Search Results for author:
Found 22 papers, 13 papers with code
Kimi-VL Technical Report
We present Kimi-VL, an efficient open-source Mixture-of-Experts (MoE) vision-language model (VLM) that offers advanced multimodal reasoning, long-context understanding, and strong agent capabilities - all while activating only 2. 8B parameters in its language decoder (Kimi-VL-A3B).
Simplify RLHF as Reward-Weighted SFT: A Variational Method
More specifically, by directly minimizing the distribution gap between the learning LLM policy and the optimal solution of RLHF, we transform the alignment objective into a reward-driven re-weighted supervised fine-tuning (SFT) form, which only requires minor adjustment on the SFT loss to obtain noticeable improvement on training stability and effectiveness.
Atoxia: Red-teaming Large Language Models with Target Toxic Answers
Given a particular harmful answer, Atoxia generates a corresponding user query and a misleading answer opening to examine the internal defects of a given LLM.
Self-playing Adversarial Language Game Enhances LLM Reasoning
In this game, an attacker and a defender communicate around a target word only visible to the attacker.
On Diversified Preferences of Large Language Model Alignment
Through experiments on four models and five human preference datasets, we find the calibration error can be adopted as a key metric for evaluating RMs and MORE can obtain superior alignment performance.
Adversarial Preference Optimization: Enhancing Your Alignment via RM-LLM Game
Targeting more efficient human preference optimization, we propose an Adversarial Preference Optimization (APO) framework, in which the LLM and the reward model update alternatively via a min-max game.
Everyone Deserves A Reward: Learning Customized Human Preferences
Besides, from the perspective of data efficiency, we propose a three-stage customized RM learning scheme, then empirically verify its effectiveness on both general preference datasets and our DSP set.
Chunk, Align, Select: A Simple Long-sequence Processing Method for Transformers
Although dominant in natural language processing, transformer-based models remain challenged by the task of long-sequence processing, because the computational cost of self-attention operations in transformers swells quadratically with the input sequence length.
Toward Fairness in Text Generation via Mutual Information Minimization based on Importance Sampling
To improve the fairness of PLMs in text generation, we propose to minimize the mutual information between the semantics in the generated text sentences and their demographic polarity, i. e., the demographic group to which the sentence is referring.
Replacing Language Model for Style Transfer
The new span is generated via a non-autoregressive masked language model, which can better preserve the local-contextual meaning of the replaced token.
Semi-constraint Optimal Transport for Entity Alignment with Dangling Cases
To improve EA with dangling entities, we propose an unsupervised method called Semi-constraint Optimal Transport for Entity Alignment in Dangling cases (SoTead).
Speaker Adaption with Intuitive Prosodic Features for Statistical Parametric Speech Synthesis
In this paper, we propose a method of speaker adaption with intuitive prosodic features for statistical parametric speech synthesis.
Improving Zero-shot Voice Style Transfer via Disentangled Representation Learning
Voice style transfer, also called voice conversion, seeks to modify one speaker's voice to generate speech as if it came from another (target) speaker.
FairFil: Contrastive Neural Debiasing Method for Pretrained Text Encoders
Pretrained text encoders, such as BERT, have been applied increasingly in various natural language processing (NLP) tasks, and have recently demonstrated significant performance gains.
WAFFLe: Weight Anonymized Factorization for Federated Learning
Experiments on MNIST, FashionMNIST, and CIFAR-10 demonstrate WAFFLe's significant improvement to local test performance and fairness while simultaneously providing an extra layer of security.
CLUB: A Contrastive Log-ratio Upper Bound of Mutual Information
In this paper, we propose a novel Contrastive Log-ratio Upper Bound (CLUB) of mutual information.
Improving Disentangled Text Representation Learning with Information-Theoretic Guidance
Learning disentangled representations of natural language is essential for many NLP tasks, e. g., conditional text generation, style transfer, personalized dialogue systems, etc.
Straight-Through Estimator as Projected Wasserstein Gradient Flow
The Straight-Through (ST) estimator is a widely used technique for back-propagating gradients through discrete random variables.
Dynamic Embedding on Textual Networks via a Gaussian Process
The relative importance of global versus local structure for the embeddings is learned automatically.
Improving Textual Network Embedding with Global Attention via Optimal Transport
Constituting highly informative network embeddings is an important tool for network analysis.
Understanding and Accelerating Particle-Based Variational Inference
Particle-based variational inference methods (ParVIs) have gained attention in the Bayesian inference literature, for their capacity to yield flexible and accurate approximations.
