Search Results for author:
Found 30 papers, 20 papers with code
Inductive Spatio-Temporal Kriging with Physics-Guided Increment Training Strategy for Air Quality Inference
Inductive spatio-temporal kriging with increment training strategy has demonstrated its effectiveness using virtual nodes to simulate unobserved nodes.
Textured 3D Regenerative Morphing with 3D Diffusion Prior
Unlike previous methods that depend on explicit correspondences and deformations, our method eliminates the additional need for obtaining correspondence and uses the 3D diffusion prior to generate morphing.
ARFlow: Autogressive Flow with Hybrid Linear Attention
Flow models are effective at progressively generating realistic images, but they generally struggle to capture long-range dependencies during the generation process as they compress all the information from previous time steps into a single corrupted image.
Gated Delta Networks: Improving Mamba2 with Delta Rule
Linear Transformers have gained attention as efficient alternatives to standard Transformers, but their performance in retrieval and long-context tasks has been limited.
Stick-breaking Attention
We propose an alternative attention mechanism based on the stick-breaking process: For each token before the current, we determine a break point $\beta_{i, j}$, which represents the proportion of the remaining stick to allocate to the current token.
A Controlled Study on Long Context Extension and Generalization in LLMs
Broad textual understanding and in-context learning require language models that utilize full document contexts.
Gated Slot Attention for Efficient Linear-Time Sequence Modeling
Linear attention Transformers and their gated variants, celebrated for enabling parallel training and efficient recurrent inference, still fall short in recall-intensive tasks compared to traditional Transformers and demand significant resources for training from scratch.
Parallelizing Linear Transformers with the Delta Rule over Sequence Length
Transformers with linear attention (i. e., linear transformers) and state-space models have recently been suggested as a viable linear-time alternative to transformers with softmax attention.
Probing Unlearned Diffusion Models: A Transferable Adversarial Attack Perspective
Specifically, we employ an adversarial search strategy to search for the adversarial embedding which can transfer across different unlearned models.
Counterfactual Explanations for Face Forgery Detection via Adversarial Removal of Artifacts
We verify the effectiveness of the proposed explanations from two aspects: (1) Counterfactual Trace Visualization: the enhanced forgery images are useful to reveal artifacts by visually contrasting the original images and two different visualization methods; (2) Transferable Adversarial Attacks: the adversarial forgery images generated by attacking the detection model are able to mislead other detection models, implying the removed artifacts are general.
HGRN2: Gated Linear RNNs with State Expansion
Hierarchically gated linear RNN (HGRN, \citealt{HGRN}) has demonstrated competitive training speed and performance in language modeling while offering efficient inference.
Beyond Inserting: Learning Identity Embedding for Semantic-Fidelity Personalized Diffusion Generation
The previous methods either failed to accurately fit the face region or lost the interactive generative ability with other existing concepts in T2I models.
Is It Possible to Backdoor Face Forgery Detection with Natural Triggers?
To further investigate natural triggers, we propose a novel analysis-by-synthesis backdoor attack against face forgery detection models, which embeds natural triggers in the latent space.
Learning Dense Correspondence for NeRF-Based Face Reenactment
Therefore, we are inspired to ask: Can we learn the dense correspondence between different NeRF-based face representations without a 3D parametric model prior?
Gated Linear Attention Transformers with Hardware-Efficient Training
When used as a replacement for the standard attention layer in Transformers, the resulting gated linear attention (GLA) Transformer is found to perform competitively against the LLaMA-architecture Transformer (Touvron et al., 2023) as well recent linear-time-inference baselines such as RetNet (Sun et al., 2023a) and Mamba (Gu & Dao, 2023) on moderate-scale language modeling experiments.
Joint Entity and Relation Extraction with Span Pruning and Hypergraph Neural Networks
Also, most of current ERE models do not take into account higher-order interactions between multiple entities and relations, while higher-order modeling could be beneficial. In this work, we propose HyperGraph neural network for ERE ($\hgnn{}$), which is built upon the PL-marker (a state-of-the-art marker-based pipleline model).
Simple Hardware-Efficient PCFGs with Independent Left and Right Productions
Scaling dense PCFGs to thousands of nonterminals via a low-rank parameterization of the rule probability tensor has been shown to be beneficial for unsupervised parsing.
Designing a 3D-Aware StyleNeRF Encoder for Face Editing
For more flexible face manipulation, we then design a dual-branch StyleFlow module to transfer the StyleNeRF codes with disentangled geometry and texture flows.
Unsupervised Discontinuous Constituency Parsing with Mildly Context-Sensitive Grammars
We study grammar induction with mildly context-sensitive grammars for unsupervised discontinuous parsing.
Exposing Fine-Grained Adversarial Vulnerability of Face Anti-Spoofing Models
These fine-grained adversarial examples can be used for selecting robust backbone networks and auxiliary features.
Dynamic Programming in Rank Space: Scaling Structured Inference with Low-Rank HMMs and PCFGs
Recent research found it beneficial to use large state spaces for HMMs and PCFGs.
Modeling Label Correlations for Second-Order Semantic Dependency Parsing with Mean-Field Inference
Second-order semantic parsing with end-to-end mean-field inference has been shown good performance.
Nested Named Entity Recognition as Latent Lexicalized Constituency Parsing
They treat nested entities as partially-observed constituency trees and propose the masked inside algorithm for partial marginalization.
Bottom-Up Constituency Parsing and Nested Named Entity Recognition with Pointer Networks
Constituency parsing and nested named entity recognition (NER) are similar tasks since they both aim to predict a collection of nested and non-crossing spans.
Combining (second-order) graph-based and headed-span-based projective dependency parsing
Graph-based methods, which decompose the score of a dependency tree into scores of dependency arcs, are popular in dependency parsing for decades.
Headed-Span-Based Projective Dependency Parsing
In a projective dependency tree, the largest subtree rooted at each word covers a contiguous sequence (i. e., a span) in the surface order.
A Systematical Solution for Face De-identification
Through this, we can construct unrestricted adversarial image to decrease ID similarity recognized by model.
Neural Bi-Lexicalized PCFG Induction
Neural lexicalized PCFGs (L-PCFGs) have been shown effective in grammar induction.
PCFGs Can Do Better: Inducing Probabilistic Context-Free Grammars with Many Symbols
In this work, we present a new parameterization form of PCFGs based on tensor decomposition, which has at most quadratic computational complexity in the symbol number and therefore allows us to use a much larger number of symbols.
Second-Order Unsupervised Neural Dependency Parsing
Inspired by second-order supervised dependency parsing, we proposed a second-order extension of unsupervised neural dependency models that incorporate grandparent-child or sibling information.
Ranked #1 on
Dependency Grammar Induction
on WSJ10
