Search Results for author:
Found 24 papers, 18 papers with code
Stop Summation: Min-Form Credit Assignment Is All Process Reward Model Needs for Reasoning
In this paper, we identify the main cause of PRM-induced reward hacking: the canonical summation-form credit assignment in reinforcement learning (RL), which defines the value as cumulative gamma-decayed future rewards, easily induces LLMs to hack steps with high rewards.
Missing Target-Relevant Information Prediction with World Model for Accurate Zero-Shot Composed Image Retrieval
The key challenge for ZS-CIR tasks is to modify a reference image according to manipulation text to accurately retrieve a target image, especially when the reference image is missing essential target content.
MADS: Multi-Attribute Document Supervision for Zero-Shot Image Classification
Zero-shot learning (ZSL) aims to train a model on seen classes and recognize unseen classes by knowledge transfer through shared auxiliary information.
ProAPO: Progressively Automatic Prompt Optimization for Visual Classification
While recent methods show that visual descriptions generated by large language models (LLMs) enhance the generalization of VLMs, class-specific prompts may be inaccurate or lack discrimination due to the hallucination in LLMs.
Reason-before-Retrieve: One-Stage Reflective Chain-of-Thoughts for Training-Free Zero-Shot Composed Image Retrieval
Existing training-free zero-shot CIR (ZS-CIR) methods often employ a two-stage process: they first generate a caption for the reference image and then use Large Language Models for reasoning to obtain a target description.
Denoise-I2W: Mapping Images to Denoising Words for Accurate Zero-Shot Composed Image Retrieval
Then, a pseudo-composed mapping module maps the pseudo-reference image to a pseudo-word token and combines it with the pseudo-manipulation text with manipulation intention.
Scaling Offline Model-Based RL via Jointly-Optimized World-Action Model Pretraining
Experimental results indicate that our largest agent, with 150 million parameters, achieves 78. 9% human-level performance on pretrained games using only 10% subsampled offline data, outperforming existing state-of-the-art large-scale offline RL baselines by 31. 6% on averange.
T2VIndexer: A Generative Video Indexer for Efficient Text-Video Retrieval
To enhance retrieval efficiency, in this paper, we introduce a model-based video indexer named T2VIndexer, which is a sequence-to-sequence generative model directly generating video identifiers and retrieving candidate videos with constant time complexity.
IIU: Independent Inference Units for Knowledge-based Visual Question Answering
In this paper, we propose Independent Inference Units (IIU) for fine-grained multi-modal reasoning to decompose intra-modal information by the functionally independent units.
Visual-Semantic Decomposition and Partial Alignment for Document-based Zero-Shot Learning
In this work, we propose a novel network to extract multi-view semantic concepts from documents and images and align the matching rather than entire concepts.
SC-Tune: Unleashing Self-Consistent Referential Comprehension in Large Vision Language Models
In this paper, we present and delve into the self-consistency capability of LVLMs, a crucial aspect that reflects the models' ability to both generate informative captions for specific objects and subsequently utilize these captions to accurately re-identify the objects in a closed-loop process.
RIME: Robust Preference-based Reinforcement Learning with Noisy Preferences
Our experiments on robotic manipulation and locomotion tasks demonstrate that RIME significantly enhances the robustness of the state-of-the-art PbRL method.
Watermarking Vision-Language Pre-trained Models for Multi-modal Embedding as a Service
Our extensive experiments on various datasets indicate that the proposed watermarking approach is effective and safe for verifying the copyright of VLPs for multi-modal EaaS and robust against model extraction attacks.
Context-I2W: Mapping Images to Context-dependent Words for Accurate Zero-Shot Composed Image Retrieval
Different from Composed Image Retrieval task that requires expensive labels for training task-specific models, Zero-Shot Composed Image Retrieval (ZS-CIR) involves diverse tasks with a broad range of visual content manipulation intent that could be related to domain, scene, object, and attribute.
Align before Search: Aligning Ads Image to Text for Accurate Cross-Modal Sponsored Search
Conventional research mainly studies from the view of modeling the implicit correlations between images and texts for query-ads matching, ignoring the alignment of detailed product information and resulting in suboptimal search performance. In this work, we propose a simple alignment network for explicitly mapping fine-grained visual parts in ads images to the corresponding text, which leverages the co-occurrence structure consistency between vision and language spaces without requiring expensive labeled training data.
Ranked #1 on
Image-text matching
on CommercialAdsDataset
Evaluate Geometry of Radiance Fields with Low-frequency Color Prior
From this insight, given a reconstructed density field and observation images, we design a closed-form method to approximate the color field with low-frequency spherical harmonics, and compute the inverse mean residual color.
GraphFit: Learning Multi-scale Graph-Convolutional Representation for Point Cloud Normal Estimation
We propose a precise and efficient normal estimation method that can deal with noise and nonuniform density for unstructured 3D point clouds.
Ranked #4 on
Surface Normals Estimation
on PCPNet
TTAGN: Temporal Transaction Aggregation Graph Network for Ethereum Phishing Scams Detection
In this paper, we propose a Temporal Transaction Aggregation Graph Network (TTAGN) to enhance phishing scams detection performance on Ethereum.
6GAN: IPv6 Multi-Pattern Target Generation via Generative Adversarial Nets with Reinforcement Learning
6GAN forces multiple generators to train with a multi-class discriminator and an alias detector to generate non-aliased active targets with different addressing pattern types.
SiamHAN: IPv6 Address Correlation Attacks on TLS Encrypted Traffic via Siamese Heterogeneous Graph Attention Network
To do this, we propose an IPv6 address correlation model - SiamHAN.
6GCVAE: Gated Convolutional Variational Autoencoder for IPv6 Target Generation
IPv6 scanning has always been a challenge for researchers in the field of network measurement.
ET-BERT: A Contextualized Datagram Representation with Pre-training Transformers for Encrypted Traffic Classification
In this paper, we propose a new traffic representation model called Encrypted Traffic Bidirectional Encoder Representations from Transformer (ET-BERT), which pre-trains deep contextualized datagram-level representation from large-scale unlabeled data.
6VecLM: Language Modeling in Vector Space for IPv6 Target Generation
Fast IPv6 scanning is challenging in the field of network measurement as it requires exploring the whole IPv6 address space but limited by current computational power.
Using Non-invertible Data Transformations to Build Adversarial-Robust Neural Networks
Deep neural networks have proven to be quite effective in a wide variety of machine learning tasks, ranging from improved speech recognition systems to advancing the development of autonomous vehicles.
