Search Results for author:
Found 41 papers, 14 papers with code
Pangu Ultra MoE: How to Train Your Big MoE on Ascend NPUs
This study led to Pangu Ultra MoE, a sparse LLM with 718 billion parameters, and we conducted experiments on the model to verify the simulation results.
Pangu Ultra: Pushing the Limits of Dense Large Language Models on Ascend NPUs
Our exploration demonstrates that Ascend NPUs are capable of efficiently and effectively training dense models with more than 100 billion parameters.
AttentionPredictor: Temporal Pattern Matters for Efficient LLM Inference
With the development of large language models (LLMs), efficient inference through Key-Value (KV) cache compression has attracted considerable attention, especially for long-context generation.
CMoE: Fast Carving of Mixture-of-Experts for Efficient LLM Inference
Large language models (LLMs) achieve impressive performance by scaling model parameters, but this comes with significant inference overhead.
KVTuner: Sensitivity-Aware Layer-wise Mixed Precision KV Cache Quantization for Efficient and Nearly Lossless LLM Inference
KV cache quantization can improve Large Language Models (LLMs) inference throughput and latency in long contexts and large batch-size scenarios while preserving LLMs effectiveness.
ACEBench: Who Wins the Match Point in Tool Learning?
Normal evaluates function calls in basic scenarios; Special evaluates function calls in scenarios with vague or incomplete instructions; Agent introduces multi-agent interactions to simulate function calling evaluation in real-world multi-turn interactions.
MixPE: Quantization and Hardware Co-design for Efficient LLM Inference
Transformer-based large language models (LLMs) have achieved remarkable success as model sizes continue to grow, yet their deployment remains challenging due to significant computational and memory demands.
FlatQuant: Flatness Matters for LLM Quantization
In this paper, we propose FlatQuant (Fast and Learnable Affine Transformation), a new post-training quantization approach to enhance flatness of weights and activations.
Mathematical Challenges in Deep Learning
Deep models are dominating the artificial intelligence (AI) industry since the ImageNet challenge in 2012.
Conformalized Fairness via Quantile Regression
To fulfill great needs and advocate the significance of quantile fairness, we propose a novel framework to learn a real-valued quantile function under the fairness requirement of Demographic Parity with respect to sensitive attributes, such as race or gender, and thereby derive a reliable fair prediction interval.
LHNN: Lattice Hypergraph Neural Network for VLSI Congestion Prediction
Precise congestion prediction from a placement solution plays a crucial role in circuit placement.
Distributional Reinforcement Learning with Regularized Wasserstein Loss
The empirical success of distributional reinforcement learning (RL) highly relies on the choice of distribution divergence equipped with an appropriate distribution representation.
Neuro-Symbolic Hierarchical Rule Induction
We propose an efficient interpretable neuro-symbolic model to solve Inductive Logic Programming (ILP) problems.
A Survey on Interpretable Reinforcement Learning
To that aim, we distinguish interpretability (as a property of a model) and explainability (as a post-hoc operation, with the intervention of a proxy) and discuss them in the context of RL with an emphasis on the former notion.
Model-Based Reinforcement Learning via Imagination with Derived Memory
Model-based reinforcement learning aims to improve the sample efficiency of policy learning by modeling the dynamics of the environment.
Model-based Reinforcement Learning
reinforcement-learning
+2
Adaptive Online Packing-guided Search for POMDPs
A belief is a distribution of states representing state uncertainty.
Generalizable Cross-Graph Embedding for GNN-based Congestion Prediction
To address this limitation, we propose a framework that can directly learn embeddings for the given netlist to enhance the quality of our node features.
Learning Explicit Credit Assignment for Multi-agent Joint Q-learning
In contrast, we formulate an \emph{explicit} credit assignment problem where each agent gives its suggestion about how to weight individual Q-values to explicitly maximize the joint Q-value, besides guaranteeing the Bellman optimality of the joint Q-value.
$S^3$: Sign-Sparse-Shift Reparametrization for Effective Training of Low-bit Shift Networks
Shift neural networks reduce computation complexity by removing expensive multiplication operations and quantizing continuous weights into low-bit discrete values, which are fast and energy efficient compared to conventional neural networks.
Cooperative Multi-Agent Transfer Learning with Level-Adaptive Credit Assignment
In addition, we use a novel agent network named Population Invariant agent with Transformer (PIT) to realize the coordination transfer in more varieties of scenarios.
S$^3$: Sign-Sparse-Shift Reparametrization for Effective Training of Low-bit Shift Networks
Shift neural networks reduce computation complexity by removing expensive multiplication operations and quantizing continuous weights into low-bit discrete values, which are fast and energy-efficient compared to conventional neural networks.
Learning Symbolic Rules for Interpretable Deep Reinforcement Learning
To address this challenge and improve the transparency, we propose a Neural Symbolic Reinforcement Learning framework by introducing symbolic logic into DRL.
Addressing Action Oscillations through Learning Policy Inertia
We propose Nested Policy Iteration as a general training algorithm for PIC-augmented policy which ensures monotonically non-decreasing updates under some mild conditions.
Foresee then Evaluate: Decomposing Value Estimation with Latent Future Prediction
Value function is the central notion of Reinforcement Learning (RL).
Differentiable Logic Machines
As a step in this direction, we propose a novel neural-logic architecture, called differentiable logic machine (DLM), that can solve both inductive logic programming (ILP) and reinforcement learning (RL) problems, where the solution can be interpreted as a first-order logic program.
Approximating Pareto Frontier through Bayesian-optimization-directed Robust Multi-objective Reinforcement Learning
Thirdly, the agent’s learning process is regarded as a black-box, and the comprehensive metric we proposed is computed after each episode of training, then a Bayesian optimization (BO) algorithm is adopted to guide the agent to evolve towards improving the quality of the approximated Pareto frontier.
Robust Memory Augmentation by Constrained Latent Imagination
The latent dynamics model summarizes an agent’s high dimensional experiences in a compact way.
Interpretable Reinforcement Learning With Neural Symbolic Logic
Recent progress in deep reinforcement learning (DRL) can be largely attributed to the use of neural networks.
Deep Reinforcement Learning
Hierarchical Reinforcement Learning
+3
Robust Multi-Agent Reinforcement Learning Driven by Correlated Equilibrium
Therefore, to achieve robust CMARL, we introduce novel strategies to encourage agents to learn correlated equilibrium while maximally preserving the convenience of the decentralized execution.
What About Inputing Policy in Value Function: Policy Representation and Policy-extended Value Function Approximator
We study Policy-extended Value Function Approximator (PeVFA) in Reinforcement Learning (RL), which extends conventional value function approximator (VFA) to take as input not only the state (and action) but also an explicit policy representation.
SMARTS: Scalable Multi-Agent Reinforcement Learning Training School for Autonomous Driving
We open-source the SMARTS platform and the associated benchmark tasks and evaluation metrics to encourage and empower research on multi-agent learning for autonomous driving.
Towards Effective Context for Meta-Reinforcement Learning: an Approach based on Contrastive Learning
How to collect informative trajectories of which the corresponding context reflects the specification of tasks?
What About Taking Policy as Input of Value Function: Policy-extended Value Function Approximator
The value function lies in the heart of Reinforcement Learning (RL), which defines the long-term evaluation of a policy in a given state.
Transfer among Agents: An Efficient Multiagent Transfer Learning Framework
In many cases, each agent's experience is inconsistent with each other which causes the option-value estimation to oscillate and to become inaccurate.
Open-Ended Question Answering
Reinforcement Learning (RL)
+1
Triple-GAIL: A Multi-Modal Imitation Learning Framework with Generative Adversarial Nets
Generative adversarial imitation learning (GAIL) has shown promising results by taking advantage of generative adversarial nets, especially in the field of robot learning.
Efficient Deep Reinforcement Learning via Adaptive Policy Transfer
Transfer Learning (TL) has shown great potential to accelerate Reinforcement Learning (RL) by leveraging prior knowledge from past learned policies of relevant tasks.
Multi-Agent Interactions Modeling with Correlated Policies
In this paper, we cast the multi-agent interactions modeling problem into a multi-agent imitation learning framework with explicit modeling of correlated policies by approximating opponents' policies, which can recover agents' policies that can regenerate similar interactions.
Neighborhood Cognition Consistent Multi-Agent Reinforcement Learning
Social psychology and real experiences show that cognitive consistency plays an important role to keep human society in order: if people have a more consistent cognition about their environments, they are more likely to achieve better cooperation.
MGHRL: Meta Goal-generation for Hierarchical Reinforcement Learning
Most meta reinforcement learning (meta-RL) methods learn to adapt to new tasks by directly optimizing the parameters of policies over primitive action space.
Variational Constrained Reinforcement Learning with Application to Planning at Roundabout
In this paper, we combine variational learning and constrained reinforcement learning to simultaneously learn a Conditional Representation Model (CRM) to encode the states into safe and unsafe distributions respectively as well as to learn the corresponding safe policy.
Graph Attention Memory for Visual Navigation
To address the long-term memory issue, this paper proposes a graph attention memory (GAM) architecture consisting of memory construction module, graph attention module and control module.
