Search Results for author:
Found 24 papers, 13 papers with code
Revisiting Training-Inference Trigger Intensity in Backdoor Attacks
Backdoor attacks typically place a specific trigger on certain training data, such that the model makes prediction errors on inputs with that trigger during inference.
ParallelComp: Parallel Long-Context Compressor for Length Extrapolation
To mitigate the attention sink issue, we propose an attention calibration strategy that reduces biases, ensuring more stable long-range attention.
Evolution of cooperation in a bimodal mixture of conditional cooperators
To explore the effects of hard and soft conditional cooperators, we examine their interactions in two scenarios: structural mixture (SM) and probabilistic mixture (PM), where the two behavioral modes are fixed and probabilistically adopted, respectively.
RGBDS-SLAM: A RGB-D Semantic Dense SLAM Based on 3D Multi Level Pyramid Gaussian Splatting
To address this, we propose RGBDS-SLAM, a RGB-D semantic dense SLAM system based on 3D multi-level pyramid gaussian splatting, which enables high-quality dense reconstruction of scene RGB, depth, and semantics. In this system, we introduce a 3D multi-level pyramid gaussian splatting method that restores scene details by extracting multi-level image pyramids for gaussian splatting training, ensuring consistency in RGB, depth, and semantic reconstructions.
Navigating Spatial Inequities in Freight Truck Crash Severity via Counterfactual Inference in Los Angeles
Freight truck-related crashes pose significant challenges, leading to substantial economic losses, injuries, and fatalities, with pronounced spatial disparities across different regions.
CoPS: Empowering LLM Agents with Provable Cross-Task Experience Sharing
In detail, CoPS leverages agents' experiences on previous tasks, selecting distribution-matched experiences via a provable pessimism-based strategy to maximize utility while minimizing risks from distribution shifts.
How to Build a Pre-trained Multimodal model for Simultaneously Chatting and Decision-making?
We provide a definitive answer to this question by developing a new model architecture termed Visual Language Action model for Chatting and Decision Making (VLA4CD), and further demonstrating its performance in challenging autonomous driving tasks.
Configurable Foundation Models: Building LLMs from a Modular Perspective
We first formalize modules into emergent bricks - functional neuron partitions that emerge during the pre-training phase, and customized bricks - bricks constructed via additional post-training to improve the capabilities and knowledge of LLMs.
SELF-GUIDE: Better Task-Specific Instruction Following via Self-Synthetic Finetuning
Large language models (LLMs) hold the promise of solving diverse tasks when provided with appropriate natural language prompts.
Internet of Agents: Weaving a Web of Heterogeneous Agents for Collaborative Intelligence
The rapid advancement of large language models (LLMs) has paved the way for the development of highly capable autonomous agents.
MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies
For data scaling, we introduce a Warmup-Stable-Decay (WSD) learning rate scheduler (LRS), conducive to continuous training and domain adaptation.
Emergence of cooperation under punishment: A reinforcement learning perspective
Punishment is a common tactic to sustain cooperation and has been extensively studied for a long time.
YAYI 2: Multilingual Open-Source Large Language Models
As the latest advancements in natural language processing, large language models (LLMs) have achieved human-level language understanding and generation abilities in many real-world tasks, and even have been regarded as a potential path to the artificial general intelligence.
Leveraging Local Patch Alignment to Seam-cutting for Large Parallax Image Stitching
In this paper, we argue that by adding a simple Local Patch Alignment Module (LPAM) into the seam cutting, the final result can be efficiently improved for large parallax image stitching.
Large Language Model as a Policy Teacher for Training Reinforcement Learning Agents
By incorporating the guidance from the teacher agent, the student agent can distill the prior knowledge of the LLM into its own model.
TeacherLM: Teaching to Fish Rather Than Giving the Fish, Language Modeling Likewise
Based on TeacherLM-7. 1B, we augmented 58 NLP datasets and taught various student models with different parameters from OPT and BLOOM series in a multi-task setting.
Prompt2Model: Generating Deployable Models from Natural Language Instructions
In this paper, we propose Prompt2Model, a general-purpose method that takes a natural language task description like the prompts provided to LLMs, and uses it to train a special-purpose model that is conducive to deployment.
Ranked #2 on
Data-free Knowledge Distillation
on SQuAD
Enabling Intelligent Interactions between an Agent and an LLM: A Reinforcement Learning Approach
We find that this problem can be naturally formulated by a Markov decision process (MDP), and propose When2Ask, a reinforcement learning based approach that learns when it is necessary to query LLMs for high-level instructions to accomplish a target task.
Replicating Complex Dialogue Policy of Humans via Offline Imitation Learning with Supervised Regularization
Policy learning (PL) is a module of a task-oriented dialogue system that trains an agent to make actions in each dialogue turn.
On Context Distribution Shift in Task Representation Learning for Offline Meta RL
Offline Meta Reinforcement Learning (OMRL) aims to learn transferable knowledge from offline datasets to enhance the learning process for new target tasks.
Towards Trustworthy Multi-label Sewer Defect Classification via Evidential Deep Learning
An automatic vision-based sewer inspection plays a key role of sewage system in a modern city.
Robust Domain Randomised Reinforcement Learning through Peer-to-Peer Distillation
In reinforcement learning, domain randomisation is an increasingly popular technique for learning more general policies that are robust to domain-shifts at deployment.
Investigating Generalisation in Continuous Deep Reinforcement Learning
Deep Reinforcement Learning has shown great success in a variety of control tasks.
