Search Results for author:
Found 85 papers, 35 papers with code
Retrieval-augmented Generation across Heterogeneous Knowledge
Retrieval-augmented generation (RAG) methods have been receiving increasing attention from the NLP community and achieved state-of-the-art performance on many NLP downstream tasks.
Knowledge-Augmented Methods for Natural Language Processing
Knowledge in natural language processing (NLP) has been a rising trend especially after the advent of large scale pre-trained models.
Knowledge-Enriched Natural Language Generation
Knowledge-enriched text generation poses unique challenges in modeling and learning, driving active research in several core directions, ranging from integrated modeling of neural representations and symbolic information in the sequential/hierarchical/graphical structures, learning without direct supervisions due to the cost of structured annotation, efficient optimization and inference with massive and global constraints, to language grounding on multiple modalities, and generative reasoning with implicit commonsense knowledge and background knowledge.
Describe-then-Reason: Improving Multimodal Mathematical Reasoning through Visual Comprehension Training
Open-source multimodal large language models (MLLMs) excel in various tasks involving textual and visual inputs but still struggle with complex multimodal mathematical reasoning, lagging behind proprietary models like GPT-4V(ision) and Gemini-Pro.
A Progressive Framework of Vision-language Knowledge Distillation and Alignment for Multilingual Scene
Pre-trained vision-language (V-L) models such as CLIP have shown excellent performance in many downstream cross-modal tasks.
StarCoder 2 and The Stack v2: The Next Generation
Our large model, StarCoder2- 15B, significantly outperforms other models of comparable size.
Ranked #25 on
Code Generation
on MBPP
Towards Safe and Reliable Autonomous Driving: Dynamic Occupancy Set Prediction
In the rapidly evolving field of autonomous driving, accurate trajectory prediction is pivotal for vehicular safety.
PIVOT: Iterative Visual Prompting Elicits Actionable Knowledge for VLMs
In each iteration, the image is annotated with a visual representation of proposals that the VLM can refer to (e. g., candidate robot actions, localizations, or trajectories).
WebVoyager: Building an End-to-End Web Agent with Large Multimodal Models
The rapid advancement of large language models (LLMs) has led to a new era marked by the development of autonomous applications in real-world scenarios, which drives innovation in creating advanced web agents.
Gradient Shaping for Multi-Constraint Safe Reinforcement Learning
Leveraging insights from this framework and recognizing the significance of \textit{redundant} and \textit{conflicting} constraint conditions, we introduce the Gradient Shaping (GradS) method for general Lagrangian-based safe RL algorithms to improve the training efficiency in terms of both reward and constraint satisfaction.
Chain-of-Note: Enhancing Robustness in Retrieval-Augmented Language Models
In response to these challenges, we introduces Chain-of-Noting (CoN), a novel approach aimed at improving the robustness of RALMs in facing noisy, irrelevant documents and in handling unknown scenarios.
PLUG: Leveraging Pivot Language in Cross-Lingual Instruction Tuning
Instruction tuning has remarkably advanced large language models (LLMs) in understanding and responding to diverse human instructions.
Sub-Sentence Encoder: Contrastive Learning of Propositional Semantic Representations
We introduce sub-sentence encoder, a contrastively-learned contextual embedding model for fine-grained semantic representation of text.
RT-Trajectory: Robotic Task Generalization via Hindsight Trajectory Sketches
Generalization remains one of the most important desiderata for robust robot learning systems.
PathRL: An End-to-End Path Generation Method for Collision Avoidance via Deep Reinforcement Learning
However, two roadblocks arise for training a DRL policy that outputs paths: (1) The action space for potential paths often involves higher dimensions comparing to low-level commands, which increases the difficulties of training; (2) It takes multiple time steps to track a path instead of a single time step, which requires the path to predicate the interactions of the robot w. r. t.
FMRT: Learning Accurate Feature Matching with Reconciliatory Transformer
However, these methods only integrate long-range context information among keypoints with a fixed receptive field, which constrains the network from reconciling the importance of features with different receptive fields to realize complete image perception, hence limiting the matching accuracy.
Auto-Instruct: Automatic Instruction Generation and Ranking for Black-Box Language Models
Large language models (LLMs) can perform a wide range of tasks by following natural language instructions, without the necessity of task-specific fine-tuning.
Creative Robot Tool Use with Large Language Models
This paper investigates the feasibility of imbuing robots with the ability to creatively use tools in tasks that involve implicit physical constraints and long-term planning.
Toward Intelligent Emergency Control for Large-scale Power Systems: Convergence of Learning, Physics, Computing and Control
Our developed methods and platform based on the convergence framework have been applied to a large (more than 3000 buses) Texas power system, and tested with 56000 scenarios.
LASER: LLM Agent with State-Space Exploration for Web Navigation
We evaluate our proposed LLM Agent with State-Space ExploRation (LASER) on both the WebShop task and amazon. com.
GeoGPT: Understanding and Processing Geospatial Tasks through An Autonomous GPT
Though limited cases are presented in this paper, GeoGPT can be further extended to various tasks by equipping with more GIS tools, and we think the paradigm of "foundational plus professional" implied in GeoGPT provides an effective way to develop next-generation GIS in this era of large foundation models.
Transforming a Quadruped into a Guide Robot for the Visually Impaired: Formalizing Wayfinding, Interaction Modeling, and Safety Mechanism
To build a successful guide robot, our paper explores three key topics: (1) formalizing the navigation mechanism of a guide dog and a human, (2) developing a data-driven model of their interaction, and (3) improving user safety.
Datasets and Benchmarks for Offline Safe Reinforcement Learning
This paper presents a comprehensive benchmarking suite tailored to offline safe reinforcement learning (RL) challenges, aiming to foster progress in the development and evaluation of safe learning algorithms in both the training and deployment phases.
Language to Rewards for Robotic Skill Synthesis
However, since low-level robot actions are hardware-dependent and underrepresented in LLM training corpora, existing efforts in applying LLMs to robotics have largely treated LLMs as semantic planners or relied on human-engineered control primitives to interface with the robot.
Barkour: Benchmarking Animal-level Agility with Quadruped Robots
In the second approach, we distill the specialist skills into a Transformer-based generalist locomotion policy, named Locomotion-Transformer, that can handle various terrains and adjust the robot's gait based on the perceived environment and robot states.
Exploring Contrast Consistency of Open-Domain Question Answering Systems on Minimally Edited Questions
Contrast consistency, the ability of a model to make consistently correct predictions in the presence of perturbations, is an essential aspect in NLP.
Pre-training Language Models for Comparative Reasoning
Comparative reasoning is a process of comparing objects, concepts, or entities to draw conclusions, which constitutes a fundamental cognitive ability.
IfQA: A Dataset for Open-domain Question Answering under Counterfactual Presuppositions
Although counterfactual reasoning is a fundamental aspect of intelligence, the lack of large-scale counterfactual open-domain question-answering (QA) benchmarks makes it difficult to evaluate and improve models on this ability.
Improving Language Models via Plug-and-Play Retrieval Feedback
ReFeed first generates initial outputs, then utilizes a retrieval model to acquire relevant information from large document collections, and finally incorporates the retrieved information into the in-context demonstration for output refinement, thereby addressing the limitations of LLMs in a more efficient and cost-effective manner.
Let GPT be a Math Tutor: Teaching Math Word Problem Solvers with Customized Exercise Generation
In this paper, we present a novel approach for distilling math word problem solving capabilities from large language models (LLMs) into smaller, more efficient student models.
Large Language Models are Built-in Autoregressive Search Engines
To overcome this limitation, recent autoregressive search engines replace the dual-encoder architecture by directly generating identifiers for relevant documents in the candidate pool.
StarCoder: may the source be with you!
The BigCode community, an open-scientific collaboration working on the responsible development of Large Language Models for Code (Code LLMs), introduces StarCoder and StarCoderBase: 15. 5B parameter models with 8K context length, infilling capabilities and fast large-batch inference enabled by multi-query attention.
Ranked #43 on
Code Generation
on MBPP
Continuous Versatile Jumping Using Learned Action Residuals
Jumping is essential for legged robots to traverse through difficult terrains.
Constrained Decision Transformer for Offline Safe Reinforcement Learning
Safe reinforcement learning (RL) trains a constraint satisfaction policy by interacting with the environment.
A Survey of Deep Learning for Mathematical Reasoning
Mathematical reasoning is a fundamental aspect of human intelligence and is applicable in various fields, including science, engineering, finance, and everyday life.
APOLLO: A Simple Approach for Adaptive Pretraining of Language Models for Logical Reasoning
Logical reasoning of text is an important ability that requires understanding the information present in the text, their interconnections, and then reasoning through them to infer new conclusions.
No driver, No Regulation? --Online Legal Driving Behavior Monitoring for Self-driving Vehicles
To address these challenges, this paper aims to digitize traffic law comprehensively and provide an application for online monitoring of legal driving behavior for autonomous vehicles.
Efficient Learning of Voltage Control Strategies via Model-based Deep Reinforcement Learning
We propose a novel model-based-DRL framework where a deep neural network (DNN)-based dynamic surrogate model, instead of a real-world power-grid or physics-based simulation, is utilized with the policy learning framework, making the process faster and sample efficient.
Empowering Language Models with Knowledge Graph Reasoning for Question Answering
Answering open-domain questions requires world knowledge about in-context entities.
SOTIF Entropy: Online SOTIF Risk Quantification and Mitigation for Autonomous Driving
Therefore, this paper proposes the "Self-Surveillance and Self-Adaption System" as a systematic approach to online minimize the SOTIF risk, which aims to provide a systematic solution for monitoring, quantification, and mitigation of inherent and external risks.
Retrieval Augmentation for Commonsense Reasoning: A Unified Approach
However, applying such methods to commonsense reasoning tasks faces two unique challenges, i. e., the lack of a general large-scale corpus for retrieval and a corresponding effective commonsense retriever.
Task Compass: Scaling Multi-task Pre-training with Task Prefix
Leveraging task-aware annotated data as supervised signals to assist with self-supervised learning on large-scale unlabeled data has become a new trend in pre-training language models.
Ranked #1 on
Sentence Completion
on HellaSwag
A Unified Encoder-Decoder Framework with Entity Memory
The entity knowledge is stored in the memory as latent representations, and the memory is pre-trained on Wikipedia along with encoder-decoder parameters.
Grape: Knowledge Graph Enhanced Passage Reader for Open-domain Question Answering
In light of this, we propose a novel knowledge Graph enhanced passage reader, namely Grape, to improve the reader performance for open-domain QA.
Multi-task Self-supervised Graph Neural Networks Enable Stronger Task Generalization
Besides, we observe that learning from multiple philosophies enhances not only the task generalization but also the single task performances, demonstrating that PARETOGNN achieves better task generalization via the disjoint yet complementary knowledge learned from different philosophies.
Generate rather than Retrieve: Large Language Models are Strong Context Generators
We call our method generate-then-read (GenRead), which first prompts a large language model to generate contextutal documents based on a given question, and then reads the generated documents to produce the final answer.
PI-ARS: Accelerating Evolution-Learned Visual-Locomotion with Predictive Information Representations
Evolution Strategy (ES) algorithms have shown promising results in training complex robotic control policies due to their massive parallelism capability, simple implementation, effective parameter-space exploration, and fast training time.
Learning Semantics-Aware Locomotion Skills from Human Demonstration
Using only 40 minutes of human demonstration data, our framework learns to adjust the speed and gait of the robot based on perceived terrain semantics, and enables the robot to walk over 6km without failure at close-to-optimal speed.
A Survey of Multi-task Learning in Natural Language Processing: Regarding Task Relatedness and Training Methods
Multi-task learning (MTL) has become increasingly popular in natural language processing (NLP) because it improves the performance of related tasks by exploiting their commonalities and differences.
Adversarial Motion Priors Make Good Substitutes for Complex Reward Functions
We also demonstrate that an effective style reward can be learned from a few seconds of motion capture data gathered from a German Shepherd and leads to energy-efficient locomotion strategies with natural gait transitions.
Diversifying Content Generation for Commonsense Reasoning with Mixture of Knowledge Graph Experts
A set of knowledge experts seek diverse reasoning on KG to encourage various generation outputs.
Safe Reinforcement Learning for Legged Locomotion
In this paper, we propose a safe reinforcement learning framework that switches between a safe recovery policy that prevents the robot from entering unsafe states, and a learner policy that is optimized to complete the task.
Physics-informed Evolutionary Strategy based Control for Mitigating Delayed Voltage Recovery
Reinforcement learning methods have been developed for the same or similar challenging control problems, but they suffer from training inefficiency and lack of robustness for "corner or unseen" scenarios.
Robot Learning from Randomized Simulations: A Review
The rise of deep learning has caused a paradigm shift in robotics research, favoring methods that require large amounts of data.
Dict-BERT: Enhancing Language Model Pre-training with Dictionary
In addition to training with the masked language modeling objective, we propose two novel self-supervised pre-training tasks on word and sentence-level alignment between input text sequence and rare word definitions to enhance language modeling representation with dictionary.
KG-FiD: Infusing Knowledge Graph in Fusion-in-Decoder for Open-Domain Question Answering
The recent proposed Fusion-in-Decoder (FiD), which is built on top of the pretrained generative model T5, achieves the state-of-the-art performance in the reading module.
Universal Controllers with Differentiable Physics for Online System Identification
In addition, we perform two studies showing that UC-DiffOSI operates well in environments with changing or unknown dynamics.
Enhancing Taxonomy Completion with Concept Generation via Fusing Relational Representations
Automatic construction of a taxonomy supports many applications in e-commerce, web search, and question answering.
Learning from Counterfactual Links for Link Prediction
However, the causal relationship between the two variables was largely ignored for learning to predict links on a graph.
Ranked #1 on
Link Property Prediction
on ogbl-ddi
Sentence-Permuted Paragraph Generation
Generating paragraphs of diverse contents is important in many applications.
Learning to Manipulate Amorphous Materials
We produce a final animation by using inverse kinematics to guide a character's arm and hand to match the motion of the manipulation tool such as a knife or a frying pan.
Few-Shot Graph Learning for Molecular Property Prediction
The recent success of graph neural networks has significantly boosted molecular property prediction, advancing activities such as drug discovery.
Ranked #1 on
Molecular Property Prediction (1-shot))
on Tox21
Unlocking Pixels for Reinforcement Learning via Implicit Attention
There has recently been significant interest in training reinforcement learning (RL) agents in vision-based environments.
Validating Label Consistency in NER Data Annotation
It can be used to validate the label consistency (or catches the inconsistency) in multiple sets of NER data annotation.
Learning and Fast Adaptation for Grid Emergency Control via Deep Meta Reinforcement Learning
In this paper, we mitigate these limitations by developing a novel deep meta reinforcement learning (DMRL) algorithm.
Protective Policy Transfer
When used with a set of thresholds, the safety estimator becomes a classifier for switching between the protective policy and the task policy.
COCOI: Contact-aware Online Context Inference for Generalizable Non-planar Pushing
General contact-rich manipulation problems are long-standing challenges in robotics due to the difficulty of understanding complicated contact physics.
Policy Transfer via Kinematic Domain Randomization and Adaptation
Transferring reinforcement learning policies trained in physics simulation to the real hardware remains a challenge, known as the "sim-to-real" gap.
Tri-Train: Automatic Pre-Fine Tuning between Pre-Training and Fine-Tuning for SciNER
The training process of scientific NER models is commonly performed in two steps: i) Pre-training a language model by self-supervised tasks on huge data and ii) fine-tune training with small labelled data.
Action Sequence Augmentation for Early Graph-based Anomaly Detection
With Eland, anomaly detection performance at an earlier stage is better than non-augmented methods that need significantly more observed data by up to 15% on the Area under the ROC curve.
Technical Question Answering across Tasks and Domains
In this paper, we propose a novel framework of deep transfer learning to effectively address technical QA across tasks and domains.
A Survey of Knowledge-Enhanced Text Generation
To address this issue, researchers have considered incorporating various forms of knowledge beyond the input text into the generation models.
A Technical Question Answering System with Transfer Learning
In recent years, the need for community technical question-answering sites has increased significantly.
Injecting Entity Types into Entity-Guided Text Generation
Our model has a multi-step decoder that injects the entity types into the process of entity mention generation.
Accelerated Deep Reinforcement Learning Based Load Shedding for Emergency Voltage Control
Load shedding has been one of the most widely used and effective emergency control approaches against voltage instability.
Crossing Variational Autoencoders for Answer Retrieval
Existing methods learned semantic representations with dual encoders or dual variational auto-encoders.
Faceted Hierarchy: A New Graph Type to Organize Scientific Concepts and a Construction Method
On a scientific concept hierarchy, a parent concept may have a few attributes, each of which has multiple values being a group of child concepts.
Learning Fast Adaptation with Meta Strategy Optimization
The key idea behind MSO is to expose the same adaptation process, Strategy Optimization (SO), to both the training and testing phases.
Learning Novel Policies For Tasks
Our method does this by creating a second reward function that recognizes previously seen state sequences and rewards those by novelty, which is measured using autoencoders that have been trained on state sequences from previously discovered policies.
Sim-to-Real Transfer for Biped Locomotion
We present a new approach for transfer of dynamic robot control policies such as biped locomotion from simulation to real hardware.
Policy Transfer with Strategy Optimization
Transfer learning using domain randomization is a promising approach, but it usually assumes that the target environment is close to the distribution of the training environments, thus relying heavily on accurate system identification.
Learning Symmetric and Low-energy Locomotion
Indeed, a standard benchmark for DRL is to automatically create a running controller for a biped character from a simple reward function.
Multi-task Learning with Gradient Guided Policy Specialization
Then, during the specialization training stage we selectively split the weights of the policy based on a per-weight metric that measures the disagreement among the multiple tasks.
Preparing for the Unknown: Learning a Universal Policy with Online System Identification
Together, UP-OSI is a robust control policy that can be used across a wide range of dynamic models, and that is also responsive to sudden changes in the environment.
