Search Results for author:
Found 158 papers, 53 papers with code
GeoSense: Evaluating Identification and Application of Geometric Principles in Multimodal Reasoning
Geometry problem-solving (GPS), a challenging task requiring both visual comprehension and symbolic reasoning, effectively measures the reasoning capabilities of multimodal large language models (MLLMs).
DMM: Building a Versatile Image Generation Model via Distillation-Based Model Merging
The success of text-to-image (T2I) generation models has spurred a proliferation of numerous model checkpoints fine-tuned from the same base model on various specialized datasets.
MMKB-RAG: A Multi-Modal Knowledge-Based Retrieval-Augmented Generation Framework
Recent advancements in large language models (LLMs) and multi-modal LLMs have been remarkable.
ECKGBench: Benchmarking Large Language Models in E-commerce Leveraging Knowledge Graph
To bridge the evaluation gap, we propose ECKGBench, a dataset specifically designed to evaluate the capacities of LLMs in e-commerce knowledge.
Deconstructing Long Chain-of-Thought: A Structured Reasoning Optimization Framework for Long CoT Distillation
Recent advancements in large language models (LLMs) have demonstrated remarkable reasoning capabilities through long chain-of-thought (CoT) reasoning.
A Comprehensive Survey on Long Context Language Modeling
With the growing number of long documents, dialogues, and other textual data, it is important to develop Long Context Language Models (LCLMs) that can process and analyze extensive inputs in an effective and efficient way.
KDSelector: A Knowledge-Enhanced and Data-Efficient Model Selector Learning Framework for Time Series Anomaly Detection
Model selection has been raised as an essential problem in the area of time series anomaly detection (TSAD), because there is no single best TSAD model for the highly heterogeneous time series in real-world applications.
D3: Diversity, Difficulty, and Dependability-Aware Data Selection for Sample-Efficient LLM Instruction Tuning
In this paper, we first establish data selection criteria based on three distinct aspects of data value: diversity, difficulty, and dependability, and then propose the D3 method comprising two key steps of scoring and selection.
Nash Equilibrium Constrained Auto-bidding With Bi-level Reinforcement Learning
However, the NCB problem presents significant challenges due to its constrained bi-level structure and the typically large number of advertisers involved.
CombatVLA: An Efficient Vision-Language-Action Model for Combat Tasks in 3D Action Role-Playing Games
Recent advances in Vision-Language-Action models (VLAs) have expanded the capabilities of embodied intelligence.
Gradient Deconfliction via Orthogonal Projections onto Subspaces For Multi-task Learning
Although multi-task learning (MTL) has been a preferred approach and successfully applied in many real-world scenarios, MTL models are not guaranteed to outperform single-task models on all tasks mainly due to the negative effects of conflicting gradients among the tasks.
ChineseEcomQA: A Scalable E-commerce Concept Evaluation Benchmark for Large Language Models
To address these problems, we propose \textbf{ChineseEcomQA}, a scalable question-answering benchmark focused on fundamental e-commerce concepts.
Can Large Language Models Detect Errors in Long Chain-of-Thought Reasoning?
In this paper, to understand the qualities of these long CoTs and measure the critique abilities of existing LLMs on these long CoTs, we introduce the DeltaBench, including the generated long CoTs from different o1-like models (e. g., QwQ, DeepSeek-R1) for different reasoning tasks (e. g., Math, Code, General Reasoning), to measure the ability to detect errors in long CoT reasoning.
UQABench: Evaluating User Embedding for Prompting LLMs in Personalized Question Answering
To address this concern, we propose \name, a benchmark designed to evaluate the effectiveness of user embeddings in prompting LLMs for personalization.
AIR: Complex Instruction Generation via Automatic Iterative Refinement
With the development of large language models, their ability to follow simple instructions has significantly improved.
VALUE: Value-Aware Large Language Model for Query Rewriting via Weighted Trie in Sponsored Search
In the realm of sponsored search advertising, matching advertisements with the search intent of a user's query is crucial.
HiddenDetect: Detecting Jailbreak Attacks against Large Vision-Language Models via Monitoring Hidden States
The integration of additional modalities increases the susceptibility of large vision-language models (LVLMs) to safety risks, such as jailbreak attacks, compared to their language-only counterparts.
"See the World, Discover Knowledge": A Chinese Factuality Evaluation for Large Vision Language Models
The evaluation of factual accuracy in large vision language models (LVLMs) has lagged behind their rapid development, making it challenging to fully reflect these models' knowledge capacity and reliability.
Equilibrate RLHF: Towards Balancing Helpfulness-Safety Trade-off in Large Language Models
Fine-tuning large language models (LLMs) based on human preferences, commonly achieved through reinforcement learning from human feedback (RLHF), has been effective in improving their performance.
Large Language Models Are Universal Recommendation Learners
In real-world recommender systems, different tasks are typically addressed using supervised learning on task-specific datasets with carefully designed model architectures.
MIM: Multi-modal Content Interest Modeling Paradigm for User Behavior Modeling
Click-Through Rate (CTR) prediction is a crucial task in recommendation systems, online searches, and advertising platforms, where accurately capturing users' real interests in content is essential for performance.
An Adaptable Budget Planner for Enhancing Budget-Constrained Auto-Bidding in Online Advertising
Extensive simulation experiments and real-world A/B testing validate the effectiveness of ABPlanner, demonstrating its capability to enhance the cumulative value achieved by auto-bidders.
DAGPrompT: Pushing the Limits of Graph Prompting with a Distribution-aware Graph Prompt Tuning Approach
This paper identifies two key challenges in adapting graph prompting methods for complex graphs: (1) adapting the model to new distributions in downstream tasks to mitigate pre-training and fine-tuning discrepancies from heterophily and (2) customizing prompts for hop-specific node requirements.
PAID: A Framework of Product-Centric Advertising Image Design
An SDXL-based layout-controlled inpainting model is trained to generate an aesthetic background image.
Demons in the Detail: On Implementing Load Balancing Loss for Training Specialized Mixture-of-Expert Models
Existing MoE training frameworks usually employ the parallel training strategy so that $f_i$ and the LBL are calculated within a $\textbf{micro-batch}$ and then averaged across parallel groups.
Compression with Global Guidance: Towards Training-free High-Resolution MLLMs Acceleration
Multimodal large language models (MLLMs) have attracted considerable attention due to their exceptional performance in visual content understanding and reasoning.
Detecting Neurocognitive Disorders through Analyses of Topic Evolution and Cross-modal Consistency in Visual-Stimulated Narratives
DTM-based approach validated the effectiveness of dynamic topic consistency as a macrostructural metric (F1=0. 61, AUC=0. 78).
ProgCo: Program Helps Self-Correction of Large Language Models
Then, program-driven refinement (ProgRe) receives feedback from ProgVe, conducts dual reflection and refinement on both responses and verification programs to mitigate misleading of incorrect feedback in complex reasoning tasks.
CodeElo: Benchmarking Competition-level Code Generation of LLMs with Human-comparable Elo Ratings
CodeElo benchmark is mainly based on the official CodeForces platform and tries to align with the platform as much as possible.
LongDocURL: a Comprehensive Multimodal Long Document Benchmark Integrating Understanding, Reasoning, and Locating
Large vision language models (LVLMs) have improved the document understanding capabilities remarkably, enabling the handling of complex document elements, longer contexts, and a wider range of tasks.
Align Anything: Training All-Modality Models to Follow Instructions with Language Feedback
In this work, we make the first attempt to fine-tune all-modality models (i. e. input and output with any modality, also named any-to-any models) using human preference data across all modalities (including text, image, audio, and video), ensuring its behavior aligns with human intentions.
Qwen2.5 Technical Report
In addition, for hosted solutions, the proprietary models currently include two mixture-of-experts (MoE) variants: Qwen2. 5-Turbo and Qwen2. 5-Plus, both available from Alibaba Cloud Model Studio.
Ranked #7 on
on GPQA
Token Preference Optimization with Self-Calibrated Visual-Anchored Rewards for Hallucination Mitigation
Direct Preference Optimization (DPO) has been demonstrated to be highly effective in mitigating hallucinations in Large Vision Language Models (LVLMs) by aligning their outputs more closely with human preferences.
LLaVA-UHD v2: an MLLM Integrating High-Resolution Feature Pyramid via Hierarchical Window Transformer
To address this issue, we present LLaVA-UHD v2, an advanced MLLM centered around a Hierarchical window transformer that enables capturing diverse visual granularity by constructing and integrating a high-resolution feature pyramid.
AuctionNet: A Novel Benchmark for Decision-Making in Large-Scale Games
We believe that AuctionNet is applicable not only to research on bid decision-making in ad auctions but also to the general area of decision-making in large-scale games.
HyViLM: Enhancing Fine-Grained Recognition with a Hybrid Encoder for Vision-Language Models
A common approach currently involves dynamically cropping the original high-resolution image into smaller sub-images, which are then fed into a vision encoder that was pre-trained on lower-resolution images.
WiS Platform: Enhancing Evaluation of LLM-Based Multi-Agent Systems Through Game-Based Analysis
In this paper, to facilitate the research on LLM-based MAS, we introduce an open, scalable, and real-time updated platform for accessing and analyzing the LLM-based MAS based on the games Who is Spy?"
FocusLLaVA: A Coarse-to-Fine Approach for Efficient and Effective Visual Token Compression
Recent advances on Multi-modal Large Language Models have demonstrated that high-resolution image input is crucial for model capabilities, especially for fine-grained tasks.
Ranked #103 on
Visual Question Answering
on MM-Vet
Explainable LLM-driven Multi-dimensional Distillation for E-Commerce Relevance Learning
Effective query-item relevance modeling is pivotal for enhancing user experience and safeguarding user satisfaction in e-commerce search systems.
PSA-VLM: Enhancing Vision-Language Model Safety through Progressive Concept-Bottleneck-Driven Alignment
However, recent research shows that the visual modality in VLMs is highly vulnerable, allowing attackers to bypass safety alignment in LLMs through visually transmitted content, launching harmful attacks.
Chinese SimpleQA: A Chinese Factuality Evaluation for Large Language Models
Based on Chinese SimpleQA, we perform a comprehensive evaluation on the factuality abilities of existing LLMs.
FlowDCN: Exploring DCN-like Architectures for Fast Image Generation with Arbitrary Resolution
Arbitrary-resolution image generation still remains a challenging task in AIGC, as it requires handling varying resolutions and aspect ratios while maintaining high visual quality.
M2rc-Eval: Massively Multilingual Repository-level Code Completion Evaluation
Besides, the existing benchmarks usually report overall average scores of different languages, where the fine-grained abilities in different completion scenarios are ignored.
2D-DPO: Scaling Direct Preference Optimization with 2-Dimensional Supervision
Recent advancements in Direct Preference Optimization (DPO) have significantly enhanced the alignment of Large Language Models (LLMs) with human preferences, owing to its simplicity and effectiveness.
Adaptive Dense Reward: Understanding the Gap Between Action and Reward Space in Alignment
Our method improves the success rate on adversarial samples by 10\% compared to the sample-wise approach, and achieves a 1. 3\% improvement on evaluation benchmarks such as MMLU, GSM8K, HumanEval, etc.
MTU-Bench: A Multi-granularity Tool-Use Benchmark for Large Language Models
Besides, all evaluation metrics of our MTU-Bench are based on the prediction results and the ground truth without using any GPT or human evaluation metrics.
SEGMENT+: Long Text Processing with Short-Context Language Models
There is a growing interest in expanding the input capacity of language models (LMs) across various domains.
Can VLMs Play Action Role-Playing Games? Take Black Myth Wukong as a Study Case
We define 12 tasks within the game, with 75% focusing on combat, and incorporate several state-of-the-art VLMs into this benchmark.
Qwen2.5-Coder Technical Report
In this report, we introduce the Qwen2. 5-Coder series, a significant upgrade from its predecessor, CodeQwen1. 5.
Enhancing Taobao Display Advertising with Multimodal Representations: Challenges, Approaches and Insights
Despite the recognized potential of multimodal data to improve model accuracy, many large-scale industrial recommendation systems, including Taobao display advertising system, predominantly depend on sparse ID features in their models.
DDK: Distilling Domain Knowledge for Efficient Large Language Models
Despite the advanced intelligence abilities of large language models (LLMs) in various applications, they still face significant computational and storage demands.
Turbo: Informativity-Driven Acceleration Plug-In for Vision-Language Large Models
Vision-Language Large Models (VLMs) recently become primary backbone of AI, due to the impressive performance.
Qwen2 Technical Report
This report introduces the Qwen2 series, the latest addition to our large language models and large multimodal models.
Ranked #3 on
Arithmetic Reasoning
on GSM8K
(using extra training data)
Deep Bag-of-Words Model: An Efficient and Interpretable Relevance Architecture for Chinese E-Commerce
Text relevance or text matching of query and product is an essential technique for the e-commerce search system to ensure that the displayed products can match the intent of the query.
GraphReader: Building Graph-based Agent to Enhance Long-Context Abilities of Large Language Models
Long-context capabilities are essential for large language models (LLMs) to tackle complex and long-input tasks.
GeoGPT4V: Towards Geometric Multi-modal Large Language Models with Geometric Image Generation
To overcome this issue, we introduce a novel pipeline that leverages GPT-4 and GPT-4V to generate relatively basic geometry problems with aligned text and images, facilitating model learning.
D-CPT Law: Domain-specific Continual Pre-Training Scaling Law for Large Language Models
To address the limitations of existing methods, inspired by the Scaling Law for performance prediction, we propose to investigate the Scaling Law of the Domain-specific Continual Pre-Training (D-CPT Law) to decide the optimal mixture ratio with acceptable training costs for LLMs of different sizes.
R2C2-Coder: Enhancing and Benchmarking Real-world Repository-level Code Completion Abilities of Code Large Language Models
Code completion models have made significant progress in recent years.
RLAIF-V: Open-Source AI Feedback Leads to Super GPT-4V Trustworthiness
Traditional feedback learning for hallucination reduction relies on labor-intensive manual labeling or expensive proprietary models.
Ranked #1 on
Visual Question Answering
on AMBER
Demystify Mamba in Vision: A Linear Attention Perspective
By exploring the similarities and disparities between the effective Mamba and subpar linear attention Transformer, we provide comprehensive analyses to demystify the key factors behind Mamba's success.
AIGB: Generative Auto-bidding via Conditional Diffusion Modeling
Auto-bidding plays a crucial role in facilitating online advertising by automatically providing bids for advertisers.
ConvLLaVA: Hierarchical Backbones as Visual Encoder for Large Multimodal Models
To enhance the capabilities of ConvLLaVA, we propose two critical optimizations.
Ranked #78 on
Visual Question Answering
on MM-Vet
Safety Alignment for Vision Language Models
To address this issue, we enhance the existing VLMs' visual modality safety alignment by adding safety modules, including a safety projector, safety tokens, and a safety head, through a two-stage training process, effectively improving the model's defense against risky images.
Enhancing Prompt Following with Visual Control Through Training-Free Mask-Guided Diffusion
Meanwhile, a network, dubbed as Masked ControlNet, is designed to utilize these object masks for object generation in the misaligned visual control region.
Accelerating Image Generation with Sub-path Linear Approximation Model
Diffusion models have significantly advanced the state of the art in image, audio, and video generation tasks.
RHanDS: Refining Malformed Hands for Generated Images with Decoupled Structure and Style Guidance
The style guidance is a hand image, e. g., the malformed hand itself, and is employed to furnish the style reference for hand refining.
Dr.Hair: Reconstructing Scalp-Connected Hair Strands without Pre-training via Differentiable Rendering of Line Segments
In the film and gaming industries, achieving a realistic hair appearance typically involves the use of strands originating from the scalp.
MetaSplit: Meta-Split Network for Limited-Stock Product Recommendation
Due to limited user interactions for each product (i. e. item), the corresponding item embedding in the CTR model may not easily converge.
Tuning-Free Noise Rectification for High Fidelity Image-to-Video Generation
The experimental results demonstrate the effectiveness of our approach in improving the fidelity of generated videos.
MEBS: Multi-task End-to-end Bid Shading for Multi-slot Display Advertising
Through extensive offline and online experiments, we demonstrate the effectiveness and efficiency of our method, and we obtain a 7. 01% lift in Gross Merchandise Volume, a 7. 42% lift in Return on Investment, and a 3. 26% lift in ad buy count.
AtomoVideo: High Fidelity Image-to-Video Generation
Recently, video generation has achieved significant rapid development based on superior text-to-image generation techniques.
Making Pre-trained Language Models Great on Tabular Prediction
Condensing knowledge from diverse domains, language models (LMs) possess the capability to comprehend feature names from various tables, potentially serving as versatile learners in transferring knowledge across distinct tables and diverse prediction tasks, but their discrete text representation space is inherently incompatible with numerical feature values in tables.
SERVAL: Synergy Learning between Vertical Models and LLMs towards Oracle-Level Zero-shot Medical Prediction
Recent development of large language models (LLMs) has exhibited impressive zero-shot proficiency on generic and common sense questions.
MT-Bench-101: A Fine-Grained Benchmark for Evaluating Large Language Models in Multi-Turn Dialogues
By conducting a detailed analysis of real multi-turn dialogue data, we construct a three-tier hierarchical ability taxonomy comprising 4208 turns across 1388 multi-turn dialogues in 13 distinct tasks.
ConceptMath: A Bilingual Concept-wise Benchmark for Measuring Mathematical Reasoning of Large Language Models
This paper introduces ConceptMath, a bilingual (English and Chinese), fine-grained benchmark that evaluates concept-wise mathematical reasoning of Large Language Models (LLMs).
Automated Deterministic Auction Design with Objective Decomposition
Identifying high-revenue mechanisms that are both dominant strategy incentive compatible (DSIC) and individually rational (IR) is a fundamental challenge in auction design.
E^2-LLM: Efficient and Extreme Length Extension of Large Language Models
Typically, training LLMs with long context sizes is computationally expensive, requiring extensive training hours and GPU resources.
EMAGE: Towards Unified Holistic Co-Speech Gesture Generation via Expressive Masked Audio Gesture Modeling
We propose EMAGE, a framework to generate full-body human gestures from audio and masked gestures, encompassing facial, local body, hands, and global movements.
Ranked #5 on
Gesture Generation
on BEAT2
Calibration-compatible Listwise Distillation of Privileged Features for CTR Prediction
A typical practice is privileged features distillation (PFD): train a teacher model using all features (including privileged ones) and then distill the knowledge from the teacher model using a student model (excluding the privileged features), which is then employed for online serving.
Combating Bilateral Edge Noise for Robust Link Prediction
To address this dilemma, we propose an information-theory-guided principle, Robust Graph Information Bottleneck (RGIB), to extract reliable supervision signals and avoid representation collapse.
Robust Representation Learning for Unified Online Top-K Recommendation
The robust representation learning employs domain adversarial learning and multi-view wasserstein distribution learning to learn robust representations.
OneSeg: Self-learning and One-shot Learning based Single-slice Annotation for 3D Medical Image Segmentation
As deep learning methods continue to improve medical image segmentation performance, data annotation is still a big bottleneck due to the labor-intensive and time-consuming burden on medical experts, especially for 3D images.
Neuro-Symbolic Recommendation Model based on Logic Query
A recommendation system assists users in finding items that are relevant to them.
Entire Space Cascade Delayed Feedback Modeling for Effective Conversion Rate Prediction
Furthermore, there is delayed feedback in both conversion and refund events and they are sequentially dependent, named cascade delayed feedback (CDF), which significantly harms data freshness for model training.
Neural-Symbolic Recommendation with Graph-Enhanced Information
Some researchers use user behavior for logic reasoning to achieve recommendation prediction from the perspective of cognitive reasoning, but this kind of reasoning is a local one and ignores implicit information on a global scale.
Multi-Scenario Ranking with Adaptive Feature Learning
Recently, Multi-Scenario Learning (MSL) is widely used in recommendation and retrieval systems in the industry because it facilitates transfer learning from different scenarios, mitigating data sparsity and reducing maintenance cost.
Adversarial Constrained Bidding via Minimax Regret Optimization with Causality-Aware Reinforcement Learning
In this regard, we explore the problem of constrained bidding in adversarial bidding environments, which assumes no knowledge about the adversarial factors.
COPR: Consistency-Oriented Pre-Ranking for Online Advertising
In this architecture, the pre-ranking model is expected to be a lightweight approximation of the ranking model, which handles more candidates with strict latency requirements.
Rec4Ad: A Free Lunch to Mitigate Sample Selection Bias for Ads CTR Prediction in Taobao
Another line of work relies on costly uniform data that is inadequate to train industrial models.
On Structural Expressive Power of Graph Transformers
Graph Transformer has recently received wide attention in the research community with its outstanding performance, yet its structural expressive power has not been well analyzed.
Capturing Conversion Rate Fluctuation during Sales Promotions: A Novel Historical Data Reuse Approach
However, we observe that a well-trained CVR prediction model often performs sub-optimally during sales promotions.
FedAds: A Benchmark for Privacy-Preserving CVR Estimation with Vertical Federated Learning
We introduce FedAds, the first benchmark for CVR estimation with vFL, to facilitate standardized and systematical evaluations for vFL algorithms.
UniTS: A Universal Time Series Analysis Framework Powered by Self-Supervised Representation Learning
Machine learning has emerged as a powerful tool for time series analysis.
Leveraging Pretrained Representations with Task-related Keywords for Alzheimer's Disease Detection
This paper presents several efficient methods to extract better AD-related cues from high-level acoustic and linguistic features.
Gradient Coordination for Quantifying and Maximizing Knowledge Transference in Multi-Task Learning
Multi-task learning (MTL) has been widely applied in online advertising and recommender systems.
Hybrid Contrastive Constraints for Multi-Scenario Ad Ranking
In this paper, we propose a Hybrid Contrastive Constrained approach (HC^2) for multi-scenario ad ranking.
RLTP: Reinforcement Learning to Pace for Delayed Impression Modeling in Preloaded Ads
In a whole delivery period, advertisers usually desire a certain impression count for the ads, and they also expect that the delivery performance is as good as possible (e. g., obtaining high click-through rate).
HIT-SCIR at MMNLU-22: Consistency Regularization for Multilingual Spoken Language Understanding
Multilingual spoken language understanding (SLU) consists of two sub-tasks, namely intent detection and slot filling.
End-to-End Modeling Hierarchical Time Series Using Autoregressive Transformer and Conditional Normalizing Flow based Reconciliation
Multivariate time series forecasting with hierarchical structure is pervasive in real-world applications, demanding not only predicting each level of the hierarchy, but also reconciling all forecasts to ensure coherency, i. e., the forecasts should satisfy the hierarchical aggregation constraints.
Correlative Preference Transfer with Hierarchical Hypergraph Network for Multi-Domain Recommendation
Conventional graph neural network based methods usually deal with each domain separately, or train a shared model to serve all domains.
Exploiting prompt learning with pre-trained language models for Alzheimer's Disease detection
Early diagnosis of Alzheimer's disease (AD) is crucial in facilitating preventive care and to delay further progression.
Sustainable Online Reinforcement Learning for Auto-bidding
Due to safety concerns, it was believed that the RL training process can only be carried out in an offline virtual advertising system (VAS) that is built based on the historical data generated in the RAS.
Towards Understanding the Overfitting Phenomenon of Deep Click-Through Rate Prediction Models
However, far less attention has been paid to the overfitting problem of models in recommendation systems, which, on the contrary, is recognized as a critical issue for deep neural networks.
Modeling Adaptive Fine-grained Task Relatedness for Joint CTR-CVR Estimation
For this purpose, we build a relatedness prediction network, so that it can predict the contrast strength for inter-task representations of an instance.
KEEP: An Industrial Pre-Training Framework for Online Recommendation via Knowledge Extraction and Plugging
To alleviate this issue, we propose to extract knowledge from the \textit{super-domain} that contains web-scale and long-time impression data, and further assist the online recommendation task (downstream task).
Joint Optimization of Ranking and Calibration with Contextualized Hybrid Model
It can be attributed to the calibration ability of the pointwise loss since the prediction can be viewed as the click probability.
AdaSparse: Learning Adaptively Sparse Structures for Multi-Domain Click-Through Rate Prediction
Click-through rate (CTR) prediction is a fundamental technique in recommendation and advertising systems.
Adaptive Domain Interest Network for Multi-domain Recommendation
Industrial recommender systems usually hold data from multiple business scenarios and are expected to provide recommendation services for these scenarios simultaneously.
ROI-Constrained Bidding via Curriculum-Guided Bayesian Reinforcement Learning
Real-Time Bidding (RTB) is an important mechanism in modern online advertising systems.
Learning Disentangled Representations for Counterfactual Regression via Mutual Information Minimization
Learning individual-level treatment effect is a fundamental problem in causal inference and has received increasing attention in many areas, especially in the user growth area which concerns many internet companies.
Hierarchically Constrained Adaptive Ad Exposure in Feeds
To this end, adaptive ad exposure has become an appealing strategy to boost the overall performance of the feed.
Towards Personalized Bundle Creative Generation with Contrastive Non-Autoregressive Decoding
Current bundle generation studies focus on generating a combination of items to improve user experience.
GBA: A Tuning-free Approach to Switch between Synchronous and Asynchronous Training for Recommendation Model
High-concurrency asynchronous training upon parameter server (PS) architecture and high-performance synchronous training upon all-reduce (AR) architecture are the most commonly deployed distributed training modes for recommendation models.
CREATER: CTR-driven Advertising Text Generation with Controlled Pre-Training and Contrastive Fine-Tuning
This paper focuses on automatically generating the text of an ad, and the goal is that the generated text can capture user interest for achieving higher click-through rate (CTR).
Posterior Probability Matters: Doubly-Adaptive Calibration for Neural Predictions in Online Advertising
Calibration techniques aim to post-process model predictions to posterior probabilities.
Visual Encoding and Debiasing for CTR Prediction
In this paper, we present a visual encoding framework for CTR prediction to overcome these problems.
StableMoE: Stable Routing Strategy for Mixture of Experts
We point out that existing learning-to-route MoE methods suffer from the routing fluctuation issue, i. e., the target expert of the same input may change along with training, but only one expert will be activated for the input during inference.
PICASSO: Unleashing the Potential of GPU-centric Training for Wide-and-deep Recommender Systems
However, we observe that GPU devices in training recommender systems are underutilized, and they cannot attain an expected throughput improvement as what it has achieved in CV and NLP areas.
Dressi: A Hardware-Agnostic Differentiable Renderer with Reactive Shader Packing and Soft Rasterization
HardSoftRas, our novel rendering process, is designed for inverse rendering with a graphics pipeline.
APG: Adaptive Parameter Generation Network for Click-Through Rate Prediction
In many web applications, deep learning-based CTR prediction models (deep CTR models for short) are widely adopted.
AMCAD: Adaptive Mixed-Curvature Representation based Advertisement Retrieval System
Moreover, to deploy AMCAD in Taobao, one of the largest ecommerce platforms with hundreds of million users, we design an efficient two-layer online retrieval framework for the task of graph based advertisement retrieval.
BEAT: A Large-Scale Semantic and Emotional Multi-Modal Dataset for Conversational Gestures Synthesis
Achieving realistic, vivid, and human-like synthesized conversational gestures conditioned on multi-modal data is still an unsolved problem due to the lack of available datasets, models and standard evaluation metrics.
Ranked #1 on
Gesture Generation
on BEAT
Asymptotically Unbiased Estimation for Delayed Feedback Modeling via Label Correction
Moreover, to estimate CVR upon the freshly observed but biased distribution with fake negatives, the importance sampling is widely used to reduce the distribution bias.
Approximate Nearest Neighbor Search under Neural Similarity Metric for Large-Scale Recommendation
In this paper, we propose a novel method to extend ANN search to arbitrary matching functions, e. g., a deep neural network.
MBCT: Tree-Based Feature-Aware Binning for Individual Uncertainty Calibration
In previous work, researchers have developed several calibration methods to post-process the outputs of a predictor to obtain calibrated values, such as binning and scaling methods.
UKD: Debiasing Conversion Rate Estimation via Uncertainty-regularized Knowledge Distillation
Then a student model is trained on both clicked and unclicked ads with knowledge distillation, performing uncertainty modeling to alleviate the inherent noise in pseudo-labels.
Leaving No One Behind: A Multi-Scenario Multi-Task Meta Learning Approach for Advertiser Modeling
Advertisers play an essential role in many e-commerce platforms like Taobao and Amazon.
Adversarial Gradient Driven Exploration for Deep Click-Through Rate Prediction
We further show that such a process is equivalent to adding an adversarial perturbation to the model input, and thereby name our proposed approach as an the Adversarial Gradient Driven Exploration (AGE).
Characterizing the adversarial vulnerability of speech self-supervised learning
As the paradigm of the self-supervised learning upstream model followed by downstream tasks arouses more attention in the speech community, characterizing the adversarial robustness of such paradigm is of high priority.
Heterogeneous Graph Neural Networks for Large-Scale Bid Keyword Matching
When speaking of sponsored search, bid keyword recommendation is the fundamental service.
Allocating Large Vocabulary Capacity for Cross-lingual Language Model Pre-training
We find that many languages are under-represented in recent cross-lingual language models due to the limited vocabulary capacity.
Learning Effective and Efficient Embedding via an Adaptively-Masked Twins-based Layer
Each feature value is mapped to an embedding vector via an embedding learning process.
Binary Code based Hash Embedding for Web-scale Applications
In these applications, embedding learning of categorical features is crucial to the success of deep learning models.
Real-world Video Deblurring: A Benchmark Dataset and An Efficient Recurrent Neural Network
Real-world video deblurring in real time still remains a challenging task due to the complexity of spatially and temporally varying blur itself and the requirement of low computational cost.
Ranked #3 on
Deblurring
on Beam-Splitter Deblurring (BSD)
XLM-E: Cross-lingual Language Model Pre-training via ELECTRA
In this paper, we introduce ELECTRA-style tasks to cross-lingual language model pre-training.
Ranked #1 on
Zero-Shot Cross-Lingual Transfer
on XTREME
Consistency Regularization for Cross-Lingual Fine-Tuning
Fine-tuning pre-trained cross-lingual language models can transfer task-specific supervision from one language to the others.
A Cooperative-Competitive Multi-Agent Framework for Auto-bidding in Online Advertising
Third, to deploy MAAB in the large-scale advertising system with millions of advertisers, we propose a mean-field approach.
Improving Pretrained Cross-Lingual Language Models via Self-Labeled Word Alignment
The cross-lingual language models are typically pretrained with masked language modeling on multilingual text or parallel sentences.
Multi-Agent Cooperative Bidding Games for Multi-Objective Optimization in e-Commercial Sponsored Search
Although a few studies use multi-agent reinforcement learning to set up a cooperative game, they still suffer the following drawbacks: (1) They fail to avoid collusion solutions where all the advertisers involved in an auction collude to bid an extremely low price on purpose.
Explicit Semantic Cross Feature Learning via Pre-trained Graph Neural Networks for CTR Prediction
Most of the existing methods adopt a DNN-based model to capture the cross features in an implicit manner.
Towards a Better Tradeoff between Effectiveness and Efficiency in Pre-Ranking: A Learnable Feature Selection based Approach
In real-world search, recommendation, and advertising systems, the multi-stage ranking architecture is commonly adopted.
4DComplete: Non-Rigid Motion Estimation Beyond the Observable Surface
Tracking non-rigidly deforming scenes using range sensors has numerous applications including computer vision, AR/VR, and robotics.
Tracking Air Pollution in China: Near Real-Time PM2.5 Retrievals from Multiple Data Sources
Accordingly, a full-coverage high-resolution air pollutant dataset with timely updates and historical long-term records is essential to support both research and environmental management.
Global Daily CO$_2$ emissions for the year 2020
That even substantial world-wide lockdowns of activity led to a one-time decline in global CO$_2$ emissions of only 5. 4% in one year highlights the significant challenges for climate change mitigation that we face in the post-COVID era.
Atmospheric and Oceanic Physics General Economics Economics
Document Modeling with Graph Attention Networks for Multi-grained Machine Reading Comprehension
Natural Questions is a new challenging machine reading comprehension benchmark with two-grained answers, which are a long answer (typically a paragraph) and a short answer (one or more entities inside the long answer).
Adversarial Multimodal Representation Learning for Click-Through Rate Prediction
Finally, we achieve the multimodal item representations by combining both modality-specific and modality-invariant representations.
RPM-Oriented Query Rewriting Framework for E-commerce Keyword-Based Sponsored Search
Sponsored search optimizes revenue and relevance, which is estimated by Revenue Per Mille (RPM).
A bi-diffusion based layer-wise sampling method for deep learning in large graphs
The Graph Convolutional Network (GCN) and its variants are powerful models for graph representation learning and have recently achieved great success on many graph-based applications.
A Minimax Game for Instance based Selective Transfer Learning
To the best of our knowledge, this is the first to build a minimax game based model for selective transfer learning.
Aggregating E-commerce Search Results from Heterogeneous Sources via Hierarchical Reinforcement Learning
In this paper, we investigate the task of aggregating search results from heterogeneous sources in an E-commerce environment.
Hierarchical Reinforcement Learning
reinforcement-learning
+4
An AMR Aligner Tuned by Transition-based Parser
In this paper, we propose a new rich resource enhanced AMR aligner which produces multiple alignments and a new transition system for AMR parsing along with its oracle parser.
Ranked #2 on
AMR Parsing
on LDC2014T12:
Towards Better UD Parsing: Deep Contextualized Word Embeddings, Ensemble, and Treebank Concatenation
This paper describes our system (HIT-SCIR) submitted to the CoNLL 2018 shared task on Multilingual Parsing from Raw Text to Universal Dependencies.
Ranked #3 on
Dependency Parsing
on Universal Dependencies
The HIT-SCIR System for End-to-End Parsing of Universal Dependencies
Our system includes three pipelined components: \textit{tokenization}, \textit{Part-of-Speech} (POS) \textit{tagging} and \textit{dependency parsing}.
Chinese Grammatical Error Diagnosis with Long Short-Term Memory Networks
This paper introduces our Chinese Grammatical Error Diagnosis (CGED) system in the NLP-TEA-3 shared task for CGED.
Robust 3D Features for Matching between Distorted Range Scans Captured by Moving Systems
Our feature description is designed as two steps: 1) we normalize the detected local regions to canonical shapes for robust matching; 2) we encode each key point with multiple vectors at different Morse function values.
Beyond Point Clouds: Scene Understanding by Reasoning Geometry and Physics
In this paper, we present an approach for scene understanding by reasoning physical stability of objects from point cloud.
