Related papers: SpecSteer: Synergizing Local Context and Global Re…
Large Language Models (LLMs) are becoming key components in various mobile operating systems, driving smart applications like interactive chatbots and personal assistants. While bringing enhanced intelligence to mobile ends, their…
Test-time compute has emerged as a powerful paradigm for improving the performance of large language models (LLMs), where generating multiple outputs or refining individual chains can significantly boost answer accuracy. However, existing…
Personal Artificial Intelligence is currently hindered by the fragmentation of user data across isolated silos. While Retrieval-Augmented Generation offers a partial remedy, its reliance on unstructured vector similarity fails to capture…
Connecting conversation with external domain knowledge is vital for conversational recommender systems (CRS) to correctly understand user preferences. However, existing solutions either require domain-specific engineering, which limits…
Large language models have made revolutionary progress in generating human-like text, yet their outputs often tend to be generic, exhibiting insufficient structural diversity, which limits personalized expression. Recent advances in…
Speculative decoding (SD) accelerates large language model inference by employing a faster draft model for generating multiple tokens, which are then verified in parallel by the larger target model, resulting in the text generated according…
The Mixture-of-Experts (MoE) architecture has emerged as a promising approach to mitigate the rising computational costs of large language models (LLMs) by selectively activating parameters. However, its high memory requirements and…
Reasoning models enhance performance by tackling problems in a step-by-step manner, decomposing them into sub-problems and exploring long chains of thought before producing an answer. However, applying extended reasoning to every step…
With the impressive generative capabilities of diffusion models, personalized content synthesis has emerged as the most highly anticipated. However, the large model sizes and iterative nature of inference make it difficult to deploy…
Large language models (LLMs) promise to accelerate UI design, yet current tools struggle with two fundamentals: externalizing designers' intent and controlling iterative change. We introduce SPEC, a structured, parameterized, hierarchical…
Recent advances in large language models (LLMs) have enabled deep research systems that synthesize comprehensive, report-style answers to open-ended queries by combining retrieval, reasoning, and generation. Yet most frameworks rely on…
Retrieval-Augmented Generation (RAG) improves factual grounding in large language models but suffers from substantial latency due to synchronous retrieval. While recent work explores asynchronous retrieval, existing approaches rely on…
We propose an end-to-end, domain-independent neural encoder-aligner-decoder model for selective generation, i.e., the joint task of content selection and surface realization. Our model first encodes a full set of over-determined database…
Scaling inference-time computation has substantially improved the reasoning capabilities of language models. However, existing methods have significant limitations: serialized chain-of-thought approaches generate overly long outputs,…
Personalized natural language generation for explainable recommendations plays a key role in justifying why a recommendation might match a user's interests. Existing models usually control the generation process by aspect planning. While…
Conversational agents deployed in industrial-scale official account platforms must generate responses that are both contextually grounded and stylistically aligned-requirements that existing methods struggle to meet. Chain-of-thought (CoT)…
Nowadays, billions of people engage in communication and express their opinions on the internet daily. Unfortunately, not all of these expressions are friendly or compliant, making content moderation an indispensable task. A common approach…
The prevailing approach to distilling reasoning from Large Language Models (LLMs)-behavioral cloning from textual rationales-is fundamentally limited. It teaches Small Language Models (SLMs) to mimic surface-level patterns rather than the…
Speculative decoding is an effective and lossless method for Large Language Model (LLM) inference acceleration. It employs a smaller model to generate a draft token sequence, which is then verified by the original base model. In multi-GPU…
Design generation requires tight integration of neural and symbolic reasoning, as good design must meet explicit user needs and honor implicit rules for aesthetics, utility, and convenience. Current automated design tools driven by neural…