4 citations · 14 across the 17 of their papers we have counts for
21 papers
HeteroVDiff: Pipelining Video Diffusion across Mobile NPU and GPU with Shared Weights
Zheyu Shen, Ziyao Wang, Yexiao He +5
Video generation is moving from the cloud to phones for privacy and offline use, and applications often ask for several clips at a time, so on-device video generation is a throughp…
ARC-KV: Amortizing Anchor Search for Reconstruction-Based KV Cache Compaction
Zheyu Shen, Guanhua Wang, Dezhan Tu +5
Long-context large language model inference is bottlenecked by KV caches that grow linearly with sequence length. This burden is especially severe for long, reusable context prefix…
TacGen: Touch Is a Necessary Dimension of Physical-World Representation -- Addressing Tactile Data Scarcity with Scalable Vision-to-Touch Alignment and Generation
Wanghao Ye, Aarosh Das, Sihan Chen +19
Touch resolves the physical-property ambiguity left by vision: exploratory contact recovers shape, texture, compliance, and material, and visuo-haptic object representations conver…
Drop-Then-Recovery: How Redundant Are Vision-Language-Action Models?
Guoheng Sun, Kaixi Feng, Shwai He +8
Vision-Language-Action (VLA) models enable instruction-driven robotic manipulation, but they inherit oversized language backbones from pretrained VLMs whose capacity far exceeds wh…
AliyunConsoleAgent: Training Web Agents in Real-World Cloud Environments via Distillation and Reinforcement Learning
Bojie Rong, Zheyu Shen, Qiaoping Wang +7
We present AliyunConsoleAgent, a web agent framework for automated documentation verification in real-world cloud consoles. Major cloud platforms encompass hundreds of products wit…
Vision-Language-Action in Robotics: A Survey of Datasets, Benchmarks, and Data Engines
Ziyao Wang, Bingying Wang, Hanrong Zhang +7
Despite remarkable progress in Vision--Language--Action (VLA) models, a central bottleneck remains underexamined: the data infrastructure that underlies embodied learning. In this…
Cognibit: From Digital Exhaustion to Real-World Connection Through Gamified Territory Control and LLM-Powered Twin Networking
Wanghao Ye, Sihan Chen, Yiting Wang +20
We present an LLM-powered social discovery platform that uses digital twins to autonomously evaluate interpersonal compatibility through behavioral simulation. The platform unifies…
FedMOA: Federated GRPO for Personalized Reasoning LLMs under Heterogeneous Rewards
Ziyao Wang, Daeun Jung, Yexiao He +4
Group Relative Policy Optimization (GRPO) has recently emerged as an effective approach for improving the reasoning capabilities of large language models through online multi-objec…
Predictive Auditing of Hidden Tokens in LLM APIs via Reasoning Length Estimation
Ziyao Wang, Guoheng Sun, Yexiao He +3
Commercial LLM services often conceal internal reasoning traces while still charging users for every generated token, including those from hidden intermediate steps, raising concer…
EdgeLoRA: An Efficient Multi-Tenant LLM Serving System on Edge Devices
Zheyu Shen, Yexiao He, Ziyao Wang +4
Large Language Models (LLMs) have gained significant attention due to their versatility across a wide array of applications. Fine-tuning LLMs with parameter-efficient adapters, suc…
CogniPair: From LLM Chatbots to Conscious AI Agents -- GNWT-Based Multi-Agent Digital Twins for Social Pairing -- Dating & Hiring Applications
Wanghao Ye, Sihan Chen, Yiting Wang +18
Current large language model (LLM) agents lack authentic human psychological processes necessary for genuine digital twins and social AI applications. To address this limitation, w…
Invisible Tokens, Visible Bills: The Urgent Need to Audit Hidden Operations in Opaque LLM Services
Guoheng Sun, Ziyao Wang, Xuandong Zhao +5
Modern large language model (LLM) services increasingly rely on complex, often abstract operations, such as multi-step reasoning and multi-agent collaboration, to generate high-qua…
CoIn: Counting the Invisible Reasoning Tokens in Commercial Opaque LLM APIs
Guoheng Sun, Ziyao Wang, Bowei Tian +7
As post-training techniques evolve, large language models (LLMs) are increasingly augmented with structured multi-step reasoning abilities, often optimized through reinforcement le…
Arctic-Text2SQL-R1: Simple Rewards, Strong Reasoning in Text-to-SQL
Zhewei Yao, Guoheng Sun, Lukasz Borchmann +7
Translating natural language into SQL (Test2SQL) is a longstanding challenge at the intersection of natural language understanding and structured data access. While large language…
SymRTLO: Enhancing RTL Code Optimization with LLMs and Neuron-Inspired Symbolic Reasoning
Yiting Wang, Wanghao Ye, Ping Guo +11
Optimizing Register Transfer Level (RTL) code is crucial for improving the power, performance, and area (PPA) of digital circuits in the early stages of synthesis. Manual rewriting…
Prada: Black-Box LLM Adaptation with Private Data on Resource-Constrained Devices
Ziyao Wang, Yexiao He, Zheyu Shen +4
In recent years, Large Language Models (LLMs) have demonstrated remarkable abilities in various natural language processing tasks. However, adapting these models to specialized dom…
Revisiting Federated Fine-Tuning: A Single Communication Round is Enough for Foundation Models
Ziyao Wang, Bowei Tian, Yexiao He +6
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…
Domino: Eliminating Communication in LLM Training via Generic Tensor Slicing and Overlapping
Guanhua Wang, Chengming Zhang, Zheyu Shen +2
Given the popularity of generative AI, Large Language Models (LLMs) often consume hundreds or thousands of GPUs for parallelizing and accelerating the training process. Communicati…
FLoRA: Federated Fine-Tuning Large Language Models with Heterogeneous Low-Rank Adaptations
Ziyao Wang, Zheyu Shen, Yexiao He +4
The rapid development of Large Language Models (LLMs) has been pivotal in advancing AI, with pre-trained LLMs being adaptable to diverse downstream tasks through fine-tuning. Feder…
What Matters in Transformers? Not All Attention is Needed
Shwai He, Guoheng Sun, Zheyu Shen +1
While scaling Transformer-based large language models (LLMs) has demonstrated promising performance across various tasks, it also introduces redundant architectures, posing efficie…
SHED: Shapley-Based Automated Dataset Refinement for Instruction Fine-Tuning
Yexiao He, Ziyao Wang, Zheyu Shen +5
The pre-trained Large Language Models (LLMs) can be adapted for many downstream tasks and tailored to align with human preferences through fine-tuning. Recent studies have discover…