22 accepted papers
Large Language Models (LLMs) have shown great potential in reasoning tasks through test-time scaling methods like self-consistency with majority voting. However, this approach often leads to diminishing returns in accuracy and high computational overhead. To address these challenges, we introduce De…
Aligning Multimodal Large Language Models (MLLMs) with human preferences remains a fundamental challenge. While Generative Reward Models (GRMs) offer a promising reasoning-based alternative to scalar models, they are often hindered by severe position bias and prohibitively high computational overhea…
Reinforcement learning has been central to recent advances in large language model reasoning, but most algorithms rely on on-policy training that demands fresh rollouts at every update, limiting efficiency and scalability. Asynchronous RL systems alleviate this by decoupling rollout generation from…
Large vision-language models (LVLMs) have achieved impressive performance across a variety of multimodal tasks, yet remain vulnerable to targeted adversarial attacks, particularly in black-box settings. In this paper, we propose VCP-Attack, a transferable targeted attack framework that combines stru
Digital watermarking is essential for securing generated images from diffusion models. Accurate watermark evaluation is critical for algorithm development, yet existing methods have significant limitations: they lack a unified framework for both residual and semantic watermarks, provide results with…
Microfluidic technology is currently a popular approach in the field of single-cell research, which is used to reveal the heterogeneity among cells. However, most of the existing microfluidic technologies for single-cell research lack the ability to control the microenvironment of single cells after
Reinforcement learning, such as PPO and GRPO, has powered recent breakthroughs in LLM reasoning. Scaling rollout to sample more prompts enables models to selectively use higher-quality data for training, which can stabilize RL training and improve model performance, but at the cost of significant co…
Large Language Models (LLMs) matrices can often be expressed in low-rank format with potential to relax memory and compute resource requirements. Unlike previous works which pivot around developing novel matrix decomposition algorithms, in this work we focus to study the emerging non-uniform low-ran…
This paper presents a multi-particle parallel manipulation optoelectronic tweezers system integrated with computer vision technology, enabling the parallel and precise manipulation of dozens of particles. This system significantly enhances manipulation efficiency while maintaining high precision. By
The optimal bit-width for achieving the best trade-off between quantized model size and accuracy has been a subject of ongoing debate. While some advocate for 4-bit quantization, others propose that 1.58-bit offers superior results. However, the lack of a cohesive framework for different bits has le…
Large Language Models (LLMs) are susceptible to jailbreak attacks that can induce them to generate harmful content.Previous jailbreak methods primarily exploited the internal properties or capabilities of LLMs, such as optimization-based jailbreak methods and methods that leveraged the model’s conte…
Optoelectronic tweezers (OET) has shown great promise in various applications, especially in the precise manipulation of microparticles and microorganisms on a micron and nanometer scale. This technology significantly enhances the efficiency of single-cell sorting and the development of antibody-bas…
Training Large Language Models (LLMs) presents significant memory challenges, predominantly due to the growing size of weights and optimizer states. Common memory-reduction approaches, such as low-rank adaptation (LoRA), add a trainable low-rank matrix to the frozen pre-trained weight in each layer,…
We introduce Mini-Sequence Transformer (MsT), a simple and effective methodology for highly efficient and accurate LLM training with extremely long sequences. MsT partitions input sequences and iteratively processes mini-sequences to reduce intermediate memory usage. Integrated with activation recom…
Current PEFT methods for LLMs can achieve high quality, efficient training, or scalable serving, but not all three simultaneously. To address this limitation, we investigate sparse fine-tuning and observe a remarkable improvement in generalization ability. Utilizing this key insight, we propose a…
The untethered microrobots driven by multiple external physics fields have promising ability in minimally invasive disease treatments. One common type of the driving fields is gradient magnetic field, which can provide microrobots with adequate driving force in complicated environment. In this study…
This work presents a novel electrical method, implemented in the form of a microfluidic device, for cell arraying and target cell lysis. The microfluidic device contains a micro-well array on the photoconductive layer based on the optoelectronic tweezers (OET) method, where parallel cell manipulatio…
Robot teleoperation has been studied for the past 70 years and is relevant in many contexts, such as in the handling of hazardous materials and telesurgery. The COVID19 pandemic has rekindled interest in this topic, but the existing robotic education kits fall short of being suitable for teleoperate…
A currently popular research area in end-to-end speech translation is the use of knowledge distillation from a machine translation (MT) task to improve the speech translation (ST) task. However, such scenario obviously only allows one way transfer, which is limited by the performance of the teacher…
The simultaneous recognition of multiple objects in one image remains a challenging task, spanning multiple events in the recognition field such as various object scales, inconsistent appearances, and confused inter-class relationships. Recent research efforts mainly resort to the statistic label co…
Compositionality is a basic structural feature of both biological and artificial neural networks. Learning compositional functions via gradient descent incurs well known problems like vanishing and exploding gradients, making careful learning rate tuning essential for real-world applications. This p…
Training neural networks on large datasets can be accelerated by distributing the workload over a network of machines. As datasets grow ever larger, networks of hundreds or thousands of machines become economically viable. The time cost of communicating gradients limits the effectiveness of using su…