We formulate the chunk-level matching as n-ary correlations modeling between words of the query and frames of the video and introduce a multi-modal hypergraph for n-ary correlation modeling. By representing textual units and video frames as nodes and using hyperedges to depict their relationships, a multi-modal hypergraph is constructed. In this way, the query and the video can be aligned in a high-order semantic space. In addition, to enhance the model's generalization ability, the extracted features are fed into a variational inference component for computation, obtaining the variational representation under the Gaussian distribution. The incorporation of hypergraphs and variational inference allows our model to capture complex, n-ary interactions among textual and visual contents. Experimental results demonstrate that our proposed method achieves state-of-the-art performance on the text-video retrieval task.

preprint2022arXiv

Contrastive Meta Learning with Behavior Multiplicity for Recommendation

A well-informed recommendation framework could not only help users identify their interested items, but also benefit the revenue of various online platforms (e.g., e-commerce, social media). Traditional recommendation models usually assume that only a single type of interaction exists between user and item, and fail to model the multiplex user-item relationships from multi-typed user behavior data, such as page view, add-to-favourite and purchase. While some recent studies propose to capture the dependencies across different types of behaviors, two important challenges have been less explored: i) Dealing with the sparse supervision signal under target behaviors (e.g., purchase). ii) Capturing the personalized multi-behavior patterns with customized dependency modeling. To tackle the above challenges, we devise a new model CML, Contrastive Meta Learning (CML), to maintain dedicated cross-type behavior dependency for different users. In particular, we propose a multi-behavior contrastive learning framework to distill transferable knowledge across different types of behaviors via the constructed contrastive loss. In addition, to capture the diverse multi-behavior patterns, we design a contrastive meta network to encode the customized behavior heterogeneity for different users. Extensive experiments on three real-world datasets indicate that our method consistently outperforms various state-of-the-art recommendation methods. Our empirical studies further suggest that the contrastive meta learning paradigm offers great potential for capturing the behavior multiplicity in recommendation. We release our model implementation at: https://github.com/weiwei1206/CML.git.

preprint2022arXiv

Factorized and Controllable Neural Re-Rendering of Outdoor Scene for Photo Extrapolation

Expanding an existing tourist photo from a partially captured scene to a full scene is one of the desired experiences for photography applications. Although photo extrapolation has been well studied, it is much more challenging to extrapolate a photo (i.e., selfie) from a narrow field of view to a wider one while maintaining a similar visual style. In this paper, we propose a factorized neural re-rendering model to produce photorealistic novel views from cluttered outdoor Internet photo collections, which enables the applications including controllable scene re-rendering, photo extrapolation and even extrapolated 3D photo generation. Specifically, we first develop a novel factorized re-rendering pipeline to handle the ambiguity in the decomposition of geometry, appearance and illumination. We also propose a composited training strategy to tackle the unexpected occlusion in Internet images. Moreover, to enhance photo-realism when extrapolating tourist photographs, we propose a novel realism augmentation process to complement appearance details, which automatically propagates the texture details from a narrow captured photo to the extrapolated neural rendered image. The experiments and photo editing examples on outdoor scenes demonstrate the superior performance of our proposed method in both photo-realism and downstream applications.

preprint2022arXiv

Gumble Softmax For User Behavior Modeling

Recently, sequential recommendation systems are important in solving the information overload in many online services. Current methods in sequential recommendation focus on learning a fixed number of representations for each user at any time, with a single representation or multi representations for the user. However, when a user is exploring items on an e-commerce recommendation system, the number of this user's hobbies may change overtime (e.g. increase/reduce one more interest), affected by the user's evolving self needs. Moreover, different users may have various number of interests. In this paper, we argue that it is meaningful to explore a personalized dynamic number of user interests, and learn a dynamic group of user interest representations accordingly. We propose a sequential model with dynamic number of representations for recommendation systems (RDRSR). Specifically, RDRSR is composed of a dynamic interest discriminator (DID) module and a dynamic interest allocator (DIA) module. The DID module explores the number of a user's interests by learning the overall sequential characteristics with bi-directional self-attention and Gumbel-Softmax. The DIA module make the historical clicked items into a group of item groups and constructs user's dynamic interest representation. Additionally, experiments on the real-world datasets demonstrates our model's effectiveness.

preprint2022arXiv

Hypergraph Contrastive Collaborative Filtering

Collaborative Filtering (CF) has emerged as fundamental paradigms for parameterizing users and items into latent representation space, with their correlative patterns from interaction data. Among various CF techniques, the development of GNN-based recommender systems, e.g., PinSage and LightGCN, has offered the state-of-the-art performance. However, two key challenges have not been well explored in existing solutions: i) The over-smoothing effect with deeper graph-based CF architecture, may cause the indistinguishable user representations and degradation of recommendation results. ii) The supervision signals (i.e., user-item interactions) are usually scarce and skewed distributed in reality, which limits the representation power of CF paradigms. To tackle these challenges, we propose a new self-supervised recommendation framework Hypergraph Contrastive Collaborative Filtering (HCCF) to jointly capture local and global collaborative relations with a hypergraph-enhanced cross-view contrastive learning architecture. In particular, the designed hypergraph structure learning enhances the discrimination ability of GNN-based CF paradigm, so as to comprehensively capture the complex high-order dependencies among users. Additionally, our HCCF model effectively integrates the hypergraph structure encoding with self-supervised learning to reinforce the representation quality of recommender systems, based on the hypergraph-enhanced self-discrimination. Extensive experiments on three benchmark datasets demonstrate the superiority of our model over various state-of-the-art recommendation methods, and the robustness against sparse user interaction data. Our model implementation codes are available at https://github.com/akaxlh/HCCF.

preprint2022arXiv

Sequential Recommendation with User Evolving Preference Decomposition

Modeling user sequential behaviors has recently attracted increasing attention in the recommendation domain. Existing methods mostly assume coherent preference in the same sequence. However, user personalities are volatile and easily changed, and there can be multiple mixed preferences underlying user behaviors. To solve this problem, in this paper, we propose a novel sequential recommender model via decomposing and modeling user independent preferences. To achieve this goal, we highlight three practical challenges considering the inconsistent, evolving and uneven nature of the user behavior, which are seldom noticed by the previous work. For overcoming these challenges in a unified framework, we introduce a reinforcement learning module to simulate the evolution of user preference. More specifically, the action aims to allocate each item into a sub-sequence or create a new one according to how the previous items are decomposed as well as the time interval between successive behaviors. The reward is associated with the final loss of the learning objective, aiming to generate sub-sequences which can better fit the training data. We conduct extensive experiments based on six real-world datasets across different domains. Compared with the state-of-the-art methods, empirical studies manifest that our model can on average improve the performance by about 8.21%, 10.08%, 10.32%, and 9.82% on the metrics of Precision, Recall, NDCG and MRR, respectively.

preprint2022arXiv

User behavior understanding in real world settings

How to extract meaningful information in user historical behavior plays a crucial role in recommendation. User behavior sequence often contains multiple conceptually distinct items that belong to different item groups and the number of the item groups is changing over time. It is necessary to learn a dynamic group of representations according the item groups in a user historical behavior. However, current works only learns a predefined and fixed number representations which includes single representation methods and multi representations methods from the user context that could lead to suboptimal recommendation quality. In this paper we propose a model that can automatically and adaptively generates a dynamic group of representations from the user behavior accordingly. To be specific, AutoRep is composed of an informative representation construct (IRC) module and a dynamic representations construct (DRC) module. The IRC module learns the overall sequential characteristics of user behavior with a bi-directional architecture transformer. The DRC module dynamically allocate the item in the user behavior into different item groups and form a dynamic group of representations in a differentiable method. Such design improves the model recommendation performance. We evaluate the proposed model on five benchmark datasets. The results show that AutoRep outperforms representative baselines. Further ablation study has been conducted to deepen our understandings of AutoRep, including the proposed module IRC and DRC.

Institution

Affiliation not imported yet

This author record came from a source that does not expose affiliation metadata. Once the author claims the profile or we enrich the record from another provider, this section will link to the concrete institution.

Topic footprint