arXiv subjects

Yang Li

Publications and source records attributed to Yang Li.

At least 541 records · Page 30Linked to original sources

arXiv2025

FlowOE: Imitation Learning with Flow Policy from Ensemble RL Experts for Optimal Execution under Heston Volatility and Concave Market Impacts

Optimal execution in financial markets refers to the process of strategically transacting a large volume of assets over a period to achieve the best possible outcome by balancing the trade-off between market impact costs and timing or volatility risks. Traditional optimal execution strategies, such as static Almgren-Chriss models, often prove suboptimal in dynamic financial markets. This paper propose flowOE, a novel imitation learning framework based on flow matching models, to address these limitations. FlowOE learns from a diverse set of expert traditional strategies and adaptively selects the most suitable expert behavior for prevailing market conditions. A key innovation is the incorporation of a refining loss function during the imitation process, enabling flowOE not only to mimic but also to improve upon the learned expert actions. To the best of our knowledge, this work is the first to apply flow matching models in a stochastic optimal execution problem. Empirical evaluations across various market conditions demonstrate that flowOE significantly outperforms both the specifically calibrated expert models and other traditional benchmarks, achieving higher profits with reduced risk. These results underscore the practical applicability and potential of flowOE to enhance adaptive optimal execution.

cs.LG↗

arXiv2025

Kimi k1.5: Scaling Reinforcement Learning with LLMs

Language model pretraining with next token prediction has proved effective for scaling compute but is limited to the amount of available training data. Scaling reinforcement learning (RL) unlocks a new axis for the continued improvement of artificial intelligence, with the promise that large language models (LLMs) can scale their training data by learning to explore with rewards. However, prior published work has not produced competitive results. In light of this, we report on the training practice of Kimi k1.5, our latest multi-modal LLM trained with RL, including its RL training techniques, multi-modal data recipes, and infrastructure optimization. Long context scaling and improved policy optimization methods are key ingredients of our approach, which establishes a simplistic, effective RL framework without relying on more complex techniques such as Monte Carlo tree search, value functions, and process reward models. Notably, our system achieves state-of-the-art reasoning performance across multiple benchmarks and modalities -- e.g., 77.5 on AIME, 96.2 on MATH 500, 94-th percentile on Codeforces, 74.9 on MathVista -- matching OpenAI's o1. Moreover, we present effective long2short methods that use long-CoT techniques to improve short-CoT models, yielding state-of-the-art short-CoT reasoning results -- e.g., 60.8 on AIME, 94.6 on MATH500, 47.3 on LiveCodeBench -- outperforming existing short-CoT models such as GPT-4o and Claude Sonnet 3.5 by a large margin (up to +550%).

cs.AI↗

arXiv2025

Improving Factuality with Explicit Working Memory

Large language models can generate factually inaccurate content, a problem known as hallucination. Recent works have built upon retrieved-augmented generation to improve factuality through iterative prompting but these methods are limited by the traditional RAG design. To address these challenges, we introduce EWE (Explicit Working Memory), a novel approach that enhances factuality in long-form text generation by integrating a working memory that receives real-time feedback from external resources. The memory is refreshed based on online fact-checking and retrieval feedback, allowing EWE to rectify false claims during the generation process and ensure more accurate and reliable outputs. Our experiments demonstrate that Ewe outperforms strong baselines on four fact-seeking long-form generation datasets, increasing the factuality metric, VeriScore, by 2 to 6 points absolute without sacrificing the helpfulness of the responses. Further analysis reveals that the design of rules for memory updates, configurations of memory units, and the quality of the retrieval datastore are crucial factors for influencing model performance.

cs.CL↗

arXiv2025

RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers

We reveal that feedforward network (FFN) layers, rather than attention layers, are the primary contributors to Vision Transformer (ViT) inference latency, with their impact signifying as model size increases. This finding highlights a critical opportunity for optimizing the efficiency of large-scale ViTs by focusing on FFN layers. In this work, we propose a novel channel idle mechanism that facilitates post-training structural reparameterization for efficient FFN layers during testing. Specifically, a set of feature channels remains idle and bypasses the nonlinear activation function in each FFN layer, thereby forming a linear pathway that enables structural reparameterization during inference. This mechanism results in a family of ReParameterizable Vision Transformers (RePaViTs), which achieve remarkable latency reductions with acceptable sacrifices (sometimes gains) in accuracy across various ViTs. The benefits of our method scale consistently with model sizes, demonstrating greater speed improvements and progressively narrowing accuracy gaps or even higher accuracies on larger models. In particular, RePa-ViT-Large and RePa-ViT-Huge enjoy 66.8% and 68.7% speed-ups with +1.7% and +1.1% higher top-1 accuracies under the same training strategy, respectively. RePaViT is the first to employ structural reparameterization on FFN layers to expedite ViTs to our best knowledge, and we believe that it represents an auspicious direction for efficient ViTs. Source code is available at https://github.com/Ackesnal/RePaViT.

cs.CV↗

arXiv2025

DenseLoRA: Dense Low-Rank Adaptation of Large Language Models

Low-rank adaptation (LoRA) has been developed as an efficient approach for adapting large language models (LLMs) by fine-tuning two low-rank matrices, thereby reducing the number of trainable parameters. However, prior research indicates that many of the weights in these matrices are redundant, leading to inefficiencies in parameter utilization. To address this limitation, we introduce Dense Low-Rank Adaptation (DenseLoRA), a novel approach that enhances parameter efficiency while achieving superior performance compared to LoRA. DenseLoRA builds upon the concept of representation fine-tuning, incorporating a single Encoder-Decoder to refine and compress hidden representations across all adaptation layers before applying adaptation. Instead of relying on two redundant low-rank matrices as in LoRA, DenseLoRA adapts LLMs through a dense low-rank matrix, improving parameter utilization and adaptation efficiency. We evaluate DenseLoRA on various benchmarks, showing that it achieves 83.8% accuracy with only 0.01% of trainable parameters, compared to LoRA's 80.8% accuracy with 0.70% of trainable parameters on LLaMA3-8B. Additionally, we conduct extensive experiments to systematically assess the impact of DenseLoRA's components on overall model performance. Code is available at https://github.com/mulin-ahu/DenseLoRA.

cs.CL↗

arXiv2025

Parrot: Multilingual Visual Instruction Tuning

The rapid development of Multimodal Large Language Models (MLLMs), such as GPT-4o, marks a significant step toward artificial general intelligence. Existing methods typically align vision encoders with LLMs via supervised fine-tuning (SFT), but this often deteriorates their ability to handle multiple languages as training progresses. We empirically observe that imbalanced SFT datasets, largely English-centric, degrade performance on non-English languages due to the failure in multilingual token alignment. To address this, we propose PARROT, a novel approach that leverages textual guidance for visual token alignment at the language level. PARROT conditions visual tokens on diverse language inputs and uses Mixture-of-Experts (MoE) to align multilingual tokens. By computing cross-attention between initial visual features and textual embeddings, we select the most relevant experts, converting visual tokens into language-specific representations. Additionally, we introduce the Massive Multilingual Multimodal Benchmark (MMMB), a new benchmark comprising 6 languages, 15 categories, and 12,000 questions, to assess multilingual capabilities. PARROT achieves state-of-the-art performance on both the multilingual benchmarks and a wide range of multimodal tasks. Code and dataset are available at: https://github.com/AIDC-AI/Parrot

cs.CV↗

arXiv2025

Coherent Control of Ion-Photoelectron Dynamics through Rabi Oscillations: An ab initio study

We present first-principles numerical simulations of photoionization in neon induced by bichromatic extreme ultraviolet pulses with frequencies $ω$ and $2ω$, specially chosen to make $ω$ equal to the energy difference between the $2s$ and $2p$ subshells. This allows for the production of photoelectrons from the $2s$ shell by $2ω$ pulse and from the $2p$ shell by $ω$ pulse with the same energy. Using the multi-configurational time-dependent Hartree-Fock method, we explore how Rabi coupling between subshells generates coherence between the corresponding photoelectron wave packets. Our \textit{ab initio} calculations confirm the analytical results derived from the essential-states approach in [K. L. Ishikawa, K. C. Prince, and K. Ueda, J. Phys. Chem. A 127, 10638 (2023)], validating the theoretical predictions. Although we focus on the Ne $2p$ and $2s$ subshells, our approach is applicable to a broad range of systems exhibiting photoionization from multiple subshells. The laser parameters employed in our simulations are available in modern Free Electron Lasers (FELs), and we anticipate that this work could stimulate experimental investigations using FELs to study ion-photoelectron coherence and entanglement.

physics.atom-ph↗

arXiv2025

REGen: Multimodal Retrieval-Embedded Generation for Long-to-Short Video Editing

Short videos are an effective tool for promoting contents and improving knowledge accessibility. While existing extractive video summarization methods struggle to produce a coherent narrative, existing abstractive methods cannot `quote' from the input videos, i.e., inserting short video clips in their outputs. In this work, we explore novel video editing models for generating shorts that feature a coherent narrative with embedded video insertions extracted from a long input video. We propose a novel retrieval-embedded generation framework that allows a large language model to quote multimodal resources while maintaining a coherent narrative. Our proposed REGen system first generates the output story script with quote placeholders using a finetuned large language model, and then uses a novel retrieval model to replace the quote placeholders by selecting a video clip that best supports the narrative from a pool of candidate quotable video clips. We examine the proposed method on the task of documentary teaser generation, where short interview insertions are commonly used to support the narrative of a documentary. Our objective evaluations show that the proposed method can effectively insert short video clips while maintaining a coherent narrative. In a subjective survey, we show that our proposed method outperforms existing abstractive and extractive approaches in terms of coherence, alignment, and realism in teaser generation.

cs.CV↗

arXiv2025

Visual Prompting with Iterative Refinement for Design Critique Generation

Feedback is crucial for every design process, such as user interface (UI) design, and automating design critiques can significantly improve the efficiency of the design workflow. Although existing multimodal large language models (LLMs) excel in many tasks, they often struggle with generating high-quality design critiques -- a complex task that requires producing detailed design comments that are visually grounded in a given design's image. Building on recent advancements in iterative refinement of text output and visual prompting methods, we propose an iterative visual prompting approach for UI critique that takes an input UI screenshot and design guidelines and generates a list of design comments, along with corresponding bounding boxes that map each comment to a specific region in the screenshot. The entire process is driven completely by LLMs, which iteratively refine both the text output and bounding boxes using few-shot samples tailored for each step. We evaluated our approach using Gemini-1.5-pro and GPT-4o, and found that human experts generally preferred the design critiques generated by our pipeline over those by the baseline, with the pipeline reducing the gap from human performance by 50% for one rating metric. To assess the generalizability of our approach to other multimodal tasks, we applied our pipeline to open-vocabulary object and attribute detection, and experiments showed that our method also outperformed the baseline.

cs.AI↗

arXiv2025

FlowHFT: Imitation Learning via Flow Matching Policy for Optimal High-Frequency Trading under Diverse Market Conditions

High-frequency trading (HFT) is an investing strategy that continuously monitors market states and places bid and ask orders at millisecond speeds. Traditional HFT approaches fit models with historical data and assume that future market states follow similar patterns. This limits the effectiveness of any single model to the specific conditions it was trained for. Additionally, these models achieve optimal solutions only under specific market conditions, such as assumptions about stock price's stochastic process, stable order flow, and the absence of sudden volatility. Real-world markets, however, are dynamic, diverse, and frequently volatile. To address these challenges, we propose the FlowHFT, a novel imitation learning framework based on flow matching policy. FlowHFT simultaneously learns strategies from numerous expert models, each proficient in particular market scenarios. As a result, our framework can adaptively adjust investment decisions according to the prevailing market state. Furthermore, FlowHFT incorporates a grid-search fine-tuning mechanism. This allows it to refine strategies and achieve superior performance even in complex or extreme market scenarios where expert strategies may be suboptimal. We test FlowHFT in multiple market environments. We first show that flow matching policy is applicable in stochastic market environments, thus enabling FlowHFT to learn trading strategies under different market conditions. Notably, our single framework consistently achieves performance superior to the best expert for each market condition.

q-fin.TR↗

arXiv2025

P3P: Pseudo-3D Pre-training for Scaling 3D Voxel-based Masked Autoencoders

3D pre-training is crucial to 3D perception tasks. Nevertheless, limited by the difficulties in collecting clean and complete 3D data, 3D pre-training has persistently faced data scaling challenges. In this work, we introduce a novel self-supervised pre-training framework that incorporates millions of images into 3D pre-training corpora by leveraging a large depth estimation model. New pre-training corpora encounter new challenges in representation ability and embedding efficiency of models. Previous pre-training methods rely on farthest point sampling and k-nearest neighbors to embed a fixed number of 3D tokens. However, these approaches prove inadequate when it comes to embedding millions of samples that feature a diverse range of point numbers, spanning from 1,000 to 100,000. In contrast, we propose a tokenizer with linear-time complexity, which enables the efficient embedding of a flexible number of tokens. Accordingly, a new 3D reconstruction target is proposed to cooperate with our 3D tokenizer. Our method achieves state-of-the-art performance in 3D classification, few-shot learning, and 3D segmentation. Code is available at https://github.com/XuechaoChen/P3P-MAE.

cs.CV↗

arXiv2025

Reachable Sets-based Trajectory Planning Combining Reinforcement Learning and iLQR

The driving risk field is applicable to more complex driving scenarios, providing new approaches for safety decision-making and active vehicle control in intricate environments. However, existing research often overlooks the driving risk field and fails to consider the impact of risk distribution within drivable areas on trajectory planning, which poses challenges for enhancing safety. This paper proposes a trajectory planning method for intelligent vehicles based on the risk reachable set to further improve the safety of trajectory planning. First, we construct the reachable set incorporating the driving risk field to more accurately assess and avoid potential risks in drivable areas. Then, the initial trajectory is generated based on safe reinforcement learning and projected onto the reachable set. Finally, we introduce a trajectory planning method based on a constrained iterative quadratic regulator to optimize the initial solution, ensuring that the planned trajectory achieves optimal comfort, safety, and efficiency. We conduct simulation tests of trajectory planning in high-speed lane-changing scenarios. The results indicate that the proposed method can guarantee trajectory comfort and driving efficiency, with the generated trajectory situated outside high-risk boundaries, thereby ensuring vehicle safety during operation.

eess.SY↗

arXiv2025

EcomScriptBench: A Multi-task Benchmark for E-commerce Script Planning via Step-wise Intention-Driven Product Association

Goal-oriented script planning, or the ability to devise coherent sequences of actions toward specific goals, is commonly employed by humans to plan for typical activities. In e-commerce, customers increasingly seek LLM-based assistants to generate scripts and recommend products at each step, thereby facilitating convenient and efficient shopping experiences. However, this capability remains underexplored due to several challenges, including the inability of LLMs to simultaneously conduct script planning and product retrieval, difficulties in matching products caused by semantic discrepancies between planned actions and search queries, and a lack of methods and benchmark data for evaluation. In this paper, we step forward by formally defining the task of E-commerce Script Planning (EcomScript) as three sequential subtasks. We propose a novel framework that enables the scalable generation of product-enriched scripts by associating products with each step based on the semantic similarity between the actions and their purchase intentions. By applying our framework to real-world e-commerce data, we construct the very first large-scale EcomScript dataset, EcomScriptBench, which includes 605,229 scripts sourced from 2.4 million products. Human annotations are then conducted to provide gold labels for a sampled subset, forming an evaluation benchmark. Extensive experiments reveal that current (L)LMs face significant challenges with EcomScript tasks, even after fine-tuning, while injecting product purchase intentions improves their performance.

cs.CL↗

arXiv2025

Numerical simulations on First-order phase transition through thermal fluctuation

In this Letter, we numerically present the possibility of the first-order phase transition occurring through the thermal fluctuation in the early universe. We find that when the temperature is slightly higher than the mass scale of the background field, the bubble-like field configurations appear proceeded by oscillons, which expand and collide to finish the phase transition. We provide the false vacuum decay rate and the accompanied gravitational waves. We also present the vacuum phase transition comparison of the quantum tunneling case and thermal fluctuation case.

hep-ph↗

arXiv2025

LMP: Leveraging Motion Prior in Zero-Shot Video Generation with Diffusion Transformer

In recent years, large-scale pre-trained diffusion transformer models have made significant progress in video generation. While current DiT models can produce high-definition, high-frame-rate, and highly diverse videos, there is a lack of fine-grained control over the video content. Controlling the motion of subjects in videos using only prompts is challenging, especially when it comes to describing complex movements. Further, existing methods fail to control the motion in image-to-video generation, as the subject in the reference image often differs from the subject in the reference video in terms of initial position, size, and shape. To address this, we propose the Leveraging Motion Prior (LMP) framework for zero-shot video generation. Our framework harnesses the powerful generative capabilities of pre-trained diffusion transformers to enable motion in the generated videos to reference user-provided motion videos in both text-to-video and image-to-video generation. To this end, we first introduce a foreground-background disentangle module to distinguish between moving subjects and backgrounds in the reference video, preventing interference in the target video generation. A reweighted motion transfer module is designed to allow the target video to reference the motion from the reference video. To avoid interference from the subject in the reference video, we propose an appearance separation module to suppress the appearance of the reference subject in the target video. We annotate the DAVIS dataset with detailed prompts for our experiments and design evaluation metrics to validate the effectiveness of our method. Extensive experiments demonstrate that our approach achieves state-of-the-art performance in generation quality, prompt-video consistency, and control capability. Our homepage is available at https://vpx-ecnu.github.io/LMP-Website/

cs.CV↗

arXiv2025

Covariant analysis of electromagnetic current on the light cone: exposition with scalar Yukawa theory

We present the first systematic investigation of the Lorentz covariance of the charge form factor for a strongly coupled scalar theory in (3+1)-dimensions. Our results are based on the first non-perturbative solution of the scalar Yukawa theory with a Fock sector expansion including up to thee-particles (one mock nucleon plus two mock pions or two mock nucleons plus one mock anti-nucleon). The light-front Hamiltonian is constructed and renormalized using a Fock sector dependent scheme. The derived eigenvalue equation is then solved non-perturbatively to obtain the wave functions, which are then used to compute the current matrix element. We perform a covariant analysis of the current matrix element taking into account possible violation of the Poincaré symmetry due to the Fock sector truncation. The physical form factor depends on two boost invariants $ζ, Δ^2_\perp$, instead of the single Lorentz invariant $Q^2$. Instead of adopting the conventional Drell-Yan frame $ζ= 0$, we evaluate the form factor in general frames, and use the frame dependence to quantitatively gauge the loss of the Lorentz covariance. Our numerical result shows that as more Fock sectors are included, the frame dependence reduces dramatically. In particular, the anti-nucleon degree of freedom plays an important role in the reduction of the frame dependence, even though it only takes a small portion within the state vector. We also find that there is no zero-mode contribution to the current for the scalar Yukawa theory.

hep-ph↗

arXiv2025

The GenUI Study: Exploring the Design of Generative UI Tools to Support UX Practitioners and Beyond

AI can now generate high-fidelity UI mock-up screens from a high-level textual description, promising to support UX practitioners' work. However, it remains unclear how UX practitioners would adopt such Generative UI (GenUI) models in a way that is integral and beneficial to their work. To answer this question, we conducted a formative study with 37 UX-related professionals that consisted of four roles: UX designers, UX researchers, software engineers, and product managers. Using a state-of-the-art GenUI tool, each participant went through a week-long, individual mini-project exercise with role-specific tasks, keeping a daily journal of their usage and experiences with GenUI, followed by a semi-structured interview. We report findings on participants' workflow using the GenUI tool, how GenUI can support all and each specific roles, and existing gaps between GenUI and users' needs and expectations, which lead to design implications to inform future work on GenUI development.

cs.HC↗

arXiv2025

MPS-Prover: Advancing Stepwise Theorem Proving by Multi-Perspective Search and Data Curation

Automated Theorem Proving (ATP) in formal languages remains a formidable challenge in AI, demanding rigorous logical deduction and navigating vast search spaces. While large language models (LLMs) have shown promising performance, existing stepwise provers often suffer from biased search guidance, leading to inefficiencies and suboptimal proof strategies. This paper introduces the Multi-Perspective Search Prover (MPS-Prover), a novel stepwise ATP system designed to overcome these limitations. MPS-Prover incorporates two key innovations: a highly effective post-training data curation strategy that prunes approximately 40% of redundant training data without sacrificing performance, and a multi-perspective tree search mechanism. This search integrates a learned critic model with strategically designed heuristic rules to diversify tactic selection, prevent getting trapped in unproductive states, and enhance search robustness. Extensive evaluations demonstrate that MPS-Prover achieves state-of-the-art performance on multiple challenging benchmarks, including miniF2F and ProofNet, outperforming prior 7B parameter models. Furthermore, our analyses reveal that MPS-Prover generates significantly shorter and more diverse proofs compared to existing stepwise and whole-proof methods, highlighting its efficiency and efficacy. Our work advances the capabilities of LLM-based formal reasoning and offers a robust framework and a comprehensive analysis for developing more powerful theorem provers.

cs.AI↗