Search Results for author:
Found 38 papers, 13 papers with code
Tractable and Provably Efficient Distributional Reinforcement Learning with General Value Function Approximation
Distributional reinforcement learning improves performance by effectively capturing environmental stochasticity, but a comprehensive theoretical understanding of its effectiveness remains elusive.
Distributional Reinforcement Learning
reinforcement-learning
+1
Learning to Explore and Select for Coverage-Conditioned Retrieval-Augmented Generation
Interactions with billion-scale large language models typically yield long-form responses due to their extensive parametric capacities, along with retrieval-augmented features.
The BiGGen Bench: A Principled Benchmark for Fine-grained Evaluation of Language Models with Language Models
To overcome these limitations, we introduce the BiGGen Bench, a principled generation benchmark designed to thoroughly evaluate nine distinct capabilities of LMs across 77 diverse tasks.
Spectral-Risk Safe Reinforcement Learning with Convergence Guarantees
Furthermore, the proposed method has been evaluated on continuous control tasks and showed the best performance among other RCRL algorithms satisfying the constraints.
KU-DMIS at EHRSQL 2024:Generating SQL query via question templatization in EHR
Transforming natural language questions into SQL queries is crucial for precise data retrieval from electronic health record (EHR) databases.
Prometheus 2: An Open Source Language Model Specialized in Evaluating Other Language Models
Proprietary LMs such as GPT-4 are often employed to assess the quality of responses from various LMs.
Reinforcement Learning from Reflective Feedback (RLRF): Aligning and Improving LLMs via Fine-Grained Self-Reflection
Despite the promise of RLHF in aligning LLMs with human preferences, it often leads to superficial alignment, prioritizing stylistic changes over improving downstream performance of LLMs.
Pitfall of Optimism: Distributional Reinforcement Learning by Randomizing Risk Criterion
Distributional reinforcement learning algorithms have attempted to utilize estimated uncertainty for exploration, such as optimism in the face of uncertainty.
Distributional Reinforcement Learning
reinforcement-learning
+1
PreWoMe: Exploiting Presuppositions as Working Memory for Long Form Question Answering
Information-seeking questions in long-form question answering (LFQA) often prove misleading due to ambiguity or false presupposition in the question.
SPOTS: Stable Placement of Objects with Reasoning in Semi-Autonomous Teleoperation Systems
Particularly, we focus on two aspects of the place task: stability robustness and contextual reasonableness of object placements.
On Monotonic Aggregation for Open-domain QA
Our experiments show that our framework not only ensures monotonicity, but also outperforms state-of-the-art multi-source QA methods on Natural Questions.
When to Read Documents or QA History: On Unified and Selective Open-domain QA
This paper studies the problem of open-domain question answering, with the aim of answering a diverse range of questions leveraging knowledge resources.
Evidentiality-aware Retrieval for Overcoming Abstractiveness in Open-Domain Question Answering
The long-standing goal of dense retrievers in abtractive open-domain question answering (ODQA) tasks is to learn to capture evidence passages among relevant passages for any given query, such that the reader produce factually correct outputs from evidence passages.
Exploring the Benefits of Training Expert Language Models over Instruction Tuning
Recently, Language Models (LMs) instruction-tuned on multiple tasks, also known as multitask-prompted fine-tuning (MT), have shown the capability to generalize to unseen tasks.
Ranked #9 on
Question Answering
on StoryCloze
Trust Region-Based Safe Distributional Reinforcement Learning for Multiple Constraints
In safety-critical robotic tasks, potential failures must be reduced, and multiple constraints must be met, such as avoiding collisions, limiting energy consumption, and maintaining balance.
Distributional Reinforcement Learning
reinforcement-learning
+3
Look Around for Anomalies: Weakly-Supervised Anomaly Detection via Context-Motion Relational Learning
Furthermore, as the relationship between context and motion is important in order to identify the anomalies in complex and diverse scenes, we propose a Context--Motion Interrelation Module (CoMo), which models the relationship between the appearance of the surroundings and motion, rather than utilizing only temporal dependencies or motion information.
Plug-and-Play Adaptation for Continuously-updated QA
To this end, we first propose a novel task--Continuously-updated QA (CuQA)--in which multiple large-scale updates are made to LMs, and the performance is measured with respect to the success in adding and updating knowledge while retaining existing knowledge.
Domain Generalization by Mutual-Information Regularization with Pre-trained Models
Domain generalization (DG) aims to learn a generalized model to an unseen target domain using only limited source domains.
Ranked #3 on
Domain Generalization
on TerraIncognita
Neural Markov Controlled SDE: Stochastic Optimization for Continuous-Time Data
We propose a novel probabilistic framework for modeling stochastic dynamics with the rigorous use of stochastic optimal control theory.
Distributional Perturbation for Efficient Exploration in Distributional Reinforcement Learning
Distributional reinforcement learning aims to learn distribution of return under stochastic environments.
Semi-Autonomous Teleoperation via Learning Non-Prehensile Manipulation Skills
In this paper, we present a semi-autonomous teleoperation framework for a pick-and-place task using an RGB-D sensor.
Robustifying Multi-hop QA through Pseudo-Evidentiality Training
This paper studies the bias problem of multi-hop question answering models, of answering correctly without correct reasoning.
Query Generation for Multimodal Documents
This paper studies the problem of generatinglikely queries for multimodal documents withimages.
SWAD: Domain Generalization by Seeking Flat Minima
Domain generalization (DG) methods aim to achieve generalizability to an unseen target domain by using only training data from the source domains.
Ranked #25 on
Domain Generalization
on TerraIncognita
Optimal Algorithms for Stochastic Multi-Armed Bandits with Heavy Tailed Rewards
In simulation, the proposed estimator shows favorable performance compared to existing robust estimators for various $p$ values and, for MAB problems, the proposed perturbation strategy outperforms existing exploration methods.
Relational Deep Feature Learning for Heterogeneous Face Recognition
Due to the lack of databases, HFR methods usually exploit the pre-trained features on a large-scale visual database that contain general facial information.
AD-VO: Scale-Resilient Visual Odometry Using Attentive Disparity Map
Visual odometry is an essential key for a localization module in SLAM systems.
Learning with Limited Data for Multilingual Reading Comprehension
This paper studies the problem of supporting question answering in a new language with limited training resources.
Categorical Metadata Representation for Customized Text Classification
The performance of text classification has improved tremendously using intelligently engineered neural-based models, especially those injecting categorical metadata as additional information, e. g., using user/product information for sentiment classification.
Ranked #4 on
Sentiment Analysis
on User and product information
(Yelp 2013 (Acc) metric)
Tsallis Reinforcement Learning: A Unified Framework for Maximum Entropy Reinforcement Learning
By controlling the entropic index, we can generate various types of entropy, including the SG entropy, and a different entropy results in a different class of the optimal policy in Tsallis MDPs.
ChoiceNet: Robust Learning by Revealing Output Correlations
To this end, we present a novel framework referred to here as ChoiceNet that can robustly infer the target distribution in the presence of inconsistent data.
Translations as Additional Contexts for Sentence Classification
We are the first to use translations as domain-free contexts for sentence classification.
Ranked #7 on
Text Classification
on TREC-6
Maximum Causal Tsallis Entropy Imitation Learning
Third, we propose a maximum causal Tsallis entropy imitation learning (MCTEIL) algorithm with a sparse mixture density network (sparse MDN) by modeling mixture weights using a sparsemax distribution.
Task Agnostic Robust Learning on Corrupt Outputs by Correlation-Guided Mixture Density Networks
In this paper, we focus on weakly supervised learning with noisy training data for both classification and regression problems. We assume that the training outputs are collected from a mixture of a target and correlated noise distributions. Our proposed method simultaneously estimates the target distribution and the quality of each data which is defined as the correlation between the target and data generating distributions. The cornerstone of the proposed method is a Cholesky Block that enables modeling dependencies among mixture distributions in a differentiable manner where we maintain the distribution over the network weights. We first provide illustrative examples in both regression and classification tasks to show the effectiveness of the proposed method. Then, the proposed method is extensively evaluated in a number of experiments where we show that it constantly shows comparable or superior performances compared to existing baseline methods in the handling of noisy data.
Sparse Markov Decision Processes with Causal Sparse Tsallis Entropy Regularization for Reinforcement Learning
The proposed sparse MDP is compared to soft MDPs which utilize causal entropy regularization.
Uncertainty-Aware Learning from Demonstration using Mixture Density Networks with Sampling-Free Variance Modeling
The proposed uncertainty-aware learning from demonstration method outperforms other compared methods in terms of safety using a complex real-world driving dataset.
Density Matching Reward Learning
The performance of KDMRL is extensively evaluated in two sets of experiments: grid world and track driving experiments.
