SSMs combined with neural networks match Transformers in dynamic token selection.
problem Understanding the capabilities of SSMs in dynamic token selection.
method Exploring SSMs combined with fully connected neural networks.
result SSMs combined with nonlinear layers can efficiently solve challenging tasks and estimate functions.
Transformers excel at sparse token selection, surpassing FCNs in both worst and average cases.
problem Sparse token selection task
method One-layer transformer trained with gradient descent
result Transformers learn sparse token selection and exhibit strong out-of-distribution length generalization
This study explains RL training dynamics in LLMs, focusing on token-level optimization and reasoning pattern reshaping.
problem Understanding the training dynamics of RL in LLMs to improve their reasoning capabilities.
method Empirical analysis and theoretical modeling of RL training process, focusing on reasoning patterns and token optimization.
result RL primarily optimizes a sparse subset of critical tokens, reshaping reasoning pattern distributions and affecting model performance.
Decoding strategies often exclude human-like tokens, creating a detectable gap in generated text.
problem Decoding strategies exclude contextually appropriate but statistically rare tokens, creating a detectable gap in generated text.
method Analysis of 1.8 million texts across 8 language models, 5 decoding strategies, and 53 hyperparameter configurations.
result 8-18% of human-selected tokens fall outside typical truncation boundaries, indicating a detectable gap.
Gradient-trained embeddings select important tokens in text.
problem Understanding the theoretical structure of token embeddings.
method One-layer softmax attention model with gradient descent.
result Gradient-trained embeddings align with important tokens based on frequency.
User surveys for Quality of Experience (QoE) are a critical source of information. In addition to the common "star rating" used to estimate Mean Opinion Score (MOS), more detailed survey questions (problem tokens) about specific areas provide valuable insight into the factors impacting QoE. This paper explores two aspe…
Attention mechanism learns to focus on sparse tokens efficiently.
problem Detecting weak, rare, and sparsely located features in long sequences.
method Theoretical analysis and training of a single-layer attention classifier in a sparse-token classification model.
result A single-layer attention classifier can achieve vanishing test error with logarithmic signal strength growth, unlike linear classifiers requiring linear growth.
Extends DeTEcT framework for token economies with dynamic and probabilistic parameters.
problem Modeling wealth distribution in token economies with dynamic and probabilistic parameters.
method Introduces four parametrization techniques: dynamic vs static, probabilistic vs non-probabilistic.
result Derives existing wealth distribution models from DeTEcT framework with added restrictions.
This work proposes a meta-learning approach for better adaptation of source code models.
problem Adapting source code models to unseen local contexts.
method Formulated as a meta-learning problem, selecting targeted information for adaptation.
result Improved performance in code auto-completion tasks, especially for identifiers and literals.
Study predicts success of crypto-tokens on Pump.fun platform.
problem Identify factors affecting the success of new crypto-tokens.
method Build predictive models using bonding curve mechanism and structural/behavioral variables.
result Conditional variables significantly improve the predictive power of token success.
New insights show stochastic initialization prevents token clustering in deep Transformers.
problem Understanding token dynamics in deep stochastic Transformers.
method Analysis of deep Transformers with random initialization noise, proving convergence to an interacting-particle system on the sphere.
result Initialization noise prevents token clustering, leading to antipodal formations.
Dynamic Vocabulary Pruning stabilizes LLM training by removing low-probability tokens.
problem Training Large Language Models (LLMs) with Reinforcement Learning (RL) causes numerical divergence between inference and training.
method Dynamic Vocabulary Pruning (DVP) constrains the RL objective to a safe vocabulary that excludes low-probability tokens.
result DVP stabilizes training by reducing systematic bias introduced by the extreme tail of the token distribution.
Study reveals risks of investing in new crypto-tokens in decentralized exchanges.
problem Risks associated with investing in newly created tokens in decentralized exchanges.
method Analysis of financial impact, market dynamics, profitability, and liquidity manipulations.
result Significant market liquidity trapped in honeypots, reducing market efficiency and misleading investors.
The paper analyzes the dynamics of tokens in transformer models at moderate interaction levels.
problem Understanding the evolution of tokens in transformer models at moderate interaction levels.
method Modeling transformer models as a system of particles interacting in a mean-field way and studying the corresponding dynamics.
result Characterization and convergence of the limiting dynamics in different phases of the system.
Gradient descent biases linear models in next-token prediction towards data entropy.
problem Optimization bias in next-token prediction models.
method Analysis of gradient descent on linear models with sparse conditional distributions.
result Gradient descent selects parameters that equate token logits differences to log-odds in the data subspace.
Particles representing tokens cluster in Transformers, influenced by initial tokens and matrix spectrum.
problem Understanding the geometry of learned representations in Transformers.
method Viewing Transformers as particle systems, applying dynamical systems and partial differential equations.
result Particles cluster towards limiting objects, confirming context-awareness and the emergence of leaders.
Self-attention networks localize when eigenspectrum variance is small.
problem Self-attention mechanisms can lead to rank and entropy collapses, reducing model expressivity and trainability.
method Characterized attention localization using query-key eigenspectrum variance.
result Small eigenspectrum variance prevents both rank and entropy collapses, improving model performance.
Dynamic abstention improves LLM accuracy by selectively terminating unpromising reasoning.
problem LLMs waste compute on incorrect responses, leading to inefficiency.
method Formal reinforcement learning framework with abstention reward parameter.
result Dynamic abstention outperforms natural baselines in selective accuracy.
Paper proposes a framework for token economy simulation and wealth distribution.
problem Simulation and regulation of token economies.
method Formal analysis framework for tokenomics, defining mechanisms for wealth distribution and stability.
result Algorithmic regulatory controls for token economies to achieve desired wealth distribution.
This paper analyzes Ethereum blockchain using topology and geometry to uncover crypto-token price dynamics.
problem Lack of understanding on crypto-token price dynamics from blockchain data.
method Topological data analysis and functional data depth.
result Ethereum blockchain provides insights into crypto-token price dynamics not accessible with conventional methods.
Model analyzes Proof-of-Stake network dynamics and speculative capital effects on token prices.
problem Understanding and managing price dynamics in Proof-of-Stake networks.
method Developed an open-economy macroeconomic model to analyze Proof-of-Stake dynamics and speculative capital effects.
result Speculative capital can shift staked-token ownership, potentially improving consensus decentralization.
DOS improves language model generation by considering inter-token dependencies.
problem Lack of sequence-level information and inter-token dependencies in existing decoding strategies.
method Dependency-Oriented Sampler (DOS) that uses attention matrices to approximate inter-token dependencies.
result DOS consistently achieves superior performance on code generation and mathematical reasoning tasks.
The paper analyzes risk spillovers between AI ETFs, AI tokens, and green markets.
problem Risk spillovers among AI ETFs, AI tokens, and green markets.
method R2 decomposition method
result AI ETFs and clean energy act as risk transmitters, while AI tokens and green assets act as receivers.
ByteGen models LOB dynamics without tokenization, achieving realistic market metrics.
problem Modeling high-frequency LOB dynamics in finance.
method Autoregressive next-byte prediction on packed binary data, using H-Net architecture.
result Successfully reproduces stylized facts of financial markets.
Study reveals AI's spontaneous topic changes in text prediction.
problem AI's inability to spontaneously switch topics like humans.
method Defined topic as Token Priority Graphs (TPGs) and analyzed self-attention models.
result AI can only switch topics if lower-priority tokens outnumber higher-priority ones.
Fan tokens surged before World Cup matches, but declined during them, revealing cognitive biases.
problem Analyzing the impact of FIFA World Cup matches on fan tokens.
method Event study and intraday analysis of blockchain-based fan tokens.
result Fan tokens experienced a surge in returns six months before the World Cup, followed by a decline during the matches, revealing asymmetries in performance.
Proof-of-Stake networks with EIP-1559 exhibit stable token prices and secure network security.
problem Token valuation and institutional capital in Proof-of-Stake networks under EIP-1559
method Open-economy macroeconomic equilibrium model
result Stable steady-state equilibrium price for ETH
DRFormer uses dynamic tokenization and multi-scale transformer to forecast long time series.
problem Forecasting long-term time series data across diverse scales.
method Dynamic tokenizer, multi-scale transformer, dynamic sparse learning, rotary position encoding.
result DRFormer outperforms existing methods in forecasting accuracy.
We empirically verify that the market capitalisations of coins and tokens in the cryptocurrency universe follow power-law distributions with significantly different values, with the tail exponent falling between 0.5 and 0.7 for coins, and between 1.0 and 1.3 for tokens. We provide a rationale for this, based on a simpl…
Study finds Aave token network has core-periphery structure, with high decentralization predicting better returns.
problem Understanding the actual decentralization in DeFi token transactions on the Ethereum blockchain.
method Applied social network analysis to measure decentralization in Aave token transactions.
result A more decentralized Aave token network predicts higher returns and lower volatility.
The study examines how language models learn to represent the world, identifying conditions for ecological veridicality.
problem Understanding when language models learn to represent the world accurately and how this learning process can fail.
method Analyzes the Bayes-optimal next-token cross-entropy decomposition and the role of training ecology in shaping model representations.
result The minimum-complexity zero-excess solution is the quotient partition by training equivalence, and this solution is not preserved in in-context learning or per-task adaptation.
Mathematical framework using Riemannian geometry for intelligence and consciousness.
problem Lack of a unified mathematical framework for intelligence and consciousness.
method Conceptualizes intelligence as tokens in a high-dimensional space, using Riemannian geometry to describe structure and dynamics.
result Integrates geometric concepts to offer a unified framework for intelligence and consciousness.
KLD token adjusts supply based on macroeconomic debt index, creating deflationary effect.
problem Managing deflationary pressures in digital assets.
method Debt-indexed supply adjustments linked to macroeconomic data.
result Deflationary mechanism strengthens as debt rises.
New analysis shows interpretability doesn't guarantee steering utility in LLMs.
problem Does higher interpretability lead to better steering utility in large language models?
method Trained 90 SAEs across three LLMs, evaluated interpretability and steering utility, used Kendall's rank coefficients for analysis.
result Interpretability is only weakly associated with steering utility, and features selected by Delta Token Confidence improve steering performance.
This paper examines challenges in analyzing NFT transaction data.
problem Challenges in analyzing NFT transaction data due to non-fungible nature and blockchain.
method Analysis of transaction history of eight NFT collections.
result Illustrates challenges such as price differentiation, lateral swaps, and volatility.
The paper analyzes the training dynamics of a transformer for next-token prediction.
problem Understanding the non-asymptotic performance of transformers in next-token prediction.
method Characterizes training dataset properties, designs a two-stage training algorithm, and analyzes attention gradient properties.
result Trained transformers converge sub-linearly to max-margin solutions and exhibit linear convergence in cross-entropy loss.
The paper explores how gradient descent trains associative memories, revealing oscillations and convergence issues.
problem Training dynamics of associative memories in overparameterized and underparameterized settings.
method Reduction to particle system dynamics, theory, and experiments.
result Oscillatory transitory regimes and benign loss spikes in overparameterized settings, suboptimal memorization in underparameterized settings.
CATR rationalizes text data to stabilize causal effect estimation.
problem Observational positivity violation in high-dimensional text data.
method Confounding-Aware Token Rationalization (CATR) selects necessary subset of tokens.
result CATR yields more accurate and stable causal effect estimates.
Novel AMM model for pegged cryptoassets using nested OU processes.
problem Liquidity and risk management in markets for pegged cryptoassets.
method Multi-level nested Ornstein-Uhlenbeck (OU) processes for exchange rate dynamics, calibrated and filtered AMM model.
result Consistent efficient quotes and improved liquidity provision for pegged cryptoassets.
New approach predicts tokens in context, explaining how ICL emerges.
problem Limited understanding of in-context learning emergence.
method Auto-regressive next-token prediction (AR-NTP) with prompt token-dependency and a two-level expectation.
result ICL emerges from the generalization of sequences and topics.
The paper analyzes risks and revenue dynamics of a liquid restaking protocol in decentralized finance.
problem Interconnected risks and revenue dynamics of a liquid restaking protocol in decentralized finance.
method Empirical analysis using OLS regression, Granger-causality, and random forest feature importance tests.
result Revenue is primarily driven by value locked in the ecosystem, yield of liquid restaking token, and multi-blockchain expansion.
Study compares Web3 tokens to traditional assets, finding similar statistical properties.
problem Understanding statistical properties of Web3 tokens compared to traditional financial assets.
method Statistical analysis of various Web3 tokens across multiple time scales, comparing with traditional financial assets.
result Most Web3 tokens exhibit similar stylized facts to traditional financial assets, including heavy tails and volatility clustering.
MAESTRO improves multimodal learning for dynamic time series with adaptive attention and robustness.
problem Challenges in multimodal learning, especially in healthcare and daily living.
method Dynamic intra- and cross-modal interactions, symbolic tokenization, adaptive attention budgeting, sparse cross-modal attention, MoE mechanism.
result Average relative improvements of 4% and 8% over existing multimodal and multivariate approaches, respectively, under complete observations.
The paper analyzes dynamics of momentum in high dimensions with sparse updates.
problem Theoretical analysis of momentum dynamics in high-dimensional sparse settings.
method Theoretical analysis of two models: least squares with sparse inputs and logistic regression with a rare class.
result Characterization of high-dimensional limits of momentum dynamics and phase structure.
Hierarchical pretraining with slow-fast ODEs
problem Causal self-attention vs. slow-fast ODEs
method Instantiating fast-slow ODE formalism as a concrete neural network
result Equilibrium manifold x=φ(y) is exactly the master-equation (ME) stationary distribution Study on price fluctuations in NFT market, showing heavy-tailed distributions and long-range memory.
problem Characterizing price fluctuations in NFT market.
method Analysis of capitalization, floor price, transactions, inter-transaction times, and volume value of NFTs.
result NFT market exhibits heavy-tailed probability distribution functions, well described by stretched exponentials, with long-range memory.
Transformer attention layers solve single-location regression tasks.
problem Understanding token-wise sparsity and internal linear representations in attention-based models.
method Introduce single-location regression task and a simplified predictor based on self-attention layers.
result Transformer attention layers are asymptotically Bayes optimal and can learn underlying structures effectively.
Study quantifies how LLMs capture higher-order statistical structure using cumulant expansion.
problem Understanding how LLMs internalize statistical structure during next-token prediction.
method Cumulant-expansion framework treating softmax entropy as perturbation around center distribution.
result Cumulants reveal distinct signatures for mathematical vs. general text prompts, quantifying feature-learning dynamics.