Continuum Limit

The continuum limit explores the behavior of systems as their discrete components become infinitely small, effectively transitioning from a discrete to a continuous representation. Current research focuses on understanding and quantifying the limitations of this transition in various domains, including neural networks, agent-based models, and dynamical systems, often employing techniques like metric entropy analysis and novel algorithms for improved approximation and efficiency. These investigations are crucial for advancing our understanding of complex systems and improving the performance of machine learning models and other computational methods in scenarios with limited resources or inherent constraints.

Papers

January 6, 2025

Randomly Sampled Language Reasoning Problems Reveal Limits of LLMs
Kavi Gupta, Kate Sanders, Armando Solar-Lezama
Medical LLM Continuum Limit Random Participation Language Structure Finite State Automaton Language Recognition Natural Language Reasoning Problem

December 18, 2024

Stealing That Free Lunch: Exposing the Limits of Dyna-Style Reinforcement Learning
Brett Barkley, David Fridovich-Keil
Reinforcement Learning Synthetic Data Continuum Limit Policy Reinforcement Learning Free Lunch

December 13, 2024

On the Limit of Language Models as Planning Formalizers
Cassie Huang, Li Zhang
Language Model Continuum Limit Planning Domain Planning Ability Logical Representation Planning Representation

December 8, 2024

BiDM: Pushing the Limit of Quantization for Diffusion Models
Xingyu Zheng, Xianglong Liu, Yichen Bian, Xudong Ma, Yulun Zhang, Jiakai Wang, Jinyang Guo, Haotong Qin
Diffusion Model Continuum Limit Quantization Operator Binarization Method Learnable Activation Binarizer

December 5, 2024

November 27, 2024

Pushing the Limits of LLM Inference via 2-Bit Layer-Discriminative KV Cache
Akshat Sharma, Hangliang Ding, Jianping Li, Neel Dani, Minjia Zhang
Continuum Limit LLM Inference KV Cache Cache Context CUDA Implementation Discriminative Encoder

November 22, 2024

Exploring Facets of Language Generation in the Limit
Moses Charikar, Chirag Pabbaraju
Language Generation Continuum Limit Unconditional Generation Large Set

November 21, 2024

MMGenBench: Evaluating the Limits of LMMs from the Text-to-Image Generation Perspective
Hailang Huang, Yong Wang, Zixuan Huang, Huaqiu Li, Tongwen Huang, Xiangxiang Chu, Richong Zhang
Faithful Generation Large Multimodal Model Text to Image Continuum Limit

November 20, 2024

Pushing the Limits of Sparsity: A Bag of Tricks for Extreme Pruning
Andy Li, Aiden Durrant, Milan Markovic, Lu Yin, Georgios Leontidis
Continuum Limit Sparsity Increase Sparse Network Bag Prototype Dense Network Unconventional Rabbit Hat Trick High Sparsity

November 14, 2024

On the Limits of Language Generation: Trade-Offs Between Hallucination and Mode Collapse
Alkis Kalavasis, Anay Mehrotra, Grigoris Velegkas
Language Model Language Generation Continuum Limit Content Hallucination Mode Collapse Consistent Generation

November 8, 2024

The Limits of Differential Privacy in Online Learning
Bo Li, Wei Wang, Peng Ye
Differential Privacy Online Learning Continuum Limit Online Learning Algorithm Adaptive Adversary Approximate Differential Privacy

November 7, 2024

Respecting the limit:Bayesian optimization with a bound on the optimal value
Hanyang Wang, Juergen Branke, Matthias Poloczek
Optimization Purpose Bayesian Optimization Surrogate Model Continuum Limit Net Present Value Real World Optimization Problem PAC Bayesian Bound

October 31, 2024

October 29, 2024

Pushing the Limits of All-Atom Geometric Graph Neural Networks: Pre-Training, Scaling and Zero-Shot Transfer
Zihan Pengmei, Zhengyuan Shen, Zichen Wang, Marcus Collins, Huzefa Rangwala
Pre Training Continuum Limit Multiplicative Size Scaling Molecular Conformation Geometric Graph Neural Network Geometric Descriptor

October 28, 2024

The Limits of Transfer Reinforcement Learning with Latent Low-rank Structure
Tyler Sam, Yudong Chen, Christina Lee Yu
Reinforcement Learning Continuum Limit Inner Structure Transferable Representation Intermediate Latent LOw Rank Transfer Reinforcement Learning

Continuum Limit

Papers

Randomly Sampled Language Reasoning Problems Reveal Limits of LLMs

Stealing That Free Lunch: Exposing the Limits of Dyna-Style Reinforcement Learning

On the Limit of Language Models as Planning Formalizers

BiDM: Pushing the Limit of Quantization for Diffusion Models

Quantifying the Limits of Segment Anything Model: Analyzing Challenges in Segmenting Tree-Like and Low-Contrast Structures

SKIM: Any-bit Quantization Pushing The Limits of Post-Training Quantization

Pushing the Limits of LLM Inference via 2-Bit Layer-Discriminative KV Cache

Push the Limit of Multi-modal Emotion Recognition by Prompting LLMs with Receptive-Field-Aware Attention Weighting

Pushing the Limits of Large Language Model Quantization via the Linearity Theorem

Inference Scaling $\scriptsize\mathtt{F}$Laws: The Limits of LLM Resampling with Imperfect Verifiers

Exploring Facets of Language Generation in the Limit

MMGenBench: Evaluating the Limits of LMMs from the Text-to-Image Generation Perspective

Pushing the Limits of Sparsity: A Bag of Tricks for Extreme Pruning

On the Limits of Language Generation: Trade-Offs Between Hallucination and Mode Collapse

The Limits of Differential Privacy in Online Learning

Respecting the limit:Bayesian optimization with a bound on the optimal value

Understanding the Limits of Vision Language Models Through the Lens of the Binding Problem

First, Learn What You Don't Know: Active Information Gathering for Driving at the Limits of Handling

Pushing the Limits of All-Atom Geometric Graph Neural Networks: Pre-Training, Scaling and Zero-Shot Transfer

The Limits of Transfer Reinforcement Learning with Latent Low-rank Structure