Related papers: ContextCache: Context-Aware Semantic Cache for Mul…

Large language models (LLMs) have achieved remarkable success in text-based tasks but often struggle to provide actionable guidance in real-world physical environments. This is because of their inability to recognize their limited…

Deploying large language models in long-horizon, goal-oriented interactions remains challenging because similar entities and facts recur under different latent goals and constraints, causing memory systems to retrieve context-mismatched…

Multi-modal Large Language Models (MLLMs) have achieved remarkable performance across a wide range of visual reasoning tasks, yet their vulnerability to safety risks remains a pressing concern. While prior research primarily focuses on…

Users interacting with Large Language Models (LLMs) in a multi-turn conversation routinely refine their requests or pivot to new topics. LLMs, however, often miss these topic shifts and carry over irrelevant context from previous turns,…

Recent advances in spoken dialogue language models (SDLMs) reflect growing interest in shifting from turn-based to full-duplex systems, where the models continuously perceive user speech streams while generating responses. This simultaneous…

Sequential recommendation models are crucial for next-item recommendations in online platforms, capturing complex patterns in user interactions. However, many focus on a single behavior, overlooking valuable implicit interactions like…

Large language models (LLMs) exhibit outstanding performance in machine translation via in-context learning. In contrast to sentence-level translation, document-level translation (DOCMT) by LLMs based on in-context learning faces two major…

Conversational text-to-SQL aims at converting multi-turn natural language queries into their corresponding SQL (Structured Query Language) representations. One of the most intractable problems of conversational text-to-SQL is modelling the…

Context distillation compresses contextual information into model parameters, yet existing methods often ignore how multiple distilled latent memories should be stored, retrieved, and safely activated in non-oracle settings. We formulate…

Large Language Models demonstrate outstanding performance in many language tasks but still face fundamental challenges in managing the non-linear flow of human conversation. The prevalent approach of treating dialogue history as a flat,…

Long-term memory systems enable conversational agents based on large language models (LLMs) to retain, retrieve, and apply user-specific information across multi-session interactions. However, existing evaluations mainly assess…

Training large language models (LLMs) in the cloud faces growing memory bottlenecks due to the limited capacity and high cost of GPUs. While GPU memory offloading to CPU and NVMe has made large-scale training more feasible, existing…

Recent advancements in Large Language Models (LLMs) have yielded remarkable success across diverse fields. However, handling long contexts remains a significant challenge for LLMs due to the quadratic time and space complexity of attention…

Recently, knowledge-grounded conversations in the open domain gain great attention from researchers. Existing works on retrieval-based dialogue systems have paid tremendous efforts to utilize neural networks to build a matching model, where…

Retrieving answers in a quick and low cost manner without hallucinations from a combination of structured and unstructured data using Language models is a major hurdle. This is what prevents employment of Language models in knowledge…

Large language models (LLMs) operate within fixed context windows that fundamentally limit conversational continuity. When context fills, compaction discards history irreversibly; when sessions end, all memory resets to zero. Existing…

To reduce LLM costs and latency, semantic caching systems must accurately identify when a new prompt matches a cached one. Current methods often rely on simplistic similarity measures, which limit their effectiveness. We introduce…

Recent advancements in multi-turn voice interaction models have improved user-model communication. However, while closed-source models effectively retain and recall past utterances, whether open-source models share this ability remains…

Although large language models (LLMs) demonstrate impressive performance for many language tasks, most of them can only handle texts a few thousand tokens long, limiting their applications on longer sequence inputs, such as books, reports,…

Large Language Models (LLMs) have demonstrated remarkable capabilities in handling long texts and have almost perfect performance in traditional retrieval tasks. However, their performance significantly degrades when it comes to numerical…