Related papers: Think-While-Generating: On-the-Fly Reasoning for P…

Recent breakthroughs in generative reasoning have fundamentally reshaped how large language models (LLMs) address complex tasks, enabling them to dynamically retrieve, refine, and organize information into coherent multi-step reasoning…

Recent large language models (LLMs) show promise in design tasks, yet a fundamental misalignment persists: design thinking requires iterative intent formulation, while LLMs treat inputs as complete specifications. This challenges design…

Realizing personalized intelligence faces a core dilemma: sending user history to centralized large language models raises privacy concerns, while on-device small language models lack the reasoning capacity required for high-quality…

Large Reasoning Models (LRMs) achieve remarkable performance by explicitly generating multi-step chains of thought, but this capability incurs substantial inference latency and computational cost. Collaborative inference offers a promising…

Large language models (LLMs) have demonstrated impressive capabilities in natural language generation. However, their output quality can be inconsistent, posing challenges for generating natural language from logical forms (LFs). This task…

Large Language Models (LLMs) are widely used in real-time voice chat applications, typically in combination with text-to-speech (TTS) systems to generate audio responses. However, their large size often leads to noticeable latency between…

As test-time scaling becomes a pivotal research frontier in Large Language Models (LLMs) development, contemporary and advanced post-training methodologies increasingly focus on extending the generation length of long Chain-of-Thought (CoT)…

Large Language Models (LLMs) have shown prominent performance in various downstream tasks and prompt engineering plays a pivotal role in optimizing LLMs' performance. This paper, not only as an overview of current prompt engineering…

Large language models (LLMs) have shown impressive capabilities in handling complex tasks through long-chain reasoning. However, the extensive reasoning steps involved can significantly increase computational costs, posing challenges for…

Generating and voting multiple answers is an effective method to mitigate reasoning inconsistencies of large language models (LLMs). Prior works have shown that multiple reasoning formats outperform a single format when generating multiple…

Large language models (LLMs) have demonstrated strong reasoning abilities in mathematical tasks, often enhanced through reinforcement learning (RL). However, RL-trained models frequently produce unnecessarily long reasoning traces -- even…

Large language models (LLMs) have demonstrated impressive capabilities in various reasoning tasks, aided by techniques like chain-of-thought prompting that elicits verbalized reasoning. However, LLMs often generate text with obvious…

Current autoregressive language models (ARMs) achieve high accuracy but require long token sequences, making them costly. Discrete diffusion language models (DDLMs) enable parallel and flexible generation within a fixed number of steps and…

Numerical reasoning over hybrid data containing tables and long texts has recently received research attention from the AI community. To generate an executable reasoning program consisting of math and table operations to answer a question,…

Code generation remains a challenging task that requires precise and structured reasoning. Existing Test Time Scaling (TTS) methods, including structured tree search, have made progress in exploring reasoning paths but still face two major…

Large language models (LLMs) excel on a variety of reasoning benchmarks, but previous studies suggest they sometimes struggle to generalize to unseen questions, potentially due to over-reliance on memorized training examples. However, the…

Human reasoning involves different strategies, each suited to specific problems. Prior work shows that large language model (LLMs) tend to favor a single reasoning strategy, potentially limiting their effectiveness in diverse reasoning…

Generative LLMs typically improve Named Entity Recognition (NER) performance through instruction tuning. They excel at generating entities by semantic pattern matching but lack an explicit, verifiable reasoning mechanism. This "cognitive…

Large Audio-Language Models (LALMs) have made significant progress in audio understanding, yet they primarily operate as perception-and-answer systems without explicit reasoning processes. Existing methods for enhancing audio reasoning rely…

This position paper proposes a fundamental shift in designing code generation models: treating reasoning depth as a controllable resource. Rather than being an incidental byproduct of prompting, we argue that the trade-off between rapid,…