Search Results for author:
Found 52 papers, 26 papers with code
FlexCAD: Unified and Versatile Controllable CAD Generation with Fine-tuned Large Language Models
First, to enhance comprehension by LLMs, we represent a CAD model as a structured text by abstracting each hierarchy as a sequence of text tokens.
Enhancing Multiple Dimensions of Trustworthiness in LLMs via Sparse Activation Control
This technique leverages semantic features to control the representation of LLM's intermediate hidden states, enabling the model to meet specific requirements such as increased honesty or heightened safety awareness.
SciPIP: An LLM-based Scientific Paper Idea Proposer
Based on a user-provided research background, SciPIP retrieves helpful papers from a literature database while leveraging the capabilities of LLMs to generate more novel and feasible ideas.
Delving into the Reversal Curse: How Far Can Large Language Models Generalize?
(2) This generalization ability is highly correlated to the structure of the fact "A is B" in the training documents.
From Yes-Men to Truth-Tellers: Addressing Sycophancy in Large Language Models with Pinpoint Tuning
Recent works propose to employ supervised fine-tuning (SFT) to mitigate the sycophancy issue, while it typically leads to the degeneration of LLMs' general capability.
Adapt2Reward: Adapting Video-Language Models to Generalizable Robotic Rewards via Failure Prompts
Central to the reinforcement learning and planning for such robotic agents is a generalizable reward function.
PD-APE: A Parallel Decoding Framework with Adaptive Position Encoding for 3D Visual Grounding
Specifically, in the target object branch, the decoder processes text tokens that describe features of the target object (e. g., category and color), guiding the queries to pay attention to the target object itself.
Towards Fundamentally Scalable Model Selection: Asymptotically Fast Update and Selection
Firstly, we define isolated model embedding, a family of model selection schemes supporting asymptotically fast update and selection: With respect to the number of candidate models $m$, the update complexity is O(1) and the selection consists of a single sweep over $m$ vectors in addition to O(1) model operations.
From Redundancy to Relevance: Information Flow in LVLMs Across Reasoning Tasks
Large Vision Language Models (LVLMs) achieve great performance on visual-language reasoning tasks, however, the black-box nature of LVLMs hinders in-depth research on the reasoning mechanism.
Pseudo Label Refinery for Unsupervised Domain Adaptation on Cross-dataset 3D Object Detection
Specifically, in the selection process, to improve the reliability of pseudo boxes, we propose a complementary augmentation strategy.
G2LTraj: A Global-to-Local Generation Approach for Trajectory Prediction
Finally, to ensure the optimal granularity of key steps, we design a selectable granularity strategy that caters to each predicted trajectory.
Model Compression and Efficient Inference for Large Language Models: A Survey
However, Large language models have two prominent characteristics compared to smaller models: (1) Most of compression algorithms require finetuning or even retraining the model after compression.
Regulating Intermediate 3D Features for Vision-Centric Autonomous Driving
To resolve this problem, we propose to regulate intermediate dense 3D features with the help of volume rendering.
To be or not to be? an exploration of continuously controllable prompt engineering
In response, we introduce ControlPE (Continuously Controllable Prompt Engineering).
Few-shot Hybrid Domain Adaptation of Image Generators
Concretely, the distance loss blends the attributes of all target domains by reducing the distances from generated images to all target subspaces.
Concise and Organized Perception Facilitates Reasoning in Large Language Models
Exploiting large language models (LLMs) to tackle reasoning has garnered growing attention.
Robustness of AI-Image Detectors: Fundamental Limits and Practical Attacks
Moreover, we show that watermarking methods are vulnerable to spoofing attacks where the attacker aims to have real images identified as watermarked ones, damaging the reputation of the developers.
M$^3$CS: Multi-Target Masked Point Modeling with Learnable Codebook and Siamese Decoders
Specifically, with masked point cloud as input, M$^3$CS introduces two decoders to predict masked representations and the original points simultaneously.
MonoNeRD: NeRF-like Representations for Monocular 3D Object Detection
To the best of our knowledge, this work is the first to introduce volume rendering for M3D, and demonstrates the potential of implicit reconstruction for image-based 3D perception.
A Study of Unsupervised Evaluation Metrics for Practical and Automatic Domain Adaptation
Unsupervised domain adaptation (UDA) methods facilitate the transfer of models to target domains without labels.
On Practical Aspects of Aggregation Defenses against Data Poisoning Attacks
The increasing access to data poses both opportunities and risks in deep learning, as one can manipulate the behaviors of deep learning models with malicious training samples.
SelFLoc: Selective Feature Fusion for Large-scale Point Cloud-based Place Recognition
To enhance message passing along particular axes, Stacked Asymmetric Convolution Block (SACB) is designed, which is one of the main contributions in this paper.
Learning Occupancy for Monocular 3D Object Detection
Monocular 3D detection is a challenging task due to the lack of accurate 3D information.
PVT-SSD: Single-Stage 3D Object Detector with Point-Voxel Transformer
The key to associating the two different representations is our introduced input-dependent Query Initialization module, which could efficiently generate reference points and content queries.
Img2Vec: A Teacher of High Token-Diversity Helps Masked AutoEncoders
To study which type of deep features is appropriate for MIM as a learning target, we propose a simple MIM framework with serials of well-trained self-supervised models to convert an Image to a feature Vector as the learning target of MIM, where the feature extractor is also known as a teacher model.
APPT : Asymmetric Parallel Point Transformer for 3D Point Cloud Understanding
To tackle these problems, we propose Asymmetric Parallel Point Transformer (APPT).
Neural Collapse Inspired Federated Learning with Non-iid Data
One of the challenges in federated learning is the non-independent and identically distributed (non-iid) characteristics between heterogeneous devices, which cause significant differences in local updates and affect the performance of the central server.
DRSM: De-Randomized Smoothing on Malware Classifier Providing Certified Robustness
After showing how DRSM is theoretically robust against attacks with contiguous adversarial bytes, we verify its performance and certified robustness experimentally, where we observe only marginal accuracy drops as the cost of robustness.
Can AI-Generated Text be Reliably Detected?
In particular, we develop a recursive paraphrasing attack to apply on AI text, which can break a whole range of detectors, including the ones using the watermarking schemes as well as neural network-based detectors, zero-shot classifiers, and retrieval-based detectors.
CrossFormer++: A Versatile Vision Transformer Hinging on Cross-scale Attention
On the one hand, CEL blends each token with multiple patches of different scales, providing the self-attention module itself with cross-scale features.
General Rotation Invariance Learning for Point Clouds via Weight-Feature Alignment
Compared to 2D images, 3D point clouds are much more sensitive to rotations.
Temporal Robustness against Data Poisoning
Data poisoning considers cases when an adversary manipulates the behavior of machine learning algorithms through malicious training data.
OBMO: One Bounding Box Multiple Objects for Monocular 3D Object Detection
Unfortunately, the network cannot accurately distinguish different depths from such non-discriminative visual features, resulting in unstable depth training.
CLIP is Also an Efficient Segmenter: A Text-Driven Approach for Weakly Supervised Semantic Segmentation
To efficiently generate high-quality segmentation masks from CLIP, we propose a novel WSSS framework called CLIP-ES.
Ranked #13 on
Weakly-Supervised Semantic Segmentation
on COCO 2014 val
One-shot Implicit Animatable Avatars with Model-based Priors
Most of these methods fail to achieve realistic reconstruction when only a single image is available.
Towards In-distribution Compatibility in Out-of-distribution Detection
Various training criteria for these auxiliary outliers are proposed based on heuristic intuitions.
Graph R-CNN: Towards Accurate 3D Object Detection with Semantic-Decorated Local Graph
The dynamic farthest voxel sampling is then applied to evenly sample the points.
Label Semantic Knowledge Distillation for Unbiased Scene Graph Generation
To this end, we propose a novel model-agnostic Label Semantic Knowledge Distillation (LS-KD) for unbiased SGG.
Lethal Dose Conjecture on Data Poisoning
Deep Partition Aggregation (DPA) and its extension, Finite Aggregation (FA) are recent approaches for provable defenses against data poisoning, where they predict through the majority vote of many base models trained from different subsets of training set using a given learner.
Masked Autoencoders for Point Cloud Self-supervised Learning
Then, a standard Transformer based autoencoder, with an asymmetric design and a shifting mask tokens operation, learns high-level latent features from unmasked point patches, aiming to reconstruct the masked point patches.
Ranked #2 on
Point Cloud Segmentation
on PointCloud-C
3D Part Segmentation
Few-Shot 3D Point Cloud Classification
+2
Improved Certified Defenses against Data Poisoning with (Deterministic) Finite Aggregation
DPA predicts through an aggregation of base classifiers trained on disjoint subsets of data, thus restricting its sensitivity to dataset distortions.
CrossFormer: A Versatile Vision Transformer Hinging on Cross-scale Attention
On the one hand, CEL blends each embedding with multiple patches of different scales, providing the self-attention module itself with cross-scale features.
Ranked #43 on
Semantic Segmentation
on ADE20K val
On Feature Decorrelation in Self-Supervised Learning
In self-supervised representation learning, a common idea behind most of the state-of-the-art approaches is to enforce the robustness of the representations to predefined augmentations.
DPlis: Boosting Utility of Differentially Private Deep Learning via Randomized Smoothing
Deep learning techniques have achieved remarkable performance in wide-ranging tasks.
Towards Better Accuracy-efficiency Trade-offs: Divide and Co-training
Each of these small networks has a fraction of the original one's parameters.
Ranked #31 on
Image Classification
on CIFAR-100
(using extra training data)
Accelerate CNNs from Three Dimensions: A Comprehensive Pruning Framework
Specifically, it first casts the relationships between a certain model's accuracy and depth/width/resolution into a polynomial regression and then maximizes the polynomial to acquire the optimal values for the three dimensions.
Boundary-Aware Dense Feature Indicator for Single-Stage 3D Object Detection from Point Clouds
3D object detection based on point clouds has become more and more popular.
DBP: Discrimination Based Block-Level Pruning for Deep Model Acceleration
The dominant pruning methods, filter-level pruning methods, evaluate their performance through the reduction ratio of computations and deem that a higher reduction ratio of computations is equivalent to a higher acceleration ratio in terms of inference time.
The Secret Revealer: Generative Model-Inversion Attacks Against Deep Neural Networks
This paper studies model-inversion attacks, in which the access to a model is abused to infer information about the training data.
REFIT: A Unified Watermark Removal Framework For Deep Learning Systems With Limited Data
The experimental results demonstrate that our fine-tuning based watermark removal attacks could pose real threats to the copyright of pre-trained models, and thus highlight the importance of further investigating the watermarking problem and proposing more robust watermark embedding schemes against the attacks.
COP: Customized Deep Model Compression via Regularized Correlation-Based Filter-Level Pruning
2) Cross-layer filter comparison is unachievable since the importance is defined locally within each layer.
