Search Results for author:
Found 45 papers, 39 papers with code
ProRL: Prolonged Reinforcement Learning Expands Reasoning Boundaries in Large Language Models
Recent advances in reasoning-centric language models have highlighted reinforcement learning (RL) as a promising method for aligning models with verifiable rewards.
LongMamba: Enhancing Mamba's Long Context Capabilities via Training-Free Receptive Field Enlargement
State space models (SSMs) have emerged as an efficient alternative to Transformer models for language modeling, offering linear computational complexity and constant memory usage as context length increases.
CLIMB: CLustering-based Iterative Data Mixture Bootstrapping for Language Model Pre-training
We analyze the final data mixture, elucidating the characteristics of an optimal data mixture.
MA-LoT: Multi-Agent Lean-based Long Chain-of-Thought Reasoning enhances Formal Theorem Proving
To solve these issues, we propose MA-LoT: Multi-Agent Lean-based Long Chain-of-Thought framework, (to the best of our knowledge), the first multi-agent framework for Lean4 theorem proving that balance high-level NL reasoning and FL verification in Long CoT.
Adapt-Pruner: Adaptive Structural Pruning for Efficient Small Language Model Training
Small language models (SLMs) have attracted considerable attention from both academia and industry due to their broad range of applications in edge devices.
UGPhysics: A Comprehensive Benchmark for Undergraduate Physics Reasoning with Large Language Models
Large language models (LLMs) have demonstrated remarkable capabilities in solving complex reasoning tasks, particularly in mathematics.
Hymba: A Hybrid-head Architecture for Small Language Models
We propose Hymba, a family of small language models featuring a hybrid-head parallel architecture that integrates transformer attention mechanisms with state space models (SSMs) for enhanced efficiency.
Grounded-VideoLLM: Sharpening Fine-grained Temporal Grounding in Video Large Language Models
Video Large Language Models (Video-LLMs) have demonstrated remarkable capabilities in coarse-grained video understanding, however, they struggle with fine-grained temporal grounding.
CodeGraph: Enhancing Graph Reasoning of LLMs with Code
Compared to the existing methods, CodeGraph demonstrates strong performance on arithmetic problems in graph tasks and offers a more controllable and interpretable approach to the reasoning process.
FIRST: Teach A Reliable Large Language Model Through Efficient Trustworthy Distillation
Then we further propose a brand new method named Efficient Trustworthy Distillation (FIRST), which utilizes a small portion of teacher's knowledge to obtain a reliable language model in a cost-efficient way.
LLM Pruning and Distillation in Practice: The Minitron Approach
We present a comprehensive report on compressing the Llama 3. 1 8B and Mistral NeMo 12B models to 4B and 8B parameters, respectively, using pruning and distillation.
TheoremLlama: Transforming General-Purpose LLMs into Lean4 Experts
However, due to the scarcity of aligned NL and Formal Language (FL) theorem-proving data most modern LLMs exhibit suboptimal performance. This scarcity results in a paucity of methodologies for training LLMs and techniques to fully utilize their capabilities in composing formal proofs.
VeraCT Scan: Retrieval-Augmented Fake News Detection with Justifiable Reasoning
In response to this challenge, we introduce VeraCT Scan, a novel retrieval-augmented system for fake news detection.
$\textbf{PLUM}$: Improving Code LMs with Execution-Guided On-Policy Preference Learning Driven By Synthetic Test Cases
Recent findings demonstrate that on-policy data is the key to successful preference learning, where the preference data is collected using the same policy LM being trained.
SaySelf: Teaching LLMs to Express Confidence with Self-Reflective Rationales
Large language models (LLMs) often generate inaccurate or fabricated information and generally fail to indicate their confidence, which limits their broader applications.
LISA: Layerwise Importance Sampling for Memory-Efficient Large Language Model Fine-Tuning
Attempting to complement this deficiency, we investigate the layerwise properties of LoRA on fine-tuning tasks and observe an unexpected but consistent skewness of weight norms across different layers.
Arithmetic Control of LLMs for Diverse User Preferences: Directional Preference Alignment with Multi-Objective Rewards
Additionally, DPA models user preferences as directions (i. e., unit vectors) in the reward space to achieve user-dependent preference control.
Can We Verify Step by Step for Incorrect Answer Detection?
Chain-of-Thought (CoT) prompting has marked a significant advancement in enhancing the reasoning capabilities of large language models (LLMs).
The Instinctive Bias: Spurious Images lead to Illusion in MLLMs
In this paper, we identify a typical class of inputs that baffles MLLMs, which consist of images that are highly relevant but inconsistent with answers, causing MLLMs to suffer from visual illusion.
ConstraintChecker: A Plugin for Large Language Models to Reason on Commonsense Knowledge Bases
When considering a new knowledge instance, ConstraintChecker employs a rule-based module to produce a list of constraints, then it uses a zero-shot learning module to check whether this knowledge instance satisfies all constraints.
R-Tuning: Instructing Large Language Models to Say `I Don't Know'
This approach is formalized by first identifying the disparity in knowledge encompassed by pre-trained parameters compared to that of instruction tuning data.
Plum: Prompt Learning using Metaheuristic
Since the emergence of large language models, prompt learning has become a popular method for optimizing and customizing these models.
MarineGPT: Unlocking Secrets of Ocean to the Public
Large language models (LLMs), such as ChatGPT/GPT-4, have proven to be powerful tools in promoting the user experience as an AI assistant.
UniTime: A Language-Empowered Unified Model for Cross-Domain Time Series Forecasting
To address these issues, we propose UniTime for effective cross-domain time series learning.
Ranked #5 on
Time Series Forecasting
on ETTh1 (336) Multivariate
Mitigating the Alignment Tax of RLHF
Building on the analysis and the observation that averaging different layers of the transformer leads to significantly different alignment-forgetting trade-offs, we propose Heterogeneous Model Averaging (HMA) to Heterogeneously find various combination ratios of model layers.
LMFlow: An Extensible Toolkit for Finetuning and Inference of Large Foundation Models
As the number of available foundation models and specialized tasks keeps growing, the job of training scientific language models becomes highly nontrivial.
Mixture-of-Domain-Adapters: Decoupling and Injecting Domain Knowledge to Pre-trained Language Models Memories
Pre-trained language models (PLMs) demonstrate excellent abilities to understand texts in the generic domain while struggling in a specific domain.
On the Difference of BERT-style and CLIP-style Text Encoders
Masked language modeling (MLM) has been one of the most popular pretraining recipes in natural language processing, e. g., BERT, one of the representative models.
DetGPT: Detect What You Need via Reasoning
Overall, our proposed paradigm and DetGPT demonstrate the potential for more sophisticated and intuitive interactions between humans and machines.
RAFT: Reward rAnked FineTuning for Generative Foundation Model Alignment
Utilizing a reward model and a sufficient number of samples, our approach selects the high-quality samples, discarding those that exhibit undesired behavior, and subsequently enhancing the model by fine-tuning on these filtered samples.
Automatic Prompt Augmentation and Selection with Chain-of-Thought from Labeled Data
However, most CoT studies rely on carefully designed human-annotated rational chains to prompt LLMs, posing challenges for real-world applications where labeled data is available without rational chains.
Active Prompting with Chain-of-Thought for Large Language Models
For this purpose, we propose a solution to the key problem of determining which questions are the most important and helpful ones to annotate from a pool of task-specific queries.
Hashtag-Guided Low-Resource Tweet Classification
Social media classification tasks (e. g., tweet sentiment analysis, tweet stance detection) are challenging because social media posts are typically short, informal, and ambiguous.
Towards Unifying Medical Vision-and-Language Pre-training via Soft Prompts
Medical vision-and-language pre-training (Med-VLP) has shown promising improvements on many downstream medical tasks owing to its applicability to extracting generic representations from medical images and texts.
ExtremeBERT: A Toolkit for Accelerating Pretraining of Customized BERT
In this paper, we present ExtremeBERT, a toolkit for accelerating and customizing BERT pretraining.
Normalizing Flow with Variational Latent Representation
The resulting method is significantly more powerful than the standard normalization flow approach for generating data distributions with multiple modes.
Write and Paint: Generative Vision-Language Models are Unified Modal Learners
In this work, we disclose the potential of symmetric generative vision-language pre-training in learning to write and paint concurrently, and propose a new unified modal model, named DaVinci, trained with prefix language modeling and prefix image modeling, a simple generative self-supervised objective on image-text pairs.
VLUE: A Multi-Task Benchmark for Evaluating Vision-Language Models
We release the VLUE benchmark to promote research on building vision-language models that generalize well to more diverse images and concepts unseen during pre-training, and are practical in terms of efficiency-performance trade-off.
Black-box Prompt Learning for Pre-trained Language Models
Particularly, instead of fine-tuning the model in the cloud, we adapt PLMs by prompt learning, which efficiently optimizes only a few parameters of the discrete prompts.
Efficient Neural Network Training via Forward and Backward Propagation Sparsification
For the latter step, instead of using the chain rule based gradient estimators as in existing methods, we propose a variance reduced policy gradient estimator, which only requires two forward passes without backward propagation, thus achieving completely sparse training.
Taming Pre-trained Language Models with N-gram Representations for Low-Resource Domain Adaptation
In this paper, we aim to adapt a generic pretrained model with a relatively small amount of domain-specific data.
Ranked #42 on
Time Series Forecasting
on ETTh1 (336) Multivariate
ZEN: Pre-training Chinese Text Encoder Enhanced by N-gram Representations
Moreover, it is shown that reasonable performance can be obtained when ZEN is trained on a small corpus, which is important for applying pre-training techniques to scenarios with limited data.
Ranked #1 on
Chinese Part-of-Speech Tagging
on CTB5 Dev
Chinese Named Entity Recognition
Chinese Word Segmentation
+5
