arXiv:2603. 18446v2 Announce Type: replace-cross Abstract: Long-context inference remains challenging for large language models due to attention dilution and out-of-distribution degradation.
arXiv:2601.03199v2 Announce Type: replace-cross Abstract: Diffusion language models (DLMs) have shown strong potential for general natural language tasks with in-context examples. Existing In-Context...
The paper introduces Retrieval-Augmented Decoding (RAD), a decoding-time method that improves the truthfulness of large language models without retraining. RAD uses a small reference set of up to ten annotated examples to build a grounding space of context embeddings and next-token logits, which it retrieves and aggregates during inference to shape the model’s output. Experiments on four open-ended generation benchmarks and four different LLMs show that RAD consistently outperforms strong baselines and generalizes well across tasks.
arXiv:2510. 00615v3 Announce Type: replace Abstract: Large language models (LLMs) are increasingly deployed as agents in dynamic real-world environments, where success depends on maintaining precise records of actions and observations.
arXiv:2608. 05813v1 Announce Type: new Abstract: Personalizing language models (LMs) to individual user preferences is essential for aligning responses with diverse goals and backgrounds.
arXiv:2607. 14327v1 Announce Type: cross Abstract: Efficient long-context inference is not only about reducing memory cost, but also about keeping useful contextual evidence accessible as generation proceeds.
arXiv:2606. 09659v1 Announce Type: cross Abstract: Long-context language model inference is bottlenecked by memory, as the KV cache grows with context length.
arXiv:2606. 26875v1 Announce Type: cross Abstract: Reasoning capability has advanced rapidly in large language models (LLMs), leading to an increasing size of key-value (KV) cache in both prefilling and decoding stages.
arXiv:2608. 12218v1 Announce Type: cross Abstract: Large language models are increasingly trained and deployed with long contexts that span documents, code repositories, and interaction histories.
arXiv:2607. 11614v1 Announce Type: cross Abstract: Extending the context length of large language models (LLMs) is critical for many real-world applications, yet standard transformers remain constrained by quadratic compute and linear memory scaling.
arXiv:2609.00796v1 Announce Type: new Abstract: As one of the most critical challenges in large language models, contextual faithfulness directly determines their reliability in knowledge-intensive a...
The paper introduces ACache, an affix-oriented cache reuse mechanism for Diffusion Large Language Models (DLLMs). ACache identifies a small set of critical affix tokens, called Anchor Tokens, and selectively recomputes their key-value states while reusing the rest of the affix cache. Experiments on Fast-dLLM and Nano-vLLM show that recomputing about 20% of affix tokens restores accuracy and can reduce recompute latency by up to 55.7% while improving throughput by up to 1.68×.
The paper introduces Variance‑Calibrated Modulation (VCM), a training‑free pre‑decoding technique that reshapes language model probability distributions before truncation. VCM uses two dynamic mechanisms: a Contextual Searchlight via PMI to suppress stopwords and highlight context‑relevant tokens, and an Adaptive Self‑Debiasing that applies scale‑invariant penalization based on real‑time logit standard deviation. Experiments on open‑ended generation, factual QA, and mathematical reasoning show that VCM consistently reduces the likelihood trap, improving diversity, coherence, and reasoning accuracy with minimal computational cost.