Viral News

Conditional regression for the Nonlinear Single-Variable Model

Conditional regression for the Nonlinear Single-Variable Model

arXiv:2411.09686v1 Announce Type: cross Abstract: Several statistical models for regression of a function $F$ on $mathbb{R}^d$ without the statistical and computational curse of dimensionality exist, for example by imposing and exploiting geometric assumptions on the distribution of the data (e.g. that its support is low-dimensional), or strong smoothness assumptions on $F$, or a special structure $F$. Among the latter, compositional models assume $F=fcirc g$ with $g$ mapping to $mathbb{R}^r$ with $rll d$, have been studied, and include classical single- and multi-index models and recent works on neural networks. While the case where $g$ is linear is rather well-understood, much less…
Read More
MikuDance: Animating Character Art with Mixed Motion Dynamics

MikuDance: Animating Character Art with Mixed Motion Dynamics

[Submitted on 13 Nov 2024 (v1), last revised 14 Nov 2024 (this version, v2)] View a PDF of the paper titled MikuDance: Animating Character Art with Mixed Motion Dynamics, by Jiaxu Zhang and 5 other authors View PDF HTML (experimental) Abstract:We propose MikuDance, a diffusion-based pipeline incorporating mixed motion dynamics to animate stylized character art. MikuDance consists of two key techniques: Mixed Motion Modeling and Mixed-Control Diffusion, to address the challenges of high-dynamic motion and reference-guidance misalignment in character art animation. Specifically, a Scene Motion Tracking strategy is presented to explicitly model the dynamic camera in pixel-wise space, enabling unified…
Read More
Not All Heads Matter: A Head-Level KV Cache Compression Method with Integrated Retrieval and Reasoning

Not All Heads Matter: A Head-Level KV Cache Compression Method with Integrated Retrieval and Reasoning

[Submitted on 25 Oct 2024 (v1), last revised 14 Nov 2024 (this version, v3)] View a PDF of the paper titled Not All Heads Matter: A Head-Level KV Cache Compression Method with Integrated Retrieval and Reasoning, by Yu Fu and 5 other authors View PDF HTML (experimental) Abstract:Key-Value (KV) caching is a common technique to enhance the computational efficiency of Large Language Models (LLMs), but its memory overhead grows rapidly with input length. Prior work has shown that not all tokens are equally important for text generation, proposing layer-level KV cache compression to selectively retain key information. Recognizing the distinct…
Read More
Stable Consistency Tuning: Understanding and Improving Consistency Models

Stable Consistency Tuning: Understanding and Improving Consistency Models

[Submitted on 24 Oct 2024 (v1), last revised 14 Nov 2024 (this version, v2)] View a PDF of the paper titled Stable Consistency Tuning: Understanding and Improving Consistency Models, by Fu-Yun Wang and 2 other authors View PDF HTML (experimental) Abstract:Diffusion models achieve superior generation quality but suffer from slow generation speed due to the iterative nature of denoising. In contrast, consistency models, a new generative family, achieve competitive performance with significantly faster sampling. These models are trained either through consistency distillation, which leverages pretrained diffusion models, or consistency training/tuning directly from raw data. In this work, we propose a…
Read More
ROCKET-1: Mastering Open-World Interaction with Visual-Temporal Context Prompting

ROCKET-1: Mastering Open-World Interaction with Visual-Temporal Context Prompting

[Submitted on 23 Oct 2024 (v1), last revised 14 Nov 2024 (this version, v2)] View a PDF of the paper titled ROCKET-1: Mastering Open-World Interaction with Visual-Temporal Context Prompting, by Shaofei Cai and 6 other authors View PDF HTML (experimental) Abstract:Vision-language models (VLMs) have excelled in multimodal tasks, but adapting them to embodied decision-making in open-world environments presents challenges. One critical issue is bridging the gap between discrete entities in low-level observations and the abstract concepts required for effective planning. A common solution is building hierarchical agents, where VLMs serve as high-level reasoners that break down tasks into executable sub-tasks,…
Read More
AutoDefense: Multi-Agent LLM Defense against Jailbreak Attacks

AutoDefense: Multi-Agent LLM Defense against Jailbreak Attacks

[Submitted on 2 Mar 2024 (v1), last revised 14 Nov 2024 (this version, v2)] View a PDF of the paper titled AutoDefense: Multi-Agent LLM Defense against Jailbreak Attacks, by Yifan Zeng and 4 other authors View PDF HTML (experimental) Abstract:Despite extensive pre-training in moral alignment to prevent generating harmful information, large language models (LLMs) remain vulnerable to jailbreak attacks. In this paper, we propose AutoDefense, a multi-agent defense framework that filters harmful responses from LLMs. With the response-filtering mechanism, our framework is robust against different jailbreak attack prompts, and can be used to defend different victim models. AutoDefense assigns different…
Read More
SDDBench: A Benchmark for Synthesizable Drug Design

SDDBench: A Benchmark for Synthesizable Drug Design

arXiv:2411.08306v1 Announce Type: new Abstract: A significant challenge in wet lab experiments with current drug design generative models is the trade-off between pharmacological properties and synthesizability. Molecules predicted to have highly desirable properties are often difficult to synthesize, while those that are easily synthesizable tend to exhibit less favorable properties. As a result, evaluating the synthesizability of molecules in general drug design scenarios remains a significant challenge in the field of drug discovery. The commonly used synthetic accessibility (SA) score aims to evaluate the ease of synthesizing generated molecules, but it falls short of guaranteeing that synthetic routes can actually…
Read More
4D Gaussian Splatting in the Wild with Uncertainty-Aware Regularization

4D Gaussian Splatting in the Wild with Uncertainty-Aware Regularization

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs. Source link lol
Read More
CorrSynth — A Correlated Sampling Method for Diverse Dataset Generation from LLMs

CorrSynth — A Correlated Sampling Method for Diverse Dataset Generation from LLMs

arXiv:2411.08553v1 Announce Type: new Abstract: Large language models (LLMs) have demonstrated remarkable performance in diverse tasks using zero-shot and few-shot prompting. Even though their capabilities of data synthesis have been studied well in recent years, the generated data suffers from a lack of diversity, less adherence to the prompt, and potential biases that creep into the data from the generator model. In this work, we tackle the challenge of generating datasets with high diversity, upon which a student model is trained for downstream tasks. Taking the route of decoding-time guidance-based approaches, we propose CorrSynth, which generates data that is more…
Read More
Rethinking Distribution Shifts: Empirical Analysis and Inductive Modeling for Tabular Data

Rethinking Distribution Shifts: Empirical Analysis and Inductive Modeling for Tabular Data

[Submitted on 11 Jul 2023 (v1), last revised 13 Nov 2024 (this version, v4)] View a PDF of the paper titled Rethinking Distribution Shifts: Empirical Analysis and Inductive Modeling for Tabular Data, by Jiashuo Liu and 3 other authors View PDF Abstract:Different distribution shifts require different interventions, and algorithms must be grounded in the specific shifts they address. However, methodological development for robust algorithms typically relies on structural assumptions that lack empirical validation. Advocating for an empirically grounded data-driven approach to research, we build an empirical testbed comprising natural shifts across 5 tabular datasets and 60,000 method configurations encompassing imbalanced…
Read More
No widgets found. Go to Widget page and add the widget in Offcanvas Sidebar Widget Area.