Direct Preference Optimization (DPO) has gained significant attention for its simplicity and computational efficiency in aligning large language models (LLMs). Recent advancements have extended DPO to multimodal scenarios, achieving strong performance. However, traditional DPO relies on binary preference optimization, rewarding or penalizing entire responses without considering fine-grained segment correctness, leading to suboptimal solutions. The root of this issue lies in the absence of fine-grained supervision during the optimization process. To address this, we propose Adaptive Sentence-level Preference Optimization (ASPO), which evaluates individual sentences for more precise preference optimization. By dynamically calculating adaptive rewards at the sentence level based on model predictions, ASPO enhances response content assessment without additional models or parameters. This significantly improves the alignment of multimodal features. Extensive experiments show that ASPO substantially enhances the overall performance of multimodal models.

We introduce a novel design of parallel-jaw grippers drawing inspiration from pin-pression toys. The proposed pin-pression gripper features a distinctive mechanism in which each finger integrates a 2D array of pins capable of independent extension and retraction. This unique design allows the gripper to instantaneously customize its finger's shape to conform to the object being grasped by dynamically adjusting the extension/retraction of the pins. In addition, the gripper excels in in-hand re-orientation of objects for enhanced grasping stability again via dynamically adjusting the pins. To learn the dynamic grasping skills of pin-pression grippers, we devise a dedicated reinforcement learning algorithm with careful designs of state representation and reward shaping. To achieve a more efficient grasp-while-lift grasping mode, we propose a curriculum learning scheme. Extensive evaluations demonstrate that our design, together with the learned skills, leads to highly flexible and robust grasping with much stronger generality to unseen objects than alternatives. We also highlight encouraging physical results of sim-to-real transfer on a physically manufactured pin-pression gripper, demonstrating the practical significance of our novel gripper design and grasping skill. Demonstration videos for this paper are available at https://github.com/siggraph-pin-pression-gripper/pin-pression-gripper-video.

This work studies knowledge distillation (KD) for large language models (LLMs) through preference optimization. We propose a reward-guided imitation learning framework for sequential KD, formulating a min-max optimization problem between the policy and reward model (RM) to minimize the performance gap between the student and teacher policies. Specifically, the reward optimization is constrained to achieve near-optimality within a confidence set for preference alignment. For preference data construction, we explore both offline and online preference-based KD. Additionally, we reformulate the RM using the $Q$-value function and extend the framework to white-box KD, where the teacher policy's predicted probabilities are accessible. Theoretical analysis and empirical results demonstrate the effectiveness of the proposed framework.

Large language models (LLMs) have demonstrated impressive capabilities across numerous NLP tasks. Nevertheless, conventional first-order fine-tuning techniques impose heavy memory demands, creating practical obstacles to real-world applications. Zeroth-order (ZO) optimization has recently emerged as a promising memory-efficient alternative, as it circumvents the need for backpropagation by estimating gradients solely through forward passes--making it particularly suitable for resource-limited environments. Despite its efficiency, ZO optimization suffers from gradient estimation bias, which significantly hinders convergence speed. To address this, we analytically identify and characterize the lower-order bias introduced during ZO-based gradient estimation in LLM fine-tuning. Motivated by tools in mathematical physics, we introduce a kernel-function-based ZO framework aimed at mitigating this bias and improving optimization stability. KerZOO achieves comparable or superior performance to existing ZO baselines in both full-parameter and parameter-efficient fine-tuning settings of LLMs, while significantly reducing the number of iterations required to reach convergence. For example, KerZOO reduces total GPU training hours by as much as 74% and 44% on WSC and MultiRC datasets in fine-tuning OPT-2.7B model and can exceed the MeZO baseline by 2.9% and 2.6% in accuracy. We show that the kernel function is an effective avenue for reducing estimation bias in ZO methods.

This work investigates the optimal allocation of inference compute across three key scaling factors in video vision language models: language model size, frame count, and the number of visual tokens per frame. While prior works typically focuses on optimizing model efficiency or improving performance without considering resource constraints, we instead identify optimal model configuration under fixed inference compute budgets. We conduct large-scale training sweeps and careful parametric modeling of task performance to identify the inference compute-optimal frontier. Our experiments reveal how task performance depends on scaling factors and finetuning data size, as well as how changes in data size shift the compute-optimal frontier. These findings translate to practical tips for selecting these scaling factors.

Direct Preference Optimization (DPO) has emerged as a promising framework for aligning Large Language Models (LLMs) with human preferences by directly optimizing the log-likelihood difference between chosen and rejected responses. However, existing methods assign equal importance to all tokens in the response, while humans focus on more meaningful parts. This leads to suboptimal preference optimization, as irrelevant or noisy tokens disproportionately influence DPO loss. To address this limitation, we propose \textbf{O}ptimal \textbf{T}ransport-based token weighting scheme for enhancing direct \textbf{P}reference \textbf{O}ptimization (OTPO). By emphasizing semantically meaningful token pairs and de-emphasizing less relevant ones, our method introduces a context-aware token weighting scheme that yields a more contrastive reward difference estimate. This adaptive weighting enhances reward stability, improves interpretability, and ensures that preference optimization focuses on meaningful differences between responses. Extensive experiments have validated OTPO's effectiveness in improving instruction-following ability across various settings\footnote{Code is available at https://github.com/Mimasss2/OTPO.}.

In this work, we propose an optimization-based trajectory planner for tractor-trailer vehicles on curvy roads. The lack of analytical expression for the trailer's errors to the center line pose a great challenge to the trajectory planning for tractor-trailer vehicles. To address this issue, we first use geometric representations to characterize the lateral and orientation errors in Cartesian frame, where the errors would serve as the components of the cost function and the road edge constraints within our optimization process. Next, we generate a coarse trajectory to warm-start the subsequent optimization problems. On the other hand, to achieve a good approximation of the continuous-time kinematics, optimization-based methods usually discretize the kinematics with a large sampling number. This leads to an increase in the number of the variables and constraints, thus making the optimization problem difficult to solve. To address this issue, we design a Progressively Increasing Sampling Number Optimization (PISNO) framework. More specifically, we first find a nearly feasible trajectory with a small sampling number to warm-start the optimization process. Then, the sampling number is progressively increased, and the corresponding intermediate Optimal Control Problem (OCP) is solved in each iteration. Next, we further resample the obtained solution into a finer sampling period, and then use it to warm-start the intermediate OCP in next iteration. This process is repeated until reaching a threshold sampling number. Simulation and experiment results show the proposed method exhibits a good performance and less computational consumption over the benchmarks.

The Area Under the ROC Curve (AUC) is a key metric for classification, especially under class imbalance, with growing research focus on optimizing AUC over accuracy in applications like medical image analysis and deepfake detection. This leads to fairness in AUC optimization becoming crucial as biases can impact protected groups. While various fairness mitigation techniques exist, fairness considerations in AUC optimization remain in their early stages, with most research focusing on improving AUC fairness under the assumption of clean protected groups. However, these studies often overlook the impact of noisy protected groups, leading to fairness violations in practice. To address this, we propose the first robust AUC fairness approach under noisy protected groups with fairness theoretical guarantees using distributionally robust optimization. Extensive experiments on tabular and image datasets show that our method outperforms state-of-the-art approaches in preserving AUC fairness. The code is in https://github.com/Purdue-M2/AUC_Fairness_with_Noisy_Groups.

--Federated Learning (FL) facilitates the fine-tuning of Foundation Models (FMs) using distributed data sources, with Low-Rank Adaptation (LoRA) gaining popularity due to its low communication costs and strong performance. While recent work acknowledges the benefits of heterogeneous LoRA in FL and introduces flexible algorithms to support its implementation, our theoretical analysis reveals a critical gap: existing methods lack formal convergence guarantees due to parameter truncation and biased gradient updates. Specifically, adapting client-specific LoRA ranks necessitates truncating global parameters, which introduces inherent truncation errors and leads to subsequent inaccurate gradient updates that accumulate over training rounds, ultimately degrading performance. T o address the above issues, we propose FedHL, a simple yet effective Federated Learning framework tailored for Heterogeneous LoRA. By leveraging the full-rank global model as a calibrated aggregation basis, FedHL eliminates the direct truncation bias from initial alignment with client-specific ranks. Furthermore, we derive the theoretically optimal aggregation weights by minimizing the gradient drift term in the convergence upper bound. Our analysis shows that FedHL guarantees O (1 / T) convergence rate, and experiments on multiple real-world datasets demonstrate a 1-3% improvement over several state-of-the-art methods. Zihao Peng, Jiandian Zeng, and Guo Li are with the Institute of Artificial Intelligence and Future Networks, Beijing Normal University, Zhuhai 519087, China (e-mail: { pzh cs, liguo }@mail.bnu.edu.cn; Boyuan Li is with the School of Computer Science and Artificial Intelligence, Zhengzhou University, Zhengzhou 450001, China (e-mail: l202311841010602@gs.zzu.edu.cn). Shengbo Chen is with the School of Software, Nanchang University, Nanchang 330000, China (e-mail: ccb02kingdom@gmail.com).

Dictionary learning has recently emerged as a promising approach for mechanistic interpretability of large transformer models. Disentangling high-dimensional transformer embeddings, however, requires algorithms that scale to high-dimensional data with large sample sizes. Recent work has explored sparse autoencoders (SAEs) for this problem. However, SAEs use a simple linear encoder to solve the sparse encoding subproblem, which is known to be NP-hard. It is therefore interesting to understand whether this structure is sufficient to find good solutions to the dictionary learning problem or if a more sophisticated algorithm could find better solutions. In this work, we propose Double-Batch KSVD (DB-KSVD), a scalable dictionary learning algorithm that adapts the classic KSVD algorithm. DB-KSVD is informed by the rich theoretical foundations of KSVD but scales to datasets with millions of samples and thousands of dimensions. We demonstrate the efficacy of DB-KSVD by disentangling embeddings of the Gemma-2-2B model and evaluating on six metrics from the SAEBench benchmark, where we achieve competitive results when compared to established approaches based on SAEs. By matching SAE performance with an entirely different optimization approach, our results suggest that (i) SAEs do find strong solutions to the dictionary learning problem and (ii) that traditional optimization approaches can be scaled to the required problem sizes, offering a promising avenue for further research. We provide an implementation of DB-KSVD at https://github.com/RomeoV/KSVD.jl.