Related papers: KaVa: Latent Reasoning via Compressed KV-Cache Dis…

Large Language Models (LLMs) demonstrate their reasoning ability through chain-of-thought (CoT) generation. However, LLM's autoregressive decoding may limit the ability to revisit and refine earlier tokens in a holistic manner, which can…

Large Language Models (LLMs) have revolutionized a wide range of domains such as natural language processing, computer vision, and multi-modal tasks due to their ability to comprehend context and perform logical reasoning. However, the…

Large language models (LLMs) have shown remarkable performance in complex reasoning tasks, but their efficiency is hindered by the substantial memory and computational costs associated with generating lengthy tokens. In this paper, we…

Recent advances in large language models (LLMs) have significantly boosted long-context processing. However, the increasing key-value (KV) cache size poses critical challenges to memory and execution efficiency. Most KV cache compression…

Chain-of-thought (CoT) reasoning improves large language models (LLMs) on difficult tasks, but it also makes inference expensive because every intermediate step must be generated as a discrete token. Latent reasoning reduces visible token…

In many practical applications, large language models (LLMs) need to acquire new knowledge not present in their pre-training data. Efficiently leveraging this knowledge usually relies on supervised fine-tuning or retrieval-augmented…

Techniques enabling large language models (LLMs) to "think more" by generating and attending to intermediate reasoning steps have shown promise in solving complex problems. However, the standard approaches generate sequences of discrete…

Self-distillation has emerged as an effective post-training paradigm for LLMs, often improving performance while shortening reasoning traces. However, in mathematical reasoning, we find that it can reduce response length while degrading…

Efficient inference of large language models (LLMs) is hindered by an ever-growing key-value (KV) cache, making KV cache compression a critical research direction. Traditional methods selectively evict less important KV cache entries, which…

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…

Temporal knowledge graphs (TKGs) support reasoning over time-evolving facts, yet state-of-the-art models are often computationally heavy and costly to deploy. Existing compression and distillation techniques are largely designed for static…

KV cache quantization can improve Large Language Models (LLMs) inference throughput and latency in long contexts and large batch-size scenarios while preserving LLMs effectiveness. However, current methods have three unsolved issues:…

Large Language Models (LLMs) are increasingly expected to operate over long contexts, yet standard softmax attention incurs a KV cache that grows linearly with sequence length, quickly becoming the bottleneck for long context inference. A…

Accurate clinical diagnosis requires extensive domain knowledge and complex clinical reasoning capabilities. Although large language models (LLMs) hold great potential for clinical reasoning, their high computational and memory requirements…

The rapid expansion of context window sizes in Large Language Models~(LLMs) has enabled them to tackle increasingly complex tasks involving lengthy documents. However, this progress comes at the cost of a substantial increase in memory…

Large language models (LLMs) have demonstrated significant improvements in contextual understanding. However, their ability to attend to truly critical information during long-context reasoning and generation still falls behind the pace.…

Distilling reasoning traces from strong large language models into smaller ones is a promising route to improve intelligence in resource-constrained settings. Existing approaches face a fundamental trade-off: offline distillation from…

While large audio-language models (LALMs) have demonstrated state-of-the-art audio understanding, their reasoning capability in complex soundscapes still falls behind large vision-language models (LVLMs). Compared to the visual domain, one…

The long-output context generation of large reasoning models enables extended chain of thought (CoT) but also drives rapid growth of the key-value (KV) cache, quickly overwhelming GPU memory. To address this challenge, we propose ThinKV, a…

Large language models (LLMs) excel at complex reasoning tasks but remain computationally expensive, limiting their practical deployment. To address this, recent works have focused on distilling reasoning capabilities into smaller language…