Search Results for author:
Found 26 papers, 15 papers with code
Embodied-Reasoner: Synergizing Visual Search, Reasoning, and Action for Embodied Interactive Tasks
Recent advances in deep thinking models have demonstrated remarkable reasoning capabilities on mathematical and coding tasks.
Think Twice, Click Once: Enhancing GUI Grounding via Fast and Slow Systems
This structured decomposition enables systematic understanding of both interface layouts and visual relationships.
DB-Explore: Automated Database Exploration and Instruction Synthesis for Text-to-SQL
Our framework enables comprehensive database understanding through diverse sampling strategies and automated instruction generation, bridging the gap between database structures and language models.
STaR-SQL: Self-Taught Reasoner for Text-to-SQL
Generating step-by-step "chain-of-thought" rationales has proven effective for improving the performance of large language models on complex reasoning tasks.
RG-Attn: Radian Glue Attention for Multi-modality Multi-agent Cooperative Perception
To harness the potential of every possible data source for optimal performance, we design a robust LiDAR and camera cross-modality fusion module, Radian-Glue-Attention (RG-Attn), applicable to both intra-agent cross-modality fusion and inter-agent cross-modality fusion scenarios, owing to the convenient coordinate conversion by transformation matrix and the unified sampling/inversion mechanism.
VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding
The key insight of our vision-centric training paradigm is that high-quality image-text data is crucial for both image and video understanding.
Ranked #3 on
Video Question Answering
on NExT-QA
ECBench: Can Multi-modal Foundation Models Understand the Egocentric World? A Holistic Embodied Cognition Benchmark
However, current datasets for embodied video question answering lack comprehensive and systematic evaluation frameworks.
2.5 Years in Class: A Multimodal Textbook for Vision-Language Pretraining
Compared to its counterparts, our video-centric textbook offers more coherent context, richer knowledge, and better image-text alignment.
GaVaMoE: Gaussian-Variational Gated Mixture of Experts for Explainable Recommendation
GaVaMoE introduces two key components: (1) a rating reconstruction module that employs Variational Autoencoder (VAE) with a Gaussian Mixture Model (GMM) to capture complex user-item collaborative preferences, serving as a pre-trained multi-gating mechanism; and (2) a set of fine-grained expert models coupled with the multi-gating mechanism for generating highly personalized explanations.
Entering Real Social World! Benchmarking the Social Intelligence of Large Language Models from a First-person Perspective
(3) a lack of comprehensive evaluation of behavioral intelligence, with specific emphasis on incorporating critical human-machine interaction scenarios.
DiReDi: Distillation and Reverse Distillation for AIoT Applications
When the user needs to update the edge AI model to better fit the actual scenario, the reverse distillation (RD) process is employed to extract the knowledge: the difference between user preferences and the manufacturer's presumptions from the edge AI model using the user's exclusive data.
Apple Intelligence Foundation Language Models
We present foundation language models developed to power Apple Intelligence features, including a ~3 billion parameter model designed to run efficiently on devices and a large server-based language model designed for Private Cloud Compute.
Multimodal Self-Instruct: Synthetic Abstract Image and Visual Reasoning Instruction Using Language Model
In light of this, we design a multi-modal self-instruct, utilizing large language models and their code capabilities to synthesize massive abstract images and visual reasoning instructions across daily scenarios.
Edge AI-Enabled Chicken Health Detection Based on Enhanced FCOS-Lite and Knowledge Distillation
The utilization of AIoT technology has become a crucial trend in modern poultry management, offering the potential to optimize farming operations and reduce human workloads.
TimeToM: Temporal Space is the Key to Unlocking the Door of Large Language Models' Theory-of-Mind
Theory of Mind (ToM)-the cognitive ability to reason about mental states of ourselves and others, is the foundation of social interaction.
Advancing Process Verification for Large Language Models via Tree-Based Preference Learning
For instance, Tree-PLV achieved substantial performance gains over the Mistral-7B self-consistency baseline on GSM8K (67. 55% to 82. 79%), MATH (17. 00% to 26. 80%), CSQA (68. 14% to 72. 97%), and StrategyQA (82. 86% to 83. 25%). Additionally, our study explores the appropriate granularity for applying preference learning, revealing that step-level guidance provides feedback that better aligns with the evaluation of the reasoning process.
On the Combination of AI and Wireless Technologies: 3GPP Standardization Progress
Combing Artificial Intelligence (AI) and wireless communication technologies has become one of the major technologies trends towards 2030.
VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs
In this paper, we present the VideoLLaMA 2, a set of Video Large Language Models (Video-LLMs) designed to enhance spatial-temporal modeling and audio understanding in video and audio-oriented tasks.
Ranked #4 on
Video Question Answering
on Perception Test
Agent-Pro: Learning to Evolve via Policy-Level Reflection and Optimization
Large Language Models (LLMs) exhibit robust problem-solving capabilities for diverse tasks.
Self-Contrast: Better Reflection Through Inconsistent Solving Perspectives
Experiments conducted on a series of reasoning and translation tasks with different LLMs serve to underscore the effectiveness and generality of our strategy.
TaskBench: Benchmarking Large Language Models for Task Automation
To address this, we introduce TaskBench, a comprehensive framework to evaluate the capability of LLMs in task automation.
An Expression Tree Decoding Strategy for Mathematical Equation Generation
To generate a tree with expression as its node, we employ a layer-wise parallel decoding strategy: we decode multiple independent expressions (leaf nodes) in parallel at each layer and repeat parallel decoding layer by layer to sequentially generate these parent node expressions that depend on others.
Ranked #2 on
Math Word Problem Solving
on MathQA
Data-Copilot: Bridging Billions of Data and Humans with Autonomous Workflow
The advancements are twofold: First, it is a code-centric agent that receives human requests and generates code as an intermediary to handle massive data, which is quite flexible for large-scale data processing tasks.
PromptNER: Prompt Locating and Typing for Named Entity Recognition
Prompt learning is a new paradigm for utilizing pre-trained language models and has achieved great success in many tasks.
Ranked #1 on
Nested Named Entity Recognition
on ACE 2004
Query-based Instance Discrimination Network for Relational Triple Extraction
Joint entity and relation extraction has been a core task in the field of information extraction.
Contrastive Learning
Joint Entity and Relation Extraction
+1
Multi-View Reasoning: Consistent Contrastive Learning for Math Word Problem
Math word problem solver requires both precise relation reasoning about quantities in the text and reliable generation for the diverse equation.
Ranked #2 on
Math Word Problem Solving
on Math23K
(using extra training data)
