Search Results for author:
Found 33 papers, 14 papers with code
Humanoid-VLA: Towards Universal Humanoid Control with Visual Integration
This paper addresses the limitations of current humanoid robot control frameworks, which primarily rely on reactive mechanisms and lack autonomous interaction capabilities due to data scarcity.
AtomR: Atomic Operator-Empowered Large Language Models for Heterogeneous Knowledge Reasoning
Drawing inspiration from the graph modeling of knowledge, AtomR leverages large language models (LLMs) to decompose complex questions into combinations of three atomic knowledge operators, significantly enhancing the reasoning process at both the planning and execution stages.
Deep Learning-Assisted Jamming Mitigation with Movable Antenna Array
This paper reveals the potential of movable antennas in enhancing anti-jamming communication.
Towards Evaluating and Building Versatile Large Language Models for Medicine
To promote further advancements in the application of LLMs to clinical challenges, we have made the MedS-Ins dataset fully accessible and invite the research community to contribute to its expansion. Additionally, we have launched a dynamic leaderboard for MedS-Bench, which we plan to regularly update the test set to track progress and enhance the adaptation of general LLMs to the medical domain.
Tracing Privacy Leakage of Language Models to Training Data via Adjusted Influence Functions
This work implements Influence Functions (IFs) to trace privacy leakage back to the training data, thereby mitigating privacy concerns of Language Models (LMs).
DIDI: Diffusion-Guided Diversity for Offline Behavioral Generation
The goal of DIDI is to learn a diverse set of skills from a mixture of label-free offline data.
Reinformer: Max-Return Sequence Modeling for Offline RL
In this work, we introduce the concept of max-return sequence modeling which integrates the goal of maximizing returns into existing sequence models.
Scalable and Effective Arithmetic Tree Generation for Adder and Multiplier Designs
We believe our work will offer valuable insights into hardware design, further accelerating speed and reducing size through the refined search space and our tree generation methodologies.
Quantum Computing-Enhanced Algorithm Unveils Novel Inhibitors for KRAS
The discovery of small molecules with therapeutic potential is a long-standing challenge in chemistry and biology.
Context-Former: Stitching via Latent Conditioned Sequence Modeling
Offline reinforcement learning (RL) algorithms can learn better decision-making compared to behavior policies by stitching the suboptimal trajectories to derive more optimal ones.
Deep Dict: Deep Learning-based Lossy Time Series Compressor for IoT Data
We propose Deep Dict, a deep learning-based lossy time series compressor designed to achieve a high compression ratio while maintaining decompression error within a predefined range.
How Proficient Are Large Language Models in Formal Languages? An In-Depth Insight for Knowledge Base Question Answering
A typical approach to KBQA is semantic parsing, which translates a question into an executable logical form in a formal language.
A dynamical clipping approach with task feedback for Proximal Policy Optimization
Unlike previous clipping approaches, we propose a bi-level proximal policy optimization objective that can dynamically adjust the clipping bound to better reflect the preference (maximizing Return) of these RL tasks.
Offline Imitation Learning with Variational Counterfactual Reasoning
We theoretically analyze the influence of the generated expert data and the improvement of generalization.
Improving Offline-to-Online Reinforcement Learning with Q Conditioned State Entropy Exploration
Studying how to fine-tune offline reinforcement learning (RL) pre-trained policy is profoundly significant for enhancing the sample efficiency of RL algorithms.
Multidomain transformer-based deep learning for early detection of network intrusion
Timely response of Network Intrusion Detection Systems (NIDS) is constrained by the flow generation process which requires accumulation of network packets.
STRAPPER: Preference-based Reinforcement Learning via Self-training Augmentation and Peer Regularization
Due to the existence of similarity trap, such consistency regularization improperly enhances the consistency possiblity of the model's predictions between segment pairs, and thus reduces the confidence in reward learning, since the augmented distribution does not match with the original one in PbRL.
ChiPFormer: Transferable Chip Placement via Offline Decision Transformer
To resolve these challenges, we cast the chip placement as an offline RL formulation and present ChiPFormer that enables learning a transferable placement policy from fixed offline data.
Design from Policies: Conservative Test-Time Adaptation for Offline Policy Optimization
Naturally, such a paradigm raises three core questions that are not fully answered by prior non-iterative offline RL counterparts like reward-conditioned policy: (q1) What information should we transfer from the inner-level to the outer-level?
CLUE: Calibrated Latent Guidance for Offline Reinforcement Learning
As a remedy for the labor-intensive labeling, we propose to endow offline RL tasks with a few expert data and utilize the limited expert data to drive intrinsic rewards, thus eliminating the need for extrinsic rewards.
Beyond OOD State Actions: Supported Cross-Domain Offline Reinforcement Learning
Offline reinforcement learning (RL) aims to learn a policy using only pre-collected and fixed data.
KoLA: Carefully Benchmarking World Knowledge of Large Language Models
The unprecedented performance of large language models (LLMs) necessitates improvements in evaluations.
Beyond Reward: Offline Preference-guided Policy Optimization
Instead, the agent is provided with fixed offline trajectories and human preferences between pairs of trajectories to extract the dynamics and task information, respectively.
Preserving Knowledge Invariance: Rethinking Robustness Evaluation of Open Information Extraction
In this paper, we present the first benchmark that simulates the evaluation of open information extraction models in the real world, where the syntactic and expressive distributions under the same knowledge meaning may drift variously.
Behavior Proximal Policy Optimization
Offline reinforcement learning (RL) is a challenging setting where existing off-policy actor-critic methods perform poorly due to the overestimation of out-of-distribution state-action pairs.
ConstGCN: Constrained Transmission-based Graph Convolutional Networks for Document-level Relation Extraction
Document-level relation extraction with graph neural networks faces a fundamental graph construction gap between training and inference - the golden graph structure only available during training, which causes that most methods adopt heuristic or syntactic rules to construct a prior graph as a pseudo proxy.
Machine Learning-Enabled IoT Security: Open Issues and Challenges Under Advanced Persistent Threats
Advanced persistent threat (APT) is prominent for cybercriminals to compromise networks, and it is crucial to long-term and harmful characteristics.
DARA: Dynamics-Aware Reward Augmentation in Offline Reinforcement Learning
Specifically, DARA emphasizes learning from those source transition pairs that are adaptive for the target environment and mitigates the offline dynamics shift by characterizing state-action-next-state pairs instead of the typical state-action distribution sketched by prior offline RL methods.
Unsupervised Domain Adaptation with Dynamics-Aware Rewards in Reinforcement Learning
Unsupervised reinforcement learning aims to acquire skills without prior goal representations, where an agent automatically explores an open-ended environment to represent goals and learn the goal-conditioned policy.
Off-Dynamics Inverse Reinforcement Learning from Hetero-Domain
To achieve this, the widely used GAN-inspired IRL method is adopted, and its discriminator, recognizing policy-generating trajectories, is modified with the quantification of dynamics difference.
Risk-Aware Fine-Grained Access Control in Cyber-Physical Contexts
The risk levels are associated with access control decisions recommended by a security policy.
Learn Goal-Conditioned Policy with Intrinsic Motivation for Deep Reinforcement Learning
It is of significance for an agent to learn a widely applicable and general-purpose policy that can achieve diverse goals including images and text descriptions.
Learning transitional skills with intrinsic motivation
By maximizing an information theoretic objective, a few recent methods empower the agent to explore the environment and learn useful skills without supervision.
