Searcharxiv⌕ Search

arXiv subjects

Yuhan Liu

Publications and source records attributed to Yuhan Liu.

At least 91 records · Page 5Linked to original sources
arXiv2025

EVICPRESS: Joint KV-Cache Compression and Eviction for Efficient LLM Serving

Reusing KV cache is essential for high efficiency of Large Language Model (LLM) inference systems. With more LLM users, the KV cache footprint can easily exceed GPU memory capacity, so prior work has proposed to either evict KV cache to lower-tier storage devices, or compress KV cache so that more KV cache can be fit in the fast memory. However, prior work misses an important opportunity: jointly optimizing the eviction and compression decisions across all KV caches to minimize average generation latency without hurting quality. We propose EVICPRESS, a KV-cache management system that applies lossy compression and adaptive eviction to KV cache across multiple storage tiers. Specifically, for each KV cache of a context, EVICPRESS considers the effect of compression and eviction of the KV cache on the average generation quality and delay across all contexts as a whole. To achieve this, EVICPRESS proposes a unified utility function that quantifies the effect of quality and delay of the lossy compression or eviction. To this end, EVICPRESS's profiling module periodically updates the utility function scores on all possible eviction-compression configurations for all contexts and places KV caches using a fast heuristic to rearrange KV caches on all storage tiers, with the goal of maximizing the utility function scores on each storage tier. Compared to the baselines that evict KV cache or compress KV cache, EVICPRESS achieves higher KV-cache hit rates on fast devices, i.e., lower delay, while preserving high generation quality by applying conservative compression to contexts that are sensitive to compression errors. Evaluation on 12 datasets and 5 models demonstrates that EVICPRESS achieves up to 2.19x faster time-to-first-token (TTFT) at equivalent generation quality.

cs.OS↗
arXiv2025

Open Polymer Challenge: Post-Competition Report

Machine learning (ML) offers a powerful path toward discovering sustainable polymer materials, but progress has been limited by the lack of large, high-quality, and openly accessible polymer datasets. The Open Polymer Challenge (OPC) addresses this gap by releasing the first community-developed benchmark for polymer informatics, featuring a dataset with 10K polymers and 5 properties: thermal conductivity, radius of gyration, density, fractional free volume, and glass transition temperature. The challenge centers on multi-task polymer property prediction, a core step in virtual screening pipelines for materials discovery. Participants developed models under realistic constraints that include small data, label imbalance, and heterogeneous simulation sources, using techniques such as feature-based augmentation, transfer learning, self-supervised pretraining, and targeted ensemble strategies. The competition also revealed important lessons about data preparation, distribution shifts, and cross-group simulation consistency, informing best practices for future large-scale polymer datasets. The resulting models, analysis, and released data create a new foundation for molecular AI in polymer science and are expected to accelerate the development of sustainable and energy-efficient materials. Along with the competition, we release the test dataset at https://www.kaggle.com/datasets/alexliu99/neurips-open-polymer-prediction-2025-test-data. We also release the data generation pipeline at https://github.com/sobinalosious/ADEPT, which simulates more than 25 properties, including thermal conductivity, radius of gyration, and density.

cs.LG↗
arXiv2025

LMCache: An Efficient KV Cache Layer for Enterprise-Scale LLM Inference

KV cache has traditionally been stored in GPU memory to accelerate the decoding phase of large language model (LLM) inference. However, it is increasingly necessary to move KV caches outside GPU devices, to enable cache reuse across different queries and inference engines. Our real-world usage statistics confirm this trend: over time, the total KV cache stored by users has grown rapidly, far exceeding the capacity of GPU memory. Despite this need, there lacks an efficient solution for offloading and transferring KV caches. We present LMCACHE, the first and so far the most efficient open-source KV caching solution, which extracts and stores KV caches generated by modern LLM engines (vLLM and SGLang) out of the GPU memory and shares them across engines and queries. LMCACHE supports both cache offloading (prefix reuse across queries) and prefill-decode (PD) disaggregation (cross-engine/GPU cache transfer). LMCACHE's high performance and wide adoption stem from the following contributions: (1) highly optimized KV cache data movement powered by batched data movement operations, compute and I/O pipelining; (2) a modular KV cache connector component, decoupling LMCACHE from the rapid evolution of inference engines; (3) a first-class control API for flexible cache orchestration across GPU, CPU, storage, and network layers. Our evaluation shows that combining LMCACHE with vLLM achieves up to 15x improvement in throughput across workloads such as multi-round question answering and document analysis. Large-scale adoption of LMCACHE in enterprise settings provides us valuable insights, for example, fetching KV cache from remote storage has unsurprisingly benefits to prefill delay, and that context truncation, which is a widely applied technique in industry, can greatly reduce prefix cache hit ratio by half. The source code of LMCACHE is at: https://github.com/LMCache/LMCache.

cs.LG↗
arXiv2025

Shadow Tomography Against Adversaries

We study single-copy shadow tomography in the adversarial robust setting, where the goal is to learn the expectation values of $M$ observables $O_1, \ldots, O_M$ with $\varepsilon$ accuracy, but $γ$-fraction of the outcomes can be arbitrarily corrupted by an adversary. We show that all non-adaptive shadow tomography algorithms must incur an error of $\varepsilon=\tildeΩ(γ\min\{\sqrt{M}, \sqrt{d}\})$ for some choice of observables, even with unlimited copies. Unfortunately, the classical shadows algorithm by [HKP20] and naive algorithms that directly measure each observable suffer even more. We design an algorithm that achieves an error of $\varepsilon=\tilde{O}(γ\max_{i\in[M]}\|O_i\|_{HS})$, which nearly matches our worst-case error lower bound for $M\ge d$ and guarantees better accuracy when the observables have stronger structure. Remarkably, the algorithm only needs $n=\frac{1}{γ^2}\log(M/δ)$ copies to achieve that error with probability at least $1-δ$, matching the sample complexity of the classical shadows algorithm that achieves the same error without corrupted measurement outcomes. Our algorithm is conceptually simple and easy to implement. Classical simulation for fidelity estimation shows that our algorithm enjoys much stronger robustness than [HKP20] under adversarial noise. Finally, based on a reduction from full-state tomography to shadow tomography, we prove that for rank $r$ states, both the near-optimal asymptotic error of $\varepsilon=\tilde{O}(γ\sqrt{r})$ and copy complexity $\tilde{O}(dr^2/\varepsilon^2)=\tilde{O}(dr/γ^2)$ can be achieved for adversarially robust state tomography, closing the large gap in [ABCL25] where optimal error can only be achieved using pseudo-polynomial number of copies in $d$.

quant-ph↗
arXiv2025

Colin: A Multimodal Human-AI Co-Creation Storytelling System To Support Children's Multi-Level Narrative Skills

Children develop narrative skills by understanding and actively building connections between elements, image text matching, and consequences. However, it is challenging for children to clearly grasp these multi level links only through explanations of text or the facilitator's speech. To address this, we developed Colin, an interactive storytelling tool that supports children's multi level narrative skills through both voice and visual modalities. In the generation stage, Colin supports the facilitator to define and review the generated text and image content freely. In the understanding stage, a question feedback model helps children understand multi level connections while co creating stories with Colin. In the building phase, Colin actively encourages children to create connections between elements through drawing and speaking. A user study with 20 participants evaluated Colin by measuring children's engagement, understanding of cause and effect relationships, and the quality of their new story creations. Our results demonstrate that Colin significantly enhances the development of children's narrative skills across multiple levels.

cs.HC↗
arXiv2025

Conditional Information Bottleneck for Multimodal Fusion: Overcoming Shortcut Learning in Sarcasm Detection

Multimodal sarcasm detection is a complex task that requires distinguishing subtle complementary signals across modalities while filtering out irrelevant information. Many advanced methods rely on learning shortcuts from datasets rather than extracting intended sarcasm-related features. However, our experiments show that shortcut learning impairs the model's generalization in real-world scenarios. Furthermore, we reveal the weaknesses of current modality fusion strategies for multimodal sarcasm detection through systematic experiments, highlighting the necessity of focusing on effective modality fusion for complex emotion recognition. To address these challenges, we construct MUStARD++$^{R}$ by removing shortcut signals from MUStARD++. Then, a Multimodal Conditional Information Bottleneck (MCIB) model is introduced to enable efficient multimodal fusion for sarcasm detection. Experimental results show that the MCIB achieves the best performance without relying on shortcut learning.

cs.LG↗
arXiv2025

Revisiting Federated Fine-Tuning: A Single Communication Round is Enough for Foundation Models

The recent advancement of foundation models (FMs) has increased the demand for fine-tuning these models on large-scale cross-domain datasets. To address this, federated fine-tuning has emerged, allowing FMs to be fine-tuned on distributed datasets across multiple devices while ensuring data privacy. However, the substantial parameter size and the multi-round communication in federated learning algorithms result in prohibitively high communication costs, challenging the practicality of federated fine-tuning. In this paper, we identify and analyze, both theoretically and empirically, that the traditional multi-round aggregation algorithms may not be necessary for federated fine-tuning large FMs. Our experiments reveal that a single round of aggregation (i.e., one-shot federated fine-tuning) yields a global model performance comparable to that achieved through multiple rounds of aggregation. Through rigorous mathematical and empirical analyses, we demonstrate that large FMs, due to their extensive parameter sizes and pre-training on general tasks, achieve significantly lower training loss in one-shot federated fine-tuning compared to smaller models. Our extensive experiments show that one-shot federated fine-tuning significantly reduces communication costs. It also has the potential to enable asynchronous aggregation, enhances privacy, and maintains performance consistency with multi-round federated fine-tuning on both text generation and text-to-image generation tasks. Our findings provide insights to revolutionize federated fine-tuning in practice, enhancing efficiency, reducing costs, and expanding accessibility for FMs.

cs.LG↗
arXiv2025

EmoDebt: Bayesian-Optimized Emotional Intelligence for Strategic Agent-to-Agent Debt Recovery

The emergence of autonomous Large Language Model (LLM) agents has created a new ecosystem of strategic, agent-to-agent interactions. However, a critical challenge remains unaddressed: in high-stakes, emotion-sensitive domains like debt collection, LLM agents pre-trained on human dialogue are vulnerable to exploitation by adversarial counterparts who simulate negative emotions to derail negotiations. To fill this gap, we first contribute a novel dataset of simulated debt recovery scenarios and a multi-agent simulation framework. Within this framework, we introduce EmoDebt, an LLM agent architected for robust performance. Its core innovation is a Bayesian-optimized emotional intelligence engine that reframes a model's ability to express emotion in negotiation as a sequential decision-making problem. Through online learning, this engine continuously tunes EmoDebt's emotional transition policies, discovering optimal counter-strategies against specific debtor tactics. Extensive experiments on our proposed benchmark demonstrate that EmoDebt achieves significant strategic robustness, substantially outperforming non-adaptive and emotion-agnostic baselines across key performance metrics, including success rate and operational efficiency. By introducing both a critical benchmark and a robustly adaptive agent, this work establishes a new foundation for deploying strategically robust LLM agents in adversarial, emotion-sensitive debt interactions. The code is available at \textcolor{blue}{https://github.com/Yunbo-max/EmoDebt}.

cs.CL↗
arXiv2025

ViPER: Empowering the Self-Evolution of Visual Perception Abilities in Vision-Language Model

The limited capacity for fine-grained visual perception presents a critical bottleneck for Vision-Language Models (VLMs) in real-world applications. Addressing this is challenging due to the scarcity of high-quality data and the limitations of existing methods: supervised fine-tuning (SFT) often compromises general capabilities, while reinforcement fine-tuning (RFT) prioritizes textual reasoning over visual perception. To bridge this gap, we propose a novel two-stage task that structures visual perception learning as a coarse-to-fine progressive process. Based on this task formulation, we develop ViPER, a self-bootstrapping framework specifically designed to enable iterative evolution through self-critiquing and self-prediction. By synergistically integrating image-level and instance-level reconstruction with a two-stage reinforcement learning strategy, ViPER establishes a closed-loop training paradigm, where internally synthesized data directly fuel the enhancement of perceptual ability. Applied to the Qwen2.5-VL family, ViPER produces the Qwen-Viper series. With an average gain of 1.7% on seven comprehensive benchmarks spanning various tasks and up to 6.0% on fine-grained perception, Qwen-Viper consistently demonstrates superior performance across different vision-language scenarios while maintaining generalizability. Beyond enabling self-improvement in perceptual capabilities, ViPER provides concrete evidence for the reciprocal relationship between generation and understanding, a breakthrough to developing more autonomous and capable VLMs.

cs.CV↗
arXiv2025

Parent Lindbladians for Matrix Product Density Operators

Understanding quantum phases of matter is a fundamental goal in physics. For pure states, the representatives of phases are the ground states of locally interacting Hamiltonians, which are also renormalization fixed points (RFPs). These RFP states are exactly described by tensor networks. Extending this framework to mixed states, matrix product density operators (MPDOs) which are RFPs are believed to encapsulate mixed-state phases of matter in one dimension, where non-trivial topological phases have already been shown to exist. However, to better motivate the physical relevance of those states, and in particular the physical relevance of the recently found non-trivial phases, it remains an open question whether such MPDO RFPs can be realized as steady states of local Lindbladians. In this work, we resolve this question by analytically constructing parent Lindbladians for MPDO RFPs. These Lindbladians are local, frustration-free, and exhibit minimal steady-state degeneracy. Interestingly, we find that parent Lindbladians possess a rich structure that distinguishes them from their Hamiltonian counterparts. In particular, we uncover an intriguing connection between the non-commutativity of the Lindbladian terms and the fact that the corresponding MPDO RFP belongs to a non-trivial phase.

quant-ph↗
arXiv2025

When to Reason: Semantic Router for vLLM

Large Language Models (LLMs) demonstrate substantial accuracy gains when augmented with reasoning modes such as chain-of-thought and inference-time scaling. However, reasoning also incurs significant costs in inference latency and token usage, with environmental and financial impacts, which are unnecessary for many simple prompts. We present a semantic router that classifies queries based on their reasoning requirements and selectively applies reasoning only when beneficial. Our approach achieves a 10.2 percentage point improvement in accuracy on the MMLU-Pro benchmark while reducing response latency by 47.1% and token consumption by 48.5% compared to direct inference with vLLM. These results demonstrate that semantic routing offers an effective mechanism for striking a balance between accuracy and efficiency in open-source LLM serving systems

cs.ET↗
arXiv2025

Motion Blender Gaussian Splatting for Dynamic Scene Reconstruction

Gaussian splatting has emerged as a powerful tool for high-fidelity reconstruction of dynamic scenes. However, existing methods primarily rely on implicit motion representations, such as encoding motions into neural networks or per-Gaussian parameters, which makes it difficult to further manipulate the reconstructed motions. This lack of explicit controllability limits existing methods to replaying recorded motions only, which hinders a wider application in robotics. To address this, we propose Motion Blender Gaussian Splatting (MBGS), a novel framework that uses motion graphs as an explicit and sparse motion representation. The motion of a graph's links is propagated to individual Gaussians via dual quaternion skinning, with learnable weight painting functions that determine the influence of each link. The motion graphs and 3D Gaussians are jointly optimized from input videos via differentiable rendering. Experiments show that MBGS achieves state-of-the-art performance on the highly challenging iPhone dataset while being competitive on HyperNeRF. We demonstrate the application potential of our method in animating novel object poses, synthesizing real robot demonstrations, and predicting robot actions through visual planning. The source code, models, video demonstrations can be found at http://mlzxy.github.io/motion-blender-gs.

cs.CV↗
arXiv2025

User Feedback in Human-LLM Dialogues: A Lens to Understand Users But Noisy as a Learning Signal

Once language models (LMs) are deployed, they can interact with users long-term, ideally evolving based on their feedback. Asking for direct user feedback can be disruptive; thus, we study harvesting implicit user feedback from user-LM interaction logs. We study two user-LM interaction datasets (WildChat and LMSYS). First, we analyze user feedback in the user-LLM conversation logs, providing insights into when and why such feedback occurs. Second, we study harvesting learning signals from such implicit user feedback. Specifically, we study whether incorporating the contents of user feedback (e.g., user wanted clarification), in addition to the polarity of the feedback, can improve the model performance. We observe mixed results, showing this helps in short human-designed questions (MTBench) but not on longer and more complex questions (WildBench). Together, we provide an in-depth study of implicit user feedback, showing its potential and limitations.

cs.CL↗
arXiv2025

Beyond Static Testbeds: An Interaction-Centric Agent Simulation Platform for Dynamic Recommender Systems

Evaluating and iterating upon recommender systems is crucial, yet traditional A/B testing is resource-intensive, and offline methods struggle with dynamic user-platform interactions. While agent-based simulation is promising, existing platforms often lack a mechanism for user actions to dynamically reshape the environment. To bridge this gap, we introduce RecInter, a novel agent-based simulation platform for recommender systems featuring a robust interaction mechanism. In RecInter platform, simulated user actions (e.g., likes, reviews, purchases) dynamically update item attributes in real-time, and introduced Merchant Agents can reply, fostering a more realistic and evolving ecosystem. High-fidelity simulation is ensured through Multidimensional User Profiling module, Advanced Agent Architecture, and LLM fine-tuned on Chain-of-Thought (CoT) enriched interaction data. Our platform achieves significantly improved simulation credibility and successfully replicates emergent phenomena like Brand Loyalty and the Matthew Effect. Experiments demonstrate that this interaction mechanism is pivotal for simulating realistic system evolution, establishing our platform as a credible testbed for recommender systems research. Our codes are available at https://github.com/jinsong8/RecInter.

cs.CL↗
arXiv2025

ShadowServe: Interference-Free KV Cache Fetching for Distributed Prefix Caching

Distributed prefix caching accelerates long-context LLM serving by reusing KV cache entries for common context prefixes. However, KV cache fetches can become a bottleneck when network bandwidth is limited. Compression mitigates the bandwidth issue, but can degrade overall performance when decompression interferes with model computation. We present ShadowServe, the first SmartNIC-accelerated, interference-free prefix caching system for LLM serving. ShadowServe separates a control plane on the host and a data plane fully offloaded to the SmartNIC, which eliminates interference to both host GPU and CPU. To overcome the SmartNIC's limited compute and memory resources, we design a chunked pipeline that parallelizes data plane operations across the SmartNIC's compute resources, and a minimal-copy memory management scheme that reduces memory pressure on the SmartNIC. Compared to state-of-the-art solutions, ShadowServe achieves up to 2.2x lower loaded time-per-output-token (TPOT), and reduces time-to-first-token (TTFT) by up to 1.38x in low-bandwidth scenarios (<= 20 Gbps), translating to up to 1.35x higher throughput.

cs.DC↗
arXiv2025

Trustless Autonomy: Understanding Motivations, Benefits, and Governance Dilemmas in Self-Sovereign Decentralized AI Agents

The recent trend of self-sovereign Decentralized AI Agents (DeAgents) combines Large Language Model (LLM)-based AI agents with decentralization technologies such as blockchain smart contracts and trusted execution environments (TEEs). These tamper-resistant trustless substrates allow agents to achieve self-sovereignty through ownership of cryptowallet private keys and control of digital assets and social media accounts. DeAgents eliminate centralized control and reduce human intervention, addressing key trust concerns inherent in centralized AI systems. This contributes to social computing by enabling new human cooperative paradigm "intelligence as commons." However, given ongoing challenges in LLM reliability such as hallucinations, this creates paradoxical tension between trustlessness and unreliable autonomy. This study addresses this empirical research gap through interviews with DeAgents stakeholders-experts, founders, and developers-to examine their motivations, benefits, and governance dilemmas. The findings will guide future DeAgents system and protocol design and inform discussions about governance in sociotechnical AI systems in the future agentic web.

cs.HC↗
arXiv2025

MMoE: Robust Spoiler Detection with Multi-modal Information and Domain-aware Mixture-of-Experts

Online movie review websites are valuable for information and discussion about movies. However, the massive spoiler reviews detract from the movie-watching experience, making spoiler detection an important task. Previous methods simply focus on reviews' text content, ignoring the heterogeneity of information in the platform. For instance, the metadata and the corresponding user's information of a review could be helpful. Besides, the spoiler language of movie reviews tends to be genre-specific, thus posing a domain generalization challenge for existing methods. To this end, we propose MMoE, a multi-modal network that utilizes information from multiple modalities to facilitate robust spoiler detection and adopts Mixture-of-Experts to enhance domain generalization. MMoE first extracts graph, text, and meta feature from the user-movie network, the review's textual content, and the review's metadata respectively. To handle genre-specific spoilers, we then adopt Mixture-of-Experts architecture to process information in three modalities to promote robustness. Finally, we use an expert fusion layer to integrate the features from different perspectives and make predictions based on the fused embedding. Experiments demonstrate that MMoE achieves state-of-the-art performance on two widely-used spoiler detection datasets, surpassing previous SOTA methods by 2.56% and 8.41% in terms of accuracy and F1-score. Further experiments also demonstrate MMoE's superiority in robustness and generalization. Our code is available at https://github.com/zzqbjt/Spoiler-Detection.

cs.AI↗