Related papers: LiteStage: Latency-aware Layer Skipping for Multi-…

Multi-hop question answering (MHQA) enables accurate answers to complex queries by retrieving and reasoning over evidence dispersed across multiple documents. Existing MHQA approaches mainly rely on iterative retrieval-augmented generation,…

Generative reasoning with large language models (LLMs) often involves long decoding sequences, leading to substantial memory and latency overheads from accumulating key-value (KV) caches. While existing KV compression methods primarily…

The success of large language models (LLMs) depends heavily on large-scale, high-quality instruction-following and reinforcement datasets. However, generating such data through human annotation is prohibitively time-consuming particularly…

Large Reasoning Language Models (LRLMs) demonstrate impressive capabilities on complex tasks by utilizing long Chain-of-Thought reasoning. However, they are prone to overthinking, which generates redundant reasoning steps that degrade both…

Token-level Chain-of-Thought (CoT) prompting has become a standard way to elicit multi-step reasoning in large language models (LLMs), especially for mathematical word problems. However, generating long intermediate traces increases output…

Advanced reasoning in LLMs on challenging domains like mathematical reasoning can be tackled using verifiable rewards based reinforced fine-tuning (ReFT). In standard ReFT frameworks, a behavior model generates multiple completions with…

Structured reasoning over natural language inputs remains a core challenge in artificial intelligence, as it requires bridging the gap between unstructured linguistic expressions and formal logical representations. In this paper, we propose…

Reasoning Large Language Models (LLMs) have shown promising results when tasked with solving complex problems. In this paper, we propose and evaluate a multi-stage workflow that leverages the capabilities of fine-tuned reasoning LLMs to…

Recent work has shown that eliciting Large Language Models (LLMs) to generate reasoning traces in natural language before answering the user's request can significantly improve their performance across tasks. This approach has been extended…

Curating foundation speech models for edge and IoT settings, where computational resources vary over time, requires dynamic architectures featuring adaptable reduction strategies. One emerging approach is layer dropping ($\mathcal{LD}$)…

Large Language Models (LLMs) solve many reasoning tasks via chain-of-thought (CoT) prompting, but smaller models (about 7 to 8B parameters) still struggle with multi-step reasoning under tight compute and token budgets. Existing test time…

Large Reasoning Models (LRMs) often suffer from computational inefficiency due to overthinking, where a fixed reasoning budget fails to match the varying complexity of tasks. To address this issue, we propose Adaptive Overclocking, a method…

Query-service relevance prediction in e-commerce search systems faces strict latency requirements that prevent the direct application of Large Language Models (LLMs). To bridge this gap, we propose a two-stage reasoning distillation…

What makes a difference in the post-training of LLMs? We investigate the training patterns of different layers in large language models (LLMs) through the lens of the gradient. We are specifically interested in how fast vs. slow thinking…

Data and pipeline parallelism are ubiquitous for training of Large Language Models (LLM) on distributed nodes. Driven by the need for cost-effective training, recent work explores efficient communication arrangement for end to end training.…

Recent advancements in the field of large language models, particularly through the Chain of Thought (CoT) approach, have demonstrated significant improvements in solving complex problems. However, existing models either tend to sacrifice…

Existing knowledge-grounded dialogue systems typically use finetuned versions of a pretrained language model (LM) and large-scale knowledge bases. These models typically fail to generalize on topics outside of the knowledge base, and…

Large language models (LLMs) achieve remarkable performance across tasks but incur substantial computational costs due to their deep, multi-layered architectures. Layer pruning has emerged as a strategy to alleviate these inefficiencies,…

We study Latent Recurrent Transformer (LRT), a lightweight augmentation of autoregressive transformers that reuses a high-level source-layer hidden state from the previous token as recurrent memory for the next token. Because this source…

This paper introduces lateral thinking to implement System-2 reasoning capabilities in AI systems, focusing on anticipatory and causal reasoning under uncertainty. We present a framework for systematic generation and modeling of lateral…