arXiv subjects

Jussi Keppo

Publications and source records attributed to Jussi Keppo.

14 recordsLinked to original sources

arXiv2026

Trusting AI in Competitive Markets

People's trust in AI advice diverges as they use it, deepening for some and eroding for others. We study this divergence in oligopoly pricing, where advice cannot prove itself: rivals' responses decide whether it pays off. In a laboratory experiment, 273 sellers compete across 91 three-seller markets over 30 rounds; we vary the presence of AI pricing recommendations and the gender composition of the market (female-only, male-only, or mixed). We find that the gender composition of the market shapes how sellers learn from the advice, and where prices settle as a result. In female-only markets, recommendations raise prices by 29% and profits by 39%; in male-only and mixed-gender markets, they have no significant effect. A Non-Homogeneous Hidden Markov Model reveals a composition-specific dynamic association: profitable rounds predict rising adherence to the AI in female-only markets and declining adherence otherwise, a pattern consistent with learned trust and self-serving attribution. The pattern reverses what recent evidence on gender and AI would predict. We discuss implications for platform governance and regulatory oversight, which should focus not only on the algorithm but on the human side that shapes its effects.

cs.GT↗

arXiv2026

On the Fragility of AI Agent Collusion

Recent work shows that pricing with symmetric LLM agents leads to algorithmic collusion. We show that collusion is fragile under the heterogeneity typical of real deployments. In a stylized repeated-pricing model, heterogeneity in patience or data access reduces the set of collusive equilibria. Experiments with open-source LLM agents (totaling over 2,000 compute hours) align with these predictions: patience heterogeneity reduces price lift from 22% to 10% above competitive levels; asymmetric data access, to 7%. Increasing the number of competing LLMs breaks up collusion; so does cross-algorithm heterogeneity, that is, setting LLMs against Q-learning agents. But model-size differences (e.g., 32B vs. 14B weights) do not; they generate leader-follower dynamics that stabilize collusion. We discuss antitrust implications, such as enforcement actions restricting data-sharing and policies promoting algorithmic diversity.

cs.GT↗

arXiv2025

Three Tiers and Thresholds: Incentives in Private Market Investing

This paper studies optimal contract design in private market investing, focusing on internal decision making in venture capital and private equity firms. A principal relies on an agent who privately exerts costly due diligence effort and then recommends whether to invest. Outcomes are observable ex post even when an opportunity is declined, allowing compensation to reward both successful investments and prudent decisions to pass. We characterize profit maximizing contracts that induce information acquisition and truthful reporting. We show that three tier contracts are sufficient, with payments contingent on the agent's recommendation and the realized return. In symmetric environments satisfying the monotone likelihood ratio property, the optimal contract further simplifies to a threshold contract that pays only when the recommendation is aligned with an extreme realized return. These results provide guidance for performance based compensation that promotes diligent screening while limiting excessive risk taking.

cs.GT↗

arXiv2024

CroCoDai: A Stablecoin for Cross-Chain Commerce

Decentralized Finance (DeFi), in which digital assets are exchanged without trusted intermediaries, has grown rapidly in value in recent years. The global DeFi ecosystem is fragmented into multiple blockchains, fueling the demand for cross-chain commerce. Existing approaches for cross-chain transactions, e.g., bridges and cross-chain deals, achieve atomicity by locking assets in escrow. However, locking up assets increases the financial risks for the participants, especially due to price fluctuations and the long latency of cross-chain transactions. Stablecoins, which are pegged to a non-volatile asset such as the US dollar, help mitigate the risk associated with price fluctuations. However, existing stablecoin designs are tied to individual blockchain platforms, and trusted parties or complex protocols are needed to exchange stablecoin tokens between blockchains. Our goal is to design a practical stablecoin for cross-chain commerce. Realizing this goal requires addressing two challenges. The first challenge is to support a large and growing number of blockchains efficiently. The second challenge is to be resilient to price fluctuations and blockchain platform failures. We present CroCoDai to address these challenges. We also present three prototype implementations of our stablecoin system, and show that it incurs small execution overhead.

cs.CR↗

arXiv2024

Collateral Portfolio Optimization in Crypto-Backed Stablecoins

Stablecoins - crypto tokens whose value is pegged to a real-world asset such as the US Dollar - are an important component of the DeFi ecosystem as they mitigate the impact of token price volatility. In crypto-backed stablecoins, the peg is founded on the guarantee that in case of system shutdown, each stablecoin can be exchanged for a basket of other crypto tokens worth approximately its nominal value. However, price fluctuations that affect the collateral tokens may cause this guarantee to be invalidated. In this work, we investigate the impact of the collateral portfolio's composition on the resilience to this type of catastrophic event. For stablecoins whose developers maintain a significant portion of the collateral (e.g., MakerDAO's Dai), we propose two portfolio optimization methods, based on convex optimization and (semi)variance minimization, that account for the correlation between the various token prices. We compare the optimal portfolios to the historical evolution of Dai's collateral portfolio, and to aid reproducibility, we have made our data and code publicly available.

cs.CR↗

arXiv2024

Instant3D: Instant Text-to-3D Generation

Text-to-3D generation has attracted much attention from the computer vision community. Existing methods mainly optimize a neural field from scratch for each text prompt, relying on heavy and repetitive training cost which impedes their practical deployment. In this paper, we propose a novel framework for fast text-to-3D generation, dubbed Instant3D. Once trained, Instant3D is able to create a 3D object for an unseen text prompt in less than one second with a single run of a feedforward network. We achieve this remarkable speed by devising a new network that directly constructs a 3D triplane from a text prompt. The core innovation of our Instant3D lies in our exploration of strategies to effectively inject text conditions into the network. In particular, we propose to combine three key mechanisms: cross-attention, style injection, and token-to-plane transformation, which collectively ensure precise alignment of the output with the input text. Furthermore, we propose a simple yet effective activation function, the scaled-sigmoid, to replace the original sigmoid function, which speeds up the training convergence by more than ten times. Finally, to address the Janus (multi-head) problem in 3D generation, we propose an adaptive Perp-Neg algorithm that can dynamically adjust its concept negation scales according to the severity of the Janus problem during training, effectively reducing the multi-head effect. Extensive experiments on a wide variety of benchmark datasets demonstrate that the proposed algorithm performs favorably against the state-of-the-art methods both qualitatively and quantitatively, while achieving significantly better efficiency. The code, data, and models are available at https://github.com/ming1993li/Instant3DCodes.

cs.CV↗

arXiv2024

X-Adapter: Adding Universal Compatibility of Plugins for Upgraded Diffusion Model

We introduce X-Adapter, a universal upgrader to enable the pretrained plug-and-play modules (e.g., ControlNet, LoRA) to work directly with the upgraded text-to-image diffusion model (e.g., SDXL) without further retraining. We achieve this goal by training an additional network to control the frozen upgraded model with the new text-image data pairs. In detail, X-Adapter keeps a frozen copy of the old model to preserve the connectors of different plugins. Additionally, X-Adapter adds trainable mapping layers that bridge the decoders from models of different versions for feature remapping. The remapped features will be used as guidance for the upgraded model. To enhance the guidance ability of X-Adapter, we employ a null-text training strategy for the upgraded model. After training, we also introduce a two-stage denoising strategy to align the initial latents of X-Adapter and the upgraded model. Thanks to our strategies, X-Adapter demonstrates universal compatibility with various plugins and also enables plugins of different versions to work together, thereby expanding the functionalities of diffusion community. To verify the effectiveness of the proposed method, we conduct extensive experiments and the results show that X-Adapter may facilitate wider application in the upgraded foundational diffusion model.

cs.CV↗

arXiv2023

DynVideo-E: Harnessing Dynamic NeRF for Large-Scale Motion- and View-Change Human-Centric Video Editing

Despite recent progress in diffusion-based video editing, existing methods are limited to short-length videos due to the contradiction between long-range consistency and frame-wise editing. Prior attempts to address this challenge by introducing video-2D representations encounter significant difficulties with large-scale motion- and view-change videos, especially in human-centric scenarios. To overcome this, we propose to introduce the dynamic Neural Radiance Fields (NeRF) as the innovative video representation, where the editing can be performed in the 3D spaces and propagated to the entire video via the deformation field. To provide consistent and controllable editing, we propose the image-based video-NeRF editing pipeline with a set of innovative designs, including multi-view multi-pose Score Distillation Sampling (SDS) from both the 2D personalized diffusion prior and 3D diffusion prior, reconstruction losses, text-guided local parts super-resolution, and style transfer. Extensive experiments demonstrate that our method, dubbed as DynVideo-E, significantly outperforms SOTA approaches on two challenging datasets by a large margin of 50% ~ 95% for human preference. Code will be released at https://showlab.github.io/DynVideo-E/.

cs.CV↗

arXiv2023

MotionDirector: Motion Customization of Text-to-Video Diffusion Models

Large-scale pre-trained diffusion models have exhibited remarkable capabilities in diverse video generations. Given a set of video clips of the same motion concept, the task of Motion Customization is to adapt existing text-to-video diffusion models to generate videos with this motion. For example, generating a video with a car moving in a prescribed manner under specific camera movements to make a movie, or a video illustrating how a bear would lift weights to inspire creators. Adaptation methods have been developed for customizing appearance like subject or style, yet unexplored for motion. It is straightforward to extend mainstream adaption methods for motion customization, including full model tuning, parameter-efficient tuning of additional layers, and Low-Rank Adaptions (LoRAs). However, the motion concept learned by these methods is often coupled with the limited appearances in the training videos, making it difficult to generalize the customized motion to other appearances. To overcome this challenge, we propose MotionDirector, with a dual-path LoRAs architecture to decouple the learning of appearance and motion. Further, we design a novel appearance-debiased temporal loss to mitigate the influence of appearance on the temporal training objective. Experimental results show the proposed method can generate videos of diverse appearances for the customized motions. Our method also supports various downstream applications, such as the mixing of different videos with their appearance and motion respectively, and animating a single image with customized motions. Our code and model weights will be released.

cs.CV↗

arXiv2023

Gender Animus Can Still Exist Under Favorable Disparate Impact: a Cautionary Tale from Online P2P Lending

This paper investigates gender discrimination and its underlying drivers on a prominent Chinese online peer-to-peer (P2P) lending platform. While existing studies on P2P lending focus on disparate treatment (DT), DT narrowly recognizes direct discrimination and overlooks indirect and proxy discrimination, providing an incomplete picture. In this work, we measure a broadened discrimination notion called disparate impact (DI), which encompasses any disparity in the loan's funding rate that does not commensurate with the actual return rate. We develop a two-stage predictor substitution approach to estimate DI from observational data. Our findings reveal (i) female borrowers, given identical actual return rates, are 3.97% more likely to receive funding, (ii) at least 37.1% of this DI favoring female is indirect or proxy discrimination, and (iii) DT indeed underestimates the overall female favoritism by 44.6%. However, we also identify the overall female favoritism can be explained by one specific discrimination driver, rational statistical discrimination, wherein investors accurately predict the expected return rate from imperfect observations. Furthermore, female borrowers still require 2% higher expected return rate to secure funding, indicating another driver taste-based discrimination co-exists and is against female. These results altogether tell a cautionary tale: on one hand, P2P lending provides a valuable alternative credit market where the affirmative action to support female naturally emerges from the rational crowd; on the other hand, while the overall discrimination effect (both in terms of DI or DT) favors female, concerning taste-based discrimination can persist and can be obscured by other co-existing discrimination drivers, such as statistical discrimination.

cs.CY↗

arXiv2023

HOSNeRF: Dynamic Human-Object-Scene Neural Radiance Fields from a Single Video

We introduce HOSNeRF, a novel 360° free-viewpoint rendering method that reconstructs neural radiance fields for dynamic human-object-scene from a single monocular in-the-wild video. Our method enables pausing the video at any frame and rendering all scene details (dynamic humans, objects, and backgrounds) from arbitrary viewpoints. The first challenge in this task is the complex object motions in human-object interactions, which we tackle by introducing the new object bones into the conventional human skeleton hierarchy to effectively estimate large object deformations in our dynamic human-object model. The second challenge is that humans interact with different objects at different times, for which we introduce two new learnable object state embeddings that can be used as conditions for learning our human-object representation and scene representation, respectively. Extensive experiments show that HOSNeRF significantly outperforms SOTA approaches on two challenging datasets by a large margin of 40% ~ 50% in terms of LPIPS. The code, data, and compelling examples of 360° free-viewpoint renderings from single videos will be released in https://showlab.github.io/HOSNeRF.

cs.CV↗

arXiv2023

STPrivacy: Spatio-Temporal Privacy-Preserving Action Recognition

Existing methods of privacy-preserving action recognition (PPAR) mainly focus on frame-level (spatial) privacy removal through 2D CNNs. Unfortunately, they have two major drawbacks. First, they may compromise temporal dynamics in input videos, which are critical for accurate action recognition. Second, they are vulnerable to practical attacking scenarios where attackers probe for privacy from an entire video rather than individual frames. To address these issues, we propose a novel framework STPrivacy to perform video-level PPAR. For the first time, we introduce vision Transformers into PPAR by treating a video as a tubelet sequence, and accordingly design two complementary mechanisms, i.e., sparsification and anonymization, to remove privacy from a spatio-temporal perspective. In specific, our privacy sparsification mechanism applies adaptive token selection to abandon action-irrelevant tubelets. Then, our anonymization mechanism implicitly manipulates the remaining action-tubelets to erase privacy in the embedding space through adversarial learning. These mechanisms provide significant advantages in terms of privacy preservation for human eyes and action-privacy trade-off adjustment during deployment. We additionally contribute the first two large-scale PPAR benchmarks, VP-HMDB51 and VP-UCF101, to the community. Extensive evaluations on them, as well as two other tasks, validate the effectiveness and generalization capability of our framework.

cs.CV↗

arXiv2022

DeVRF: Fast Deformable Voxel Radiance Fields for Dynamic Scenes

Modeling dynamic scenes is important for many applications such as virtual reality and telepresence. Despite achieving unprecedented fidelity for novel view synthesis in dynamic scenes, existing methods based on Neural Radiance Fields (NeRF) suffer from slow convergence (i.e., model training time measured in days). In this paper, we present DeVRF, a novel representation to accelerate learning dynamic radiance fields. The core of DeVRF is to model both the 3D canonical space and 4D deformation field of a dynamic, non-rigid scene with explicit and discrete voxel-based representations. However, it is quite challenging to train such a representation which has a large number of model parameters, often resulting in overfitting issues. To overcome this challenge, we devise a novel static-to-dynamic learning paradigm together with a new data capture setup that is convenient to deploy in practice. This paradigm unlocks efficient learning of deformable radiance fields via utilizing the 3D volumetric canonical space learnt from multi-view static images to ease the learning of 4D voxel deformation field with only few-view dynamic sequences. To further improve the efficiency of our DeVRF and its synthesized novel view's quality, we conduct thorough explorations and identify a set of strategies. We evaluate DeVRF on both synthetic and real-world dynamic scenes with different types of deformation. Experiments demonstrate that DeVRF achieves two orders of magnitude speedup (100x faster) with on-par high-fidelity results compared to the previous state-of-the-art approaches. The code and dataset will be released in https://github.com/showlab/DeVRF.

cs.CV↗

arXiv2019

Discrete dividend payments in continuous time

We propose a model in which dividend payments occur at regular, deterministic intervals in an otherwise continuous model. This contrasts traditional models where either the payment of continuous dividends is controlled or the dynamics are given by discrete time processes. Moreover, between two dividend payments, the structure allows for other types of control; we consider the possibility of equity issuance at any point in time. The value is characterized as the fixed point of an optimal control problem with periodic initial and terminal conditions. We prove the regularity and uniqueness of the corresponding dynamic programming equation, and the convergence of an efficient numerical algorithm that we use to study the problem. The model enables us to find the loss caused by infrequent dividend payments. We show that under realistic parameter values this loss varies from around 1% to 24% depending on the state of the system, and that using the optimal policy from the continuous problem further increases the loss.

math.OC↗