Related papers: Accuracy Is Speed: Towards Long-Context-Aware Rout…

Applications such as cloud gaming, video streaming, telemetry, ML inference, and data transfer provide a better experience when data is released at the receiver with timing reflecting how the data enters the sender. In practice, network…

Diffusion large language models (dLLMs) offer a promising paradigm for parallel text generation, but in practice they face an accuracy-parallelism trade-off, where increasing tokens per forward (TPF) often degrades generation quality.…

Large Language Models (LLMs) present a critical trade-off between inference quality and computational cost: larger models offer superior capabilities but incur significant latency, while smaller models are faster but less powerful. Existing…

Reinforcement learning (RL) has become a pivotal component of large language model (LLM) post-training, and agentic RL extends this paradigm to operate as agents through multi-turn interaction and tool use. Scaling such systems exposes two…

Reinforcement Learning has emerged as a key driver for LLM reasoning. This capability is equally pivotal in long-context scenarios--such as long-dialogue understanding and structured data analysis, where the challenge extends beyond…

Long-context modeling has drawn more and more attention in the area of Large Language Models (LLMs). Continual training with long-context data becomes the de-facto method to equip LLMs with the ability to process long inputs. However, it…

Online Network Resource Allocation (ONRA) for service provisioning is a fundamental problem in communication networks. As a sequential decision-making under uncertainty problem, it is promising to approach ONRA via Reinforcement Learning…

LLM decoding is bottlenecked for large batches and long contexts by loading the key-value (KV) cache from high-bandwidth memory, which inflates per-token latency, while the sequential nature of decoding limits parallelism. We analyze the…

Despite the ability to produce human-level speech for in-domain text, attention-based end-to-end text-to-speech (TTS) systems suffer from text alignment failures that increase in frequency for out-of-domain text. We show that these failures…

Inspired by the success of language models (LM), scaling up deep learning recommendation systems (DLRS) has become a recent trend in the community. All previous methods tend to scale up the model parameters during training time. However,…

Chunk-based inference stands out as a popular approach in developing real-time streaming speech recognition, valued for its simplicity and efficiency. However, because it restricts the model's focus to only the history and current chunk…

Most multi-agent systems rely exclusively on autoregressive language models (ARMs) that are based on sequential generation. Although effective for fluent text, ARMs limit global reasoning and plan revision. On the other hand, Discrete…

Long-form speech recognition is an application area of increasing research focus. ASR models based on multi-head attention (MHA) are ill-suited to long-form ASR because of their quadratic complexity in sequence length. We build on recent…

Efficiently routing queries to the optimal large language model (LLM) is crucial for optimizing the cost-performance trade-off in multi-model systems. However, most existing routers rely on single-model selection, making them susceptible to…

Test-time adaptation (TTA) offers a compelling remedy for machine learning (ML) models that degrade under domain shifts, improving generalisation on-the-fly with only unlabelled samples. This flexibility suits real deployments, yet…

Finding the most relevant person for a job proposal in real time is challenging, especially when resumes are long, structured, and multilingual. In this paper, we propose a re-ranking model based on a new generation of late cross-attention…

Long-context inference remains challenging for large language models due to attention dilution and out-of-distribution degradation. Context selection mitigates this limitation by attending to a subset of key-value cache entries, yet most…

With increasing urban traffic complexity, Traffic Signal Control (TSC) is essential for optimizing traffic flow and improving road safety. Large Language Models (LLMs) emerge as promising approaches for TSC. However, they are prone to…

Test-time scaling (TTS) -- the dynamic allocation of compute during inference -- is a promising direction for improving reasoning in large language models (LLMs). However, a systematic comparison of well-known TTS strategies under identical…

Urban forecasting models often face a severe data imbalance problem: only a few cities have dense, long-span records, while many others expose short or incomplete histories. Direct transfer from data-rich to data-scarce cities is unreliable…