arXiv subjects

Tianlong Chen

Publications and source records attributed to Tianlong Chen.

At least 127 records · Page 7Linked to original sources

arXiv2025

DOGe: Defensive Output Generation for LLM Protection Against Knowledge Distillation

Large Language Models (LLMs) represent substantial intellectual and economic investments, yet their effectiveness can inadvertently facilitate model imitation via knowledge distillation (KD). In practical scenarios, competitors can distill proprietary LLM capabilities by simply observing publicly accessible outputs, akin to reverse-engineering a complex performance by observation alone. Existing protective methods like watermarking only identify imitation post-hoc, while other defenses assume the student model mimics the teacher's internal logits, rendering them ineffective against distillation purely from observed output text. This paper confronts the challenge of actively protecting LLMs within the realistic constraints of API-based access. We introduce an effective and efficient Defensive Output Generation (DOGe) strategy that subtly modifies the output behavior of an LLM. Its outputs are accurate and useful for legitimate users, yet are designed to be misleading for distillation, significantly undermining imitation attempts. We achieve this by fine-tuning only the final linear layer of the teacher LLM with an adversarial loss. This targeted training approach anticipates and disrupts distillation attempts during inference time. Our experiments show that, while preserving the performance of the teacher model, student models distilled from the defensively generated outputs demonstrate catastrophically reduced performance, demonstrating DOGe as a practical safeguard against KD-based model imitation.

cs.LG↗

arXiv2025

Leave It to the Experts: Detecting Knowledge Distillation via MoE Expert Signatures

Knowledge Distillation (KD) accelerates training of large language models (LLMs) but poses intellectual property protection and LLM diversity risks. Existing KD detection methods based on self-identity or output similarity can be easily evaded through prompt engineering. We present a KD detection framework effective in both white-box and black-box settings by exploiting an overlooked signal: the transfer of MoE "structural habits", especially internal routing patterns. Our approach analyzes how different experts specialize and collaborate across various inputs, creating distinctive fingerprints that persist through the distillation process. To extend beyond the white-box setup and MoE architectures, we further propose Shadow-MoE, a black-box method that constructs proxy MoE representations via auxiliary distillation to compare these patterns between arbitrary model pairs. We establish a comprehensive, reproducible benchmark that offers diverse distilled checkpoints and an extensible framework to facilitate future research. Extensive experiments demonstrate >94% detection accuracy across various scenarios and strong robustness to prompt-based evasion, outperforming existing baselines while highlighting the structural habits transfer in LLMs.

cs.LG↗

arXiv2025

Mapping from Meaning: Addressing the Miscalibration of Prompt-Sensitive Language Models

An interesting behavior in large language models (LLMs) is prompt sensitivity. When provided with different but semantically equivalent versions of the same prompt, models may produce very different distributions of answers. This suggests that the uncertainty reflected in a model's output distribution for one prompt may not reflect the model's uncertainty about the meaning of the prompt. We model prompt sensitivity as a type of generalization error, and show that sampling across the semantic ``concept space'' with paraphrasing perturbations improves uncertainty calibration without compromising accuracy. Additionally, we introduce a new metric for uncertainty decomposition in black-box LLMs that improves upon entropy-based decomposition by modeling semantic continuities in natural language generation. We show that this decomposition metric can be used to quantify how much LLM uncertainty is attributed to prompt sensitivity. Our work introduces a new way to improve uncertainty calibration in prompt-sensitive language models, and provides evidence that some LLMs fail to exhibit consistent general reasoning about the meanings of their inputs.

cs.CL↗

arXiv2025

SARHAchat: An LLM-Based Chatbot for Sexual and Reproductive Health Counseling

While Artificial Intelligence (AI) shows promise in healthcare applications, existing conversational systems often falter in complex and sensitive medical domains such as Sexual and Reproductive Health (SRH). These systems frequently struggle with hallucination and lack the specialized knowledge required, particularly for sensitive SRH topics. Furthermore, current AI approaches in healthcare tend to prioritize diagnostic capabilities over comprehensive patient care and education. Addressing these gaps, this work at the UNC School of Nursing introduces SARHAchat, a proof-of-concept Large Language Model (LLM)-based chatbot. SARHAchat is designed as a reliable, user-centered system integrating medical expertise with empathetic communication to enhance SRH care delivery. Our evaluation demonstrates SARHAchat's ability to provide accurate and contextually appropriate contraceptive counseling while maintaining a natural conversational flow. The demo is available at https://sarhachat.com/}{https://sarhachat.com/.

cs.CY↗

arXiv2025

Enabling Few-Shot Alzheimer's Disease Diagnosis on Biomarker Data with Tabular LLMs

Early and accurate diagnosis of Alzheimer's disease (AD), a complex neurodegenerative disorder, requires analysis of heterogeneous biomarkers (e.g., neuroimaging, genetic risk factors, cognitive tests, and cerebrospinal fluid proteins) typically represented in a tabular format. With flexible few-shot reasoning, multimodal integration, and natural-language-based interpretability, large language models (LLMs) offer unprecedented opportunities for prediction with structured biomedical data. We propose a novel framework called TAP-GPT, Tabular Alzheimer's Prediction GPT, that adapts TableGPT2, a multimodal tabular-specialized LLM originally developed for business intelligence tasks, for AD diagnosis using structured biomarker data with small sample sizes. Our approach constructs few-shot tabular prompts using in-context learning examples from structured biomedical data and finetunes TableGPT2 using the parameter-efficient qLoRA adaption for a clinical binary classification task of AD or cognitively normal (CN). The TAP-GPT framework harnesses the powerful tabular understanding ability of TableGPT2 and the encoded prior knowledge of LLMs to outperform more advanced general-purpose LLMs and a tabular foundation model (TFM) developed for prediction tasks. To our knowledge, this is the first application of LLMs to the prediction task using tabular biomarker data, paving the way for future LLM-driven multi-agent frameworks in biomedical informatics.

cs.CL↗

arXiv2025

Multi-Agent Debate for LLM Judges with Adaptive Stability Detection

With advancements in reasoning capabilities, Large Language Models (LLMs) are increasingly employed for automated judgment tasks. While LLMs-as-Judges offer promise in automating evaluations, current approaches often rely on simplistic aggregation methods (e.g., majority voting), which can fail even when individual agents provide correct answers. To address this, we propose a multi-agent debate judge framework where agents collaboratively reason and iteratively refine their responses. We formalize the debate process mathematically, analyzing agent interactions and proving that debate amplifies correctness compared to static ensembles. To enhance efficiency, we introduce a stability detection mechanism that models judge consensus dynamics via a time-varying Beta-Binomial mixture, with adaptive stopping based on distributional similarity (Kolmogorov-Smirnov test). This mechanism models the judges' collective correct rate dynamics using a time-varying mixture of Beta-Binomial distributions and employs an adaptive stopping criterion based on distributional similarity (Kolmogorov-Smirnov statistic). Experiments across multiple benchmarks and models demonstrate that our framework improves judgment accuracy over majority voting while maintaining computational efficiency.

cs.AI↗

arXiv2025

Can GRPO Help LLMs Transcend Their Pretraining Origin?

Reinforcement Learning with Verifiable Rewards (RLVR), primarily driven by the Group Relative Policy Optimization (GRPO) algorithm, is a leading approach for enhancing the reasoning abilities of Large Language Models (LLMs). Despite its wide adoption, GRPO's gains are often inconsistent; for instance, a model may show significant improvement in one reasoning domain, like mathematics, yet remain stagnant in another, such as medicine. This inconsistency raises a critical question: under what conditions does GRPO improve reasoning and generalize out-of-distribution (OOD)? We investigate this from a data distribution perspective. We first prove theoretically that GRPO is a conservative reweighting scheme, bounded by the base model's distribution and thus unable to discover completely novel solutions. We further validate this in carefully designed controlled studies by training transformers from scratch, evaluating generalization across reasoning depth, input length, token representation, and compositionality. Our results provide a principled explanation for GRPO's boundaries: OOD improvement emerges only when the target task aligns with the model's pretrained biases, while gains on in-distribution (ID) tasks diminish as performance saturates. This reframes GRPO not as a universal reasoning enhancer but as a tool that sharpens pretraining biases. Our findings motivate future development of algorithms that can expand a model's capabilities beyond its pretraining origin.

cs.LG↗

arXiv2025

One Token Embedding Is Enough to Deadlock Your Large Reasoning Model

Modern large reasoning models (LRMs) exhibit impressive multi-step problem-solving via chain-of-thought (CoT) reasoning. However, this iterative thinking mechanism introduces a new vulnerability surface. We present the Deadlock Attack, a resource exhaustion method that hijacks an LRM's generative control flow by training a malicious adversarial embedding to induce perpetual reasoning loops. Specifically, the optimized embedding encourages transitional tokens (e.g., "Wait", "But") after reasoning steps, preventing the model from concluding its answer. A key challenge we identify is the continuous-to-discrete projection gap: naïve projections of adversarial embeddings to token sequences nullify the attack. To overcome this, we introduce a backdoor implantation strategy, enabling reliable activation through specific trigger tokens. Our method achieves a 100% attack success rate across four advanced LRMs (Phi-RM, Nemotron-Nano, R1-Qwen, R1-Llama) and three math reasoning benchmarks, forcing models to generate up to their maximum token limits. The attack is also stealthy (in terms of causing negligible utility loss on benign user inputs) and remains robust against existing strategies trying to mitigate the overthinking issue. Our findings expose a critical and underexplored security vulnerability in LRMs from the perspective of reasoning (in)efficiency.

cs.LG↗

arXiv2025

EditCast3D: Single-Frame-Guided 3D Editing with Video Propagation and View Selection

Recent advances in foundation models have driven remarkable progress in image editing, yet their extension to 3D editing remains underexplored. A natural approach is to replace the image editing modules in existing workflows with foundation models. However, their heavy computational demands and the restrictions and costs of closed-source APIs make plugging these models into existing iterative editing strategies impractical. To address this limitation, we propose EditCast3D, a pipeline that employs video generation foundation models to propagate edits from a single first frame across the entire dataset prior to reconstruction. While editing propagation enables dataset-level editing via video models, its consistency remains suboptimal for 3D reconstruction, where multi-view alignment is essential. To overcome this, EditCast3D introduces a view selection strategy that explicitly identifies consistent and reconstruction-friendly views and adopts feedforward reconstruction without requiring costly refinement. In combination, the pipeline both minimizes reliance on expensive image editing and mitigates prompt ambiguities that arise when applying foundation models independently across images. We evaluate EditCast3D on commonly used 3D editing datasets and compare it against state-of-the-art 3D editing baselines, demonstrating superior editing quality and high efficiency. These results establish EditCast3D as a scalable and general paradigm for integrating foundation models into 3D editing pipelines. The code is available at https://github.com/UNITES-Lab/EditCast3D

cs.CV↗

arXiv2025

Task-Aware Resolution Optimization for Visual Large Language Models

Real-world vision-language applications demand varying levels of perceptual granularity. However, most existing visual large language models (VLLMs), such as LLaVA, pre-assume a fixed resolution for downstream tasks, which leads to subpar performance. To address this problem, we first conduct a comprehensive and pioneering investigation into the resolution preferences of different vision-language tasks, revealing a correlation between resolution preferences with image complexity, and uncertainty variance of the VLLM at different image input resolutions. Building on this insight, we propose an empirical formula to determine the optimal resolution for a given vision-language task, combining these two factors. Second, based on rigorous experiments, we propose a novel parameter-efficient fine-tuning technique to extend the visual input resolution of pre-trained VLLMs to the identified optimal resolution. Extensive experiments on various vision-language tasks validate the effectiveness of our method.

cs.CV↗

arXiv2025

RTGS: Real-Time 3D Gaussian Splatting SLAM via Multi-Level Redundancy Reduction

3D Gaussian Splatting (3DGS) based Simultaneous Localization and Mapping (SLAM) systems can largely benefit from 3DGS's state-of-the-art rendering efficiency and accuracy, but have not yet been adopted in resource-constrained edge devices due to insufficient speed. Addressing this, we identify notable redundancies across the SLAM pipeline for acceleration. While conceptually straightforward, practical approaches are required to minimize the overhead associated with identifying and eliminating these redundancies. In response, we propose RTGS, an algorithm-hardware co-design framework that comprehensively reduces the redundancies for real-time 3DGS-SLAM on edge. To minimize the overhead, RTGS fully leverages the characteristics of the 3DGS-SLAM pipeline. On the algorithm side, we introduce (1) an adaptive Gaussian pruning step to remove the redundant Gaussians by reusing gradients computed during backpropagation; and (2) a dynamic downsampling technique that directly reuses the keyframe identification and alpha computing steps to eliminate redundant pixels. On the hardware side, we propose (1) a subtile-level streaming strategy and a pixel-level pairwise scheduling strategy that mitigates workload imbalance via a Workload Scheduling Unit (WSU) guided by previous iteration information; (2) a Rendering and Backpropagation (R&B) Buffer that accelerates the rendering backpropagation by reusing intermediate data computed during rendering; and (3) a Gradient Merging Unit (GMU) to reduce intensive memory accesses caused by atomic operations while enabling pipelined aggregation. Integrated into an edge GPU, RTGS achieves real-time performance (>= 30 FPS) on four datasets and three algorithms, with up to 82.5x energy efficiency over the baseline and negligible quality loss. Code is available at https://github.com/UMN-ZhaoLab/RTGS.

cs.AR↗

arXiv2025

$\textit{Agents Under Siege}$: Breaking Pragmatic Multi-Agent LLM Systems with Optimized Prompt Attacks

Most discussions about Large Language Model (LLM) safety have focused on single-agent settings but multi-agent LLM systems now create novel adversarial risks because their behavior depends on communication between agents and decentralized reasoning. In this work, we innovatively focus on attacking pragmatic systems that have constrains such as limited token bandwidth, latency between message delivery, and defense mechanisms. We design a $\textit{permutation-invariant adversarial attack}$ that optimizes prompt distribution across latency and bandwidth-constraint network topologies to bypass distributed safety mechanisms within the system. Formulating the attack path as a problem of $\textit{maximum-flow minimum-cost}$, coupled with the novel $\textit{Permutation-Invariant Evasion Loss (PIEL)}$, we leverage graph-based optimization to maximize attack success rate while minimizing detection risk. Evaluating across models including $\texttt{Llama}$, $\texttt{Mistral}$, $\texttt{Gemma}$, $\texttt{DeepSeek}$ and other variants on various datasets like $\texttt{JailBreakBench}$ and $\texttt{AdversarialBench}$, our method outperforms conventional attacks by up to $7\times$, exposing critical vulnerabilities in multi-agent systems. Moreover, we demonstrate that existing defenses, including variants of $\texttt{Llama-Guard}$ and $\texttt{PromptGuard}$, fail to prohibit our attack, emphasizing the urgent need for multi-agent specific safety mechanisms.

cs.MA↗

arXiv2025

AsyncSpade: Efficient Test-Time Scaling with Asynchronous Sparse Decoding

Test-time scaling (TTS) boosts LLM reasoning via long chain-of-thought (CoT), but the linear KV-cache growth amplifies the memory-bound bottleneck of LLM decoding. Query-aware page-level sparse decoding can achieve state-of-the-art performance under constrained FLOPs budgets, but is limited by both sequential-dependent page filtering and coarse-grained token selection, hampering serving efficiency and model performance on TTS tasks under high concurrency and long CoT scenarios (consuming even higher runtime than the forward pipeline itself). In this paper, we first find that the current-step query state can be accurately approximated in a unified manner from a short window of recent queries, enabling training-free query-aware sparsity without waiting in the decoding loop. We propose AsyncSpade, an asynchronous framework for efficient TTS built on two core components: (1) a novel light-weight temporal-regressive module that predicts the next-token query state; (2) an asynchronous and disaggregated framework that decouples the KV cache filtering from the auto-regressive decoding loop, overlapping the token-level KV selection with the forward inference computation through asynchronism. To our knowledge, AsyncSpade is the first to eliminate the sequential dependence without sacrificing model performance. We validate the effectiveness of AsyncSpade on common LLM serving setups with an A100 node, where AsyncSpade fully overlaps KV-cache operations with the inference pipeline, achieving theoretical optimal time-per-output-token (TPOT). Specifically, AsyncSpade delivers over 20% reduction on TPOT compared to SoTA baseline (i.e. Quest) and at least 50% TPOT reduction compared to full attention on Qwen3-8B and Qwen3-32B models, while matching or surpassing their accuracy on various TTS benchmarks (AIME-24/25, GPQA-Diamond, MATH-500).

cs.CL↗

arXiv2025

GEM: 3D Gaussian Splatting for Efficient and Accurate Cryo-EM Reconstruction

Cryo-electron microscopy (cryo-EM) has become a central tool for high-resolution structural biology, yet the massive scale of datasets (often exceeding 100k particle images) renders 3D reconstruction both computationally expensive and memory intensive. Traditional Fourier-space methods are efficient but lose fidelity due to repeated transforms, while recent real-space approaches based on neural radiance fields (NeRFs) improve accuracy but incur cubic memory and computation overhead. Therefore, we introduce GEM, a novel cryo-EM reconstruction framework built on 3D Gaussian Splatting (3DGS) that operates directly in real-space while maintaining high efficiency. Instead of modeling the entire density volume, GEM represents proteins with compact 3D Gaussians, each parameterized by only 11 values. To further improve the training efficiency, we designed a novel gradient computation to 3D Gaussians that contribute to each voxel. This design substantially reduced both memory footprint and training cost. On standard cryo-EM benchmarks, GEM achieves up to 48% faster training and 12% lower memory usage compared to state-of-the-art methods, while improving local resolution by as much as 38.8%. These results establish GEM as a practical and scalable paradigm for cryo-EM reconstruction, unifying speed, efficiency, and high-resolution accuracy. Our code is available at https://github.com/UNITES-Lab/GEM.

cs.CV↗

arXiv2025

DD-Ranking: Rethinking the Evaluation of Dataset Distillation

In recent years, dataset distillation has provided a reliable solution for data compression, where models trained on the resulting smaller synthetic datasets achieve performance comparable to those trained on the original datasets. To further improve the performance of synthetic datasets, various training pipelines and optimization objectives have been proposed, greatly advancing the field of dataset distillation. Recent decoupled dataset distillation methods introduce soft labels and stronger data augmentation during the post-evaluation phase and scale dataset distillation up to larger datasets (e.g., ImageNet-1K). However, this raises a question: Is accuracy still a reliable metric to fairly evaluate dataset distillation methods? Our empirical findings suggest that the performance improvements of these methods often stem from additional techniques rather than the inherent quality of the images themselves, with even randomly sampled images achieving superior results. Such misaligned evaluation settings severely hinder the development of DD. Therefore, we propose DD-Ranking, a unified evaluation framework, along with new general evaluation metrics to uncover the true performance improvements achieved by different methods. By refocusing on the actual information enhancement of distilled datasets, DD-Ranking provides a more comprehensive and fair evaluation standard for future research advancements.

cs.CV↗

arXiv2025

FIER: Fine-Grained and Efficient KV Cache Retrieval for Long-context LLM Inference

The Key-Value (KV) cache reading latency increases significantly with context lengths, hindering the efficiency of long-context LLM inference. To address this, previous works propose retaining a small fraction of KV cache based on token importance. For example, KV eviction uses static heuristics to retain tokens, while KV retrieval dynamically selects query-relevant tokens for more adaptive cache management. However, we observe that important tokens are often sparsely distributed across the long context. This sparsity makes existing page-level KV retrieval inaccurate, as each page may include irrelevant tokens and miss critical ones. In this work, we propose Fier, a \underline{Fi}ne-Grained and \underline{E}fficient KV cache \underline{R}etrieval method. Fier uses 1-bit quantized keys to estimate the importance of each token, resulting in efficient and precise retrieval. Experiments show that Fier matches full KV performance using only 11\% of the cache budget across various long-context tasks, reducing decoding latency by 1.2$\times$ to 1.5$\times$.Code is available at https://github.com/SimWangArizona/FIER

cs.DB↗

arXiv2025

A Survey on Model MoErging: Recycling and Routing Among Specialized Experts for Collaborative Learning

The availability of performant pre-trained models has led to a proliferation of fine-tuned expert models that are specialized to a particular domain or task. Model MoErging methods aim to recycle expert models to create an aggregate system with improved performance or generalization. A key component of MoErging methods is the creation of a router that decides which expert model(s) to use for a particular input or application. The promise, effectiveness, and large design space of MoErging has spurred the development of many new methods over the past few years. This rapid pace of development has made it challenging to compare different MoErging methods, which are rarely compared to one another and are often validated in different experimental setups. To remedy such gaps, we present a comprehensive survey of MoErging methods that includes a novel taxonomy for cataloging key design choices and clarifying suitable applications for each method. Apart from surveying MoErging research, we inventory software tools and applications that make use of MoErging. We additionally discuss related fields of study such as model merging, multitask learning, and mixture-of-experts models. Taken as a whole, our survey provides a unified overview of existing MoErging methods and creates a solid foundation for future work in this burgeoning field.

cs.LG↗

arXiv2025

Transferring Expert Cognitive Models to Social Robots via Agentic Concept Bottleneck Models

Successful group meetings, such as those implemented in group behavioral-change programs, work meetings, and other social contexts, must promote individual goal setting and execution while strengthening the social relationships within the group. Consequently, an ideal facilitator must be sensitive to the subtle dynamics of disengagement, difficulties with individual goal setting and execution, and interpersonal difficulties that signal a need for intervention. The challenges and cognitive load experienced by facilitators create a critical gap for an embodied technology that can interpret social exchanges while remaining aware of the needs of the individuals in the group and providing transparent recommendations that go beyond powerful but "black box" foundation models (FMs) that identify social cues. We address this important demand with a social robot co-facilitator that analyzes multimodal meeting data and provides discreet cues to the facilitator. The robot's reasoning is powered by an agentic concept bottleneck model (CBM), which makes decisions based on human-interpretable concepts like participant engagement and sentiments, ensuring transparency and trustworthiness. Our core contribution is a transfer learning framework that distills the broad social understanding of an FM into our specialized and transparent CBM. This concept-driven system significantly outperforms direct zero-shot FMs in predicting the need for intervention and enables real-time human correction of its reasoning. Critically, we demonstrate robust knowledge transfer: the model generalizes across different groups and successfully transfers the expertise of senior human facilitators to improve the performance of novices. By transferring an expert's cognitive model into an interpretable robotic partner, our work provides a powerful blueprint for augmenting human capabilities in complex social domains.

cs.CL↗