Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

169,291 papers · 148 categories

Trend · papers per month

316394125 · Jun 202019922001200920182026
48 results for order-aware memory tokens

iStructTab improves multimodal learning by optimizing feature sequencing.

problem Redundancy, dispersion, and generalization issues in multimodal learning of images and tabular data.
method Graph-Enhanced Descriptor Sequencing (GEDS) algorithm that refines statistical descriptors through similarity graph-based computations.
result iStructTab effectively minimizes feature dispersion, improving predictive performance and robustness.

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.

New algorithm reduces costs and latency for large language model inference.

problem Optimizing inference costs and latency for large language models with GPU constraints.
method Formulated as an online scheduling problem with endogenous memory growth, introduced fluid model and WAIT algorithms.
result Reduced costs and latency, especially in near-overloaded and overloaded regimes.

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.

A novel memory mechanism for reinforcement learning agents that stores past events in human-readable language.

problem Lack of interpretability in reinforcement learning agent's memory mechanisms.
method Uses CLIP to associate visual inputs with language tokens, then feeds these tokens to a pretrained language model.
result Significantly faster convergence on challenging continuous recognition tasks.

Compact Recurrent Transformer (CRT) improves Transformer efficiency for long sequences.

problem Efficiently scaling Transformer architecture to long sequences with limited compute resources.
method Combines shallow Transformer models with recurrent neural networks and persistent memory.
result CRT achieves comparable or superior performance to full-length Transformers with shorter segments and reduced FLOPs.

Non-autoregressive transformer improves speech recognition speed and accuracy.

problem Reducing inference computation cost in speech recognition.
method Two non-autoregressive transformer structures (A-CMLM and A-FMLM) trained with masked tokens and iterative prediction during inference.
result Non-autoregressive transformer can match autoregressive transformer performance with 7x speedup.

This paper proposes a new approach to Transformers by integrating hierarchical associative memory with MetaFormers.

problem Theoretical framework for Transformers and MLP-Mixers remains underdeveloped.
method Integrating hierarchical associative memory with MetaFormers to create a parallelized MLP-Mixer.
result Symmetry-breaking effects improve the performance of the MLP-Mixer in image recognition tasks.

LLMs can be tricked into recalling facts based on context clues.

problem Manipulation of LLMs' factual recall through context changes.
method Mathematical exploration of transformers' associative memory properties.
result Transformers use self-attention and value matrix for associative memory.

Deep neural network translates math formula images to LaTeX sequences.

problem Translating math formula images to LaTeX sequences accurately and efficiently.
method Encoder-decoder architecture with CNN and LSTM, sequence-level training with policy gradient.
result State-of-the-art performance on sequence-based and image-based evaluation metrics.

Enhances CMS with Bayesian nonparametrics for better low-frequency token estimation.

problem Improving frequency estimation of low-frequency tokens in data streams.
method Integrates Bayesian nonparametrics (Pitman-Yor process) into CMS for more accurate frequency estimation.
result CMS-PYP outperforms CMS and CMS-DP in estimating low-frequency tokens.

SAGE improves memory efficiency by selectively adding, merging, or ignoring new facts.

problem Efficiently managing new facts in agentic LLMs to avoid costly write-time reasoning.
method SAGE uses a von Mises-Fisher-based density estimator to score and route candidate facts.
result SAGE achieves the best average token-F1 on LoCoMo and reduces add-phase API cost by 3.4x on GPT-4o-mini.

Hydra boosts efficiency for long-context reasoning in resource-constrained settings.

problem Quadratic complexity of transformers limits long-context reasoning in resource-constrained systems.
method Hydra uses a modular architecture with adaptive routing between sparse global attention, mixture-of-experts, and dual memories.
result Hydra achieves significant throughput and accuracy improvements for long-context reasoning.

Energy Transformer integrates attention, energy models, and associative memory.

problem Lack of clear theoretical foundations in attention mechanisms and straightforward design of energy functions in energy-based models.
method Proposes Energy Transformer, a sequence of attention layers with a specifically engineered energy function.
result Obtained strong results on graph anomaly detection and classification tasks.

EASE optimizes exemplar selection for ICL in LLMs efficiently.

problem Efficiently selecting exemplars for in-context learning (ICL) in large language models (LLMs).
method EASE uses neural bandit algorithms to optimize exemplar sets, considering both exemplar ordering and instruction.
result EASE outperforms existing methods in finding optimal exemplar sets for all test queries.

Service-induced congestion in memory-constrained LLM serving

problem Service-induced congestion in memory-constrained large language model (LLM) serving
method Developing a discrete-time dynamical model of memory-constrained LLM inference
result The system converges to a unique worst-case limit cycle that is asymptotically stable outside a Lebesgue-measure-zero exact-capture set, with throughput losses as large as 50%.

Unified framework for sequence models using test-time regression.

problem Designing efficient sequence models with associative memory.
method Formalizing associative recall as regression over input tokens, deriving various sequence models.
result Clarifies the effectiveness of query-key normalization in softmax attention and offers new generalizations.

A new method uses a frozen language model to improve sample efficiency in reinforcement learning.

problem Improving sample efficiency in reinforcement learning with partially observable environments.
method FROZEN Hopfield network and HELM (History Embedding Language Model) method.
result HELM achieves new state-of-the-art results on Minigrid and Procgen environments.

Bidirectional sequence generation improves performance in conversational tasks.

problem Neural sequence generation typically considers only past tokens, limiting performance.
method Introduced placeholder tokens that can consider both past and future tokens in sequence generation.
result Bidirectional model outperforms competitive baselines on conversational tasks.

Large language models based on transformers have achieved great empirical successes. However, as they are deployed more widely, there is a growing need to better understand their internal mechanisms in order to make them more reliable. These models appear to store vast amounts of knowledge from their training data, and…

2023-06-01abs ↗pdf ↗

Transformers recall from long distributions with statistical guarantees.

problem Designing Transformers that can recall from arbitrarily long, distributional contexts.
method Recast associative memory as probability measures, decomposing the task into recall and prediction.
result A shallow measure-theoretic Transformer learns the recall-and-predict map under spectral assumptions.

This research improves capital efficiency and impermanent loss in cryptocurrency markets using multi-token trading pools.

problem Poor impermanent loss and capital efficiency in automated market makers.
method Analysis and construction of a multi-token token proactive market maker (MPMM).
result MPMM shows better impermanent loss and capital efficiency than comparable market makers.

This study examines whether tokenized assets improve liquidity and finds significant differences across categories.

problem Improving liquidity for real-world assets through tokenization.
method Examined tokenized real-world assets using Ethereum-based data, measuring liquidity through turnover, active addresses, and active-month indicator.
result Gold-backed tokens show more persistent on-chain activity than Treasury and private-credit-related products, but asset value alone does not reliably predict liquidity.

Paper introduces a method to assess liquidity risk in meme tokens using entity-linked address analysis.

problem High market volatility and vulnerability to manipulation in meme tokens.
method Multi-dimensional approach integrating fund flow analysis, behavioral similarity, and anomalous transaction detection.
result Significant disparities between apparent and actual liquidity in meme token markets.

New Feedback Transformer architecture improves model performance by exposing past representations to future.

problem Limitations of Transformers in fully exploiting sequential input.
method Proposes Feedback Transformer exposing all past representations to future.
result Demonstrates improved performance with smaller, shallower models.

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.

LoLCATs improves linearized LLM quality with less memory and compute.

problem Linearizing large language models (LLMs) often degrades model quality and requires expensive training.
method Two-step method: attention transfer and low-rank adaptation.
result Significant improvement in linearizing quality with 20+ points on 5-shot MMLU.

Proving that next-token prediction makes language models generate coherent long documents.

problem Understanding why language models generate coherent documents despite focusing on next-token prediction.
method Proving the power of next-token prediction in learning longer-range structure using Recurrent Neural Networks (RNN).
result Optimizing next-token prediction in RNNs yields a model that closely approximates the training distribution, even for long-range coherence.

QA-Token improves tokenization for noisy data, boosting model performance.

problem Tokenization ignores data quality, limiting model effectiveness on noisy corpora.
method QA-Token combines signal quality with vocabulary construction through bilevel optimization and reinforcement learning.
result QA-Token achieves state-of-the-art performance on genomic and financial datasets.

Minimal token perturbations reveal how Transformer models process information.

problem Understanding information propagation in Transformer models for interpretability.
method Study of minimal token perturbations on embedding space.
result Rare tokens cause larger shifts, and input information mixes deeper.