Search Results for author:
Found 18 papers, 10 papers with code
Towards Self-Improvement of LLMs via MCTS: Leveraging Stepwise Knowledge with Curriculum Preference Learning
Monte Carlo Tree Search (MCTS) has recently emerged as a powerful technique for enhancing the reasoning capabilities of LLMs.
LLaVA-Critic: Learning to Evaluate Multimodal Models
We introduce LLaVA-Critic, the first open-source large multimodal model (LMM) designed as a generalist evaluator to assess performance across a wide range of multimodal tasks.
Multi-Stage Balanced Distillation: Addressing Long-Tail Challenges in Sequence-Level Knowledge Distillation
Large language models (LLMs) have significantly advanced various natural language processing tasks, but deploying them remains computationally expensive.
World Models with Hints of Large Language Models for Goal Achieving
By assigning higher intrinsic rewards to samples that align with the hints outlined by the language model during model rollouts, DLLM guides the agent toward meaningful and efficient exploration.
Enhancing Visual-Language Modality Alignment in Large Vision Language Models via Self-Improvement
In this paper, we propose SIMA, a framework that enhances visual and language modality alignment through self-improvement, eliminating the needs for external models or data.
Ranked #153 on
Visual Question Answering
on MM-Vet
Calibrated Self-Rewarding Vision Language Models
In the reward modeling, we employ a step-wise strategy and incorporate visual constraints into the self-rewarding process to place greater emphasis on visual input.
Ranked #96 on
Visual Question Answering
on MM-Vet
Premier-TACO is a Few-Shot Policy Learner: Pretraining Multitask Representation via Temporal Action-Driven Contrastive Loss
We present Premier-TACO, a multitask feature representation learning approach designed to improve few-shot policy learning efficiency in sequential decision-making tasks.
Emojis Decoded: Leveraging ChatGPT for Enhanced Understanding in Social Media Communications
Our objective is to validate the hypothesis that ChatGPT can serve as a viable alternative to human annotators in emoji research and that its ability to explain emoji meanings can enhance clarity and transparency in online communications.
Mementos: A Comprehensive Benchmark for Multimodal Large Language Model Reasoning over Image Sequences
However, current MLLM benchmarks are predominantly designed to evaluate reasoning based on static information about a single image, and the ability of modern MLLMs to extrapolate from image sequences, which is essential for understanding our ever-changing world, has been less investigated.
DrM: Mastering Visual Reinforcement Learning through Dormant Ratio Minimization
To quantify this inactivity, we adopt dormant ratio as a metric to measure inactivity in the RL agent's network.
COPlanner: Plan to Roll Out Conservatively but to Explore Optimistically for Model-Based RL
In this paper, we propose $\texttt{COPlanner}$, a planning-driven framework for model-based methods to address the inaccurately learned dynamics model problem with conservative model rollouts and optimistic environment exploration.
Adapting Static Fairness to Sequential Decision-Making: Bias Mitigation Strategies towards Equal Long-term Benefit Rate
To address biases in sequential decision-making, we introduce a long-term fairness concept named Equal Long-term Benefit Rate (ELBERT).
TACO: Temporal Latent Action-Driven Contrastive Loss for Visual Reinforcement Learning
Despite recent progress in reinforcement learning (RL) from raw pixel data, sample inefficiency continues to present a substantial obstacle.
Is Model Ensemble Necessary? Model-based RL via a Single Model with Lipschitz Regularized Value Function
To test this hypothesis, we devise two practical robust training mechanisms through computing the adversarial noise and regularizing the value network's spectral norm to directly regularize the Lipschitz condition of the value functions.
Live in the Moment: Learning Dynamics Model Adapted to Evolving Policy
Model-based reinforcement learning (RL) often achieves higher sample efficiency in practice than model-free RL by learning a dynamics model to generate samples for policy learning.
Transfer RL across Observation Feature Spaces via Model-Based Regularization
In many reinforcement learning (RL) applications, the observation space is specified by human developers and restricted by physical realizations, and may thus be subject to dramatic changes over time (e. g. increased number of observable features).
A Two-branch Neural Network for Non-homogeneous Dehazing via Ensemble Learning
Recently, there has been rapid and significant progress on image dehazing.
Planning with Exploration: Addressing Dynamics Bottleneck in Model-based Reinforcement Learning
We give an upper bound of the trajectory reward estimation error and point out that increasing the agent's exploration ability is the key to reduce trajectory reward estimation error, thereby alleviating dynamics bottleneck dilemma.
