LeMo: Enabling LEss Token Involvement for MOre Context Fine-tuning

The escalating demand for long-context applications has intensified the necessity of extending the LLM context windows. Despite recent fine-tuning approaches successfully expanding context lengths, their high memory footprints, especially for activations, present a critical practical limitation. Current parameter-efficient fine-tuning methods prioritize reducing parameter update overhead over addressing activation memory constraints. Similarly, existing sparsity mechanisms improve computational efficiency but overlook activation memory optimization due to the phenomenon of Shadowy Activation. In this paper, we propose LeMo, the first LLM fine-tuning system that explores and exploits a new token-level sparsity mechanism inherent in long-context scenarios, termed Contextual Token Sparsity. LeMo minimizes redundant token involvement by assessing the informativeness of token embeddings while preserving model accuracy. Specifically, LeMo introduces three key techniques: (1) Token Elimination, dynamically identifying and excluding redundant tokens across varying inputs and layers. (2) Pattern Prediction, utilizing well-trained predictors to approximate token sparsity patterns with minimal overhead. (3) Kernel Optimization, employing permutation-free and segment-based strategies to boost system performance. We implement LeMo as an end-to-end fine-tuning system compatible with various LLM architectures and other optimization techniques. Comprehensive evaluations demonstrate that LeMo reduces memory consumption by up to 1.93x and achieves up to 1.36x speedups, outperforming state-of-the-art fine-tuning systems.

Enabling Cardiac Monitoring using In-ear Ballistocardiogram on COTS Wireless Earbuds

The human ear offers a unique opportunity for cardiac monitoring due to its physiological and practical advantages. However, existing earable solutions require additional hardware and complex processing, posing challenges for commercial True Wireless Stereo (TWS) earbuds which are limited by their form factor and resources. In this paper, we propose TWSCardio, a novel system that repurposes the IMU sensors in TWS earbuds for cardiac monitoring. Our key finding is that these sensors can capture in-ear ballistocardiogram (BCG) signals. TWSCardio reuses the unstable Bluetooth channel to stream the IMU data to a smartphone for BCG processing. It incorporates a signal enhancement framework to address issues related to missing data and low sampling rate, while mitigating motion artifacts by fusing multi-axis information. Furthermore, it employs a region-focused signal reconstruction method to translate the multi-axis in-ear BCG signals into fine-grained seismocardiogram (SCG) signals. We have implemented TWSCardio as an efficient real-time app. Our experiments on 100 subjects verify that TWSCardio can accurately reconstruct cardiac signals while showing resilience to motion artifacts, missing data, and low sampling rates. Our case studies further demonstrate that TWSCardio can support diverse cardiac monitoring applications.

MobiFuse: A High-Precision On-device Depth Perception System with Multi-Data Fusion

We present MobiFuse, a high-precision depth perception system on mobile devices that combines dual RGB and Time-of-Flight (ToF) cameras. To achieve this, we leverage physical principles from various environmental factors to propose the Depth Error Indication (DEI) modality, characterizing the depth error of ToF and stereo-matching. Furthermore, we employ a progressive fusion strategy, merging geometric features from ToF and stereo depth maps with depth error features from the DEI modality to create precise depth maps. Additionally, we create a new ToF-Stereo depth dataset, RealToF, to train and validate our model. Our experiments demonstrate that MobiFuse excels over baselines by significantly reducing depth measurement errors by up to 77.7%. It also showcases strong generalization across diverse datasets and proves effectiveness in two downstream tasks: 3D reconstruction and 3D segmentation. The demo video of MobiFuse in real-life scenarios is available at the de-identified YouTube link(https://youtu.be/jy-Sp7T1LVs).

ShotVL: Human-Centric Highlight Frame Retrieval via Language Queries

Existing works on human-centric video understanding typically focus on analyzing specific moment or entire videos. However, many applications require higher precision at the frame level. In this work, we propose a novel task, BestShot, which aims to locate highlight frames within human-centric videos via language queries. This task demands not only a deep semantic comprehension of human actions but also precise temporal localization. To support this task, we introduce the BestShot Benchmark. %The benchmark is meticulously constructed by combining human detection and tracking, potential frame selection based on human judgment, and detailed textual descriptions crafted by human input to ensure precision. The benchmark is meticulously constructed by combining human-annotated highlight frames, detailed textual descriptions and duration labeling. These descriptions encompass three critical elements: (1) Visual content; (2) Fine-grained action; and (3) Human Pose Description. Together, these elements provide the necessary precision to identify the exact highlight frames in videos. To tackle this problem, we have collected two distinct datasets: (i) ShotGPT4o Dataset, which is algorithmically generated by GPT-4o and (ii) Image-SMPLText Dataset, a dataset with large-scale and accurate per-frame pose description leveraging PoseScript and existing pose estimation datasets. Based on these datasets, we present a strong baseline model, ShotVL, fine-tuned from InternVL, specifically for BestShot. We highlight the impressive zero-shot capabilities of our model and offer comparative analyses with existing SOTA models. ShotVL demonstrates a significant 52% improvement over InternVL on the BestShot Benchmark and a notable 57% improvement on the THUMOS14 Benchmark, all while maintaining the SOTA performance in general image classification and retrieval.

EdgeOAR: Real-time Online Action Recognition On Edge Devices

This paper addresses the challenges of Online Action Recognition (OAR), a framework that involves instantaneous analysis and classification of behaviors in video streams. OAR must operate under stringent latency constraints, making it an indispensable component for real-time feedback for edge computing. Existing methods, which typically rely on the processing of entire video clips, fall short in scenarios requiring immediate recognition. To address this, we designed EdgeOAR, a novel framework specifically designed for OAR on edge devices. EdgeOAR includes the Early Exit-oriented Task-specific Feature Enhancement Module (TFEM), which comprises lightweight submodules to optimize features in both temporal and spatial dimensions. We design an iterative training method to enable TFEM learning features from the beginning of the video. Additionally, EdgeOAR includes an Inverse Information Entropy (IIE) and Modality Consistency (MC)-driven fusion module to fuse features and make better exit decisions. This design overcomes the two main challenges: robust modeling of spatio-temporal action representations with limited initial frames in online video streams and balancing accuracy and efficiency on resource-constrained edge devices. Experiments show that on the UCF-101 dataset, our method EdgeOAR reduces latency by 99.23% and energy consumption by 99.28% compared to state-of-the-art (SOTA) method. And achieves an adequate accuracy on edge devices.

Ripple: Accelerating LLM Inference on Smartphones with Correlation-Aware Neuron Management

Large Language Models (LLMs) have achieved remarkable success across various domains, yet deploying them on mobile devices remains an arduous challenge due to their extensive computational and memory demands. While lightweight LLMs have been developed to fit mobile environments, they suffer from degraded model accuracy. In contrast, sparsity-based techniques minimize DRAM usage by selectively transferring only relevant neurons to DRAM while retaining the full model in external storage, such as flash. However, such approaches are critically limited by numerous I/O operations, particularly on smartphones with severe IOPS constraints. In this paper, we propose Ripple, a novel approach that accelerates LLM inference on smartphones by optimizing neuron placement in flash memory. Ripple leverages the concept of Neuron Co-Activation, where neurons frequently activated together are linked to facilitate continuous read access and optimize data transfer efficiency. Our approach incorporates a two-stage solution: an offline stage that reorganizes neuron placement based on co-activation patterns, and an online stage that employs tailored data access and caching strategies to align well with hardware characteristics. Evaluations conducted on a variety of smartphones and LLMs demonstrate that Ripple achieves up to 5.93x improvements in I/O latency compared to the state-of-the-art. As the first solution to optimize storage placement under sparsity, Ripple explores a new optimization space at the intersection of sparsity-driven algorithm and storage-level system co-design in LLM inference.

OLLIE: Imitation Learning from Offline Pretraining to Online Finetuning

In this paper, we study offline-to-online Imitation Learning (IL) that pretrains an imitation policy from static demonstration data, followed by fast finetuning with minimal environmental interaction. We find the na\"ive combination of existing offline IL and online IL methods tends to behave poorly in this context, because the initial discriminator (often used in online IL) operates randomly and discordantly against the policy initialization, leading to misguided policy optimization and $\textit{unlearning}$ of pretraining knowledge. To overcome this challenge, we propose a principled offline-to-online IL method, named $\texttt{OLLIE}$, that simultaneously learns a near-expert policy initialization along with an $\textit{aligned discriminator initialization}$, which can be seamlessly integrated into online IL, achieving smooth and fast finetuning. Empirically, $\texttt{OLLIE}$ consistently and significantly outperforms the baseline methods in $\textbf{20}$ challenging tasks, from continuous control to vision-based domains, in terms of performance, demonstration efficiency, and convergence speed. This work may serve as a foundation for further exploration of pretraining and finetuning in the context of IL.

How to Leverage Diverse Demonstrations in Offline Imitation Learning

Offline Imitation Learning (IL) with imperfect demonstrations has garnered increasing attention owing to the scarcity of expert data in many real-world domains. A fundamental problem in this scenario is how to extract positive behaviors from noisy data. In general, current approaches to the problem select data building on state-action similarity to given expert demonstrations, neglecting precious information in (potentially abundant) $\textit{diverse}$ state-actions that deviate from expert ones. In this paper, we introduce a simple yet effective data selection method that identifies positive behaviors based on their resultant states -- a more informative criterion enabling explicit utilization of dynamics information and effective extraction of both expert and beneficial diverse behaviors. Further, we devise a lightweight behavior cloning algorithm capable of leveraging the expert and selected data correctly. In the experiments, we evaluate our method on a suite of complex and high-dimensional offline IL benchmarks, including continuous-control and vision-based tasks. The results demonstrate that our method achieves state-of-the-art performance, outperforming existing methods on $\textbf{20/21}$ benchmarks, typically by $\textbf{2-5x}$, while maintaining a comparable runtime to Behavior Cloning ($\texttt{BC}$).

RobWE: Robust Watermark Embedding for Personalized Federated Learning Model Ownership Protection

Embedding watermarks into models has been widely used to protect model ownership in federated learning (FL). However, existing methods are inadequate for protecting the ownership of personalized models acquired by clients in personalized FL (PFL). This is due to the aggregation of the global model in PFL, resulting in conflicts over clients' private watermarks. Moreover, malicious clients may tamper with embedded watermarks to facilitate model leakage and evade accountability. This paper presents a robust watermark embedding scheme, named RobWE, to protect the ownership of personalized models in PFL. We first decouple the watermark embedding of personalized models into two parts: head layer embedding and representation layer embedding. The head layer belongs to clients' private part without participating in model aggregation, while the representation layer is the shared part for aggregation. For representation layer embedding, we employ a watermark slice embedding operation, which avoids watermark embedding conflicts. Furthermore, we design a malicious watermark detection scheme enabling the server to verify the correctness of watermarks before aggregating local models. We conduct an exhaustive experimental evaluation of RobWE. The results demonstrate that RobWE significantly outperforms the state-of-the-art watermark embedding schemes in FL in terms of fidelity, reliability, and robustness.

Mutual Enhancement of Large and Small Language Models with Cross-Silo Knowledge Transfer

While large language models (LLMs) are empowered with broad knowledge, their task-specific performance is often suboptimal. It necessitates fine-tuning LLMs with task-specific data, but such data may be inaccessible due to privacy concerns. In this paper, we propose a novel approach to enhance LLMs with smaller language models (SLMs) that are trained on clients using their private task-specific data. To enable mutual enhancement between LLMs and SLMs, we propose CrossLM, where the SLMs promote the LLM to generate task-specific high-quality data, and both the LLM and SLMs are enhanced with the generated data. We evaluate CrossLM using publicly accessible language models across a range of benchmark tasks. The results demonstrate that CrossLM significantly enhances the task-specific performance of SLMs on clients and the LLM on the cloud server simultaneously while preserving the LLM's generalization capability.