Quantization, distillation, pruning and serving work aimed at the same accuracy for less memory, latency and money.
arXiv:2607. 28292v1 Announce Type: cross Abstract: Large Language Models (LLMs) deployed in dynamic financial environments face a critical challenge: maintaining factual accuracy as market conditions, regulations, and corporate facts change continuously.
arXiv:2607. 27849v1 Announce Type: cross Abstract: An open-weight LLM can write composition setpoints every five minutes.
arXiv:2607. 27704v1 Announce Type: cross Abstract: As large language models (LLMs) continue to demonstrate exceptional capabilities across various domains, the challenge of achieving energy-efficient and accurate inference becomes increasingly critical.
arXiv:2607. 28582v1 Announce Type: new Abstract: On-policy self-distillation (OPSD) is a promising approach to improve reasoning language models, but it remains brittle in practice: making it work reliably often requires substantial engineering effort.
arXiv:2607. 28495v1 Announce Type: new Abstract: Stage-replay diagnostics reconstruct intermediate token prefixes and treat fresh-prefill continuation as continuation from the decoder state that originally reached the prefix.
arXiv:2607. 28308v1 Announce Type: new Abstract: Sparse mixture-of-experts (MoE) language models route each token to multiple experts, suggesting a geometric account of their benefit: co-selected experts should contribute distinct representation directions.
arXiv:2607. 28026v1 Announce Type: new Abstract: Recent advances in post-training Large Language Models (LLMs) increasingly rely on Reinforcement Learning with Verifiable Rewards (RLVR) or On-Policy Self-Distillation (OPSD).
arXiv:2607. 27968v1 Announce Type: new Abstract: Machine unlearning seeks to selectively remove specific knowledge from trained language models without full retraining, a growing necessity under privacy regulations such as GDPR and the EU AI Act.
arXiv:2607. 27913v1 Announce Type: new Abstract: Foundation models offer a promising paradigm for Electroencephalography (EEG) analysis, leveraging generalizable representations from vast unlabeled datasets.
arXiv:2607. 27770v1 Announce Type: new Abstract: A single reinforcement-learning run can produce a strong reasoner yet an incomplete teacher: it often amplifies only a subset of the valid solution modes.
arXiv:2607. 27600v1 Announce Type: new Abstract: Key-value (KV) cache management through compression and eviction strategies has emerged as an important research direction in recent years.
This work presents Fairness Pruning, a lightweight structural intervention method designed for the management and future mitigation of demographic bias in large language models (LLMs). As a foundational empirical validation of this method, this work focuses on causal bias localization.
Sparse mixture-of-experts (MoE) language models route each token to multiple experts, suggesting a geometric account of their benefit: co-selected experts should contribute distinct representation directions. Existing evidence often conflates route coherence, candidate quality, and candidate-by-context interaction.
Practitioners accept a compressed language model once it clears a stack of data-cheap quality guards: perplexity within a small factor of the original, downstream accuracy (for example MMLU) inside a confidence interval, and data-free output-fidelity signals that compare the compressed and original network's internal representations under random probe inputs. This stack has a blind spot.
Time-varying implicit neural representations (INRs) provide a compact representation of scientific volumes and, for modalities such as dynamic X-ray computed tomography (CT), are often the only practical way to represent the data. However, interactive volume rendering of INRs is challenging, as cheap memory lookups are replaced by expensive neural inferences, hindering the performance.
Recent advances in post-training Large Language Models (LLMs) increasingly rely on Reinforcement Learning with Verifiable Rewards (RLVR) or On-Policy Self-Distillation (OPSD). While OPSD provides dense, logit-level supervision, it inherently suffers from exposure bias due to the privileged information of the self-teacher.
Large language model training in open-ended domains lacks verifiable rewards, making task preferences difficult to formalize as effective supervision. Contexts can convey such preferences, yet provide little additional supervision once distilled into the student, motivating contexts that evolve with student performance.
We derive finite-sample generalization bounds for Transformers trained with dynamic programming recursions. Building on the doubly lifted, measure-valued formulation of Transformer dynamics, we view data sets as probability laws on pairs of empirical input-output measures, allowing us to interpret the training problem as a finite-horizon Markovian control problem.
Multimodal foundation models are reshaping edge-cloud visual intelligence from task-specific feature pipelines into token-based interfaces, where edge devices encode visual inputs into tokens for a general-purpose cloud MLLM. However, dense visual-token sequences increase cloud-side inference costs.
Foundation models offer a promising paradigm for Electroencephalography (EEG) analysis, leveraging generalizable representations from vast unlabeled datasets. Yet, Transformer-based architectures face a critical bottleneck: global attention mechanisms couple the attention memory state to the signal duration, causing memory overflow during continuous monitoring.