Related papers: Anchorless Diversification for Parallel LLM Ideati…

We present a system for autonomous book ideation that replaces human focus groups with synthetic reader panels -- diverse collections of LLM-instantiated reader personas that evaluate book concepts through structured tournament…

The recent rise of reasoning-tuned Large Language Models (LLMs)--which generate chains of thought (CoTs) before giving the final answer--has attracted significant attention and offers new opportunities for gaining insights into human label…

Accelerating the inference of large language models (LLMs) is a critical challenge in generative AI. Speculative decoding (SD) methods offer substantial efficiency gains by generating multiple tokens using a single target forward pass.…

Autonomous science promises to augment scientific discovery, particularly in complex fields like biomedicine. However, this requires AI systems that can consistently generate novel and diverse solutions to open-ended problems. We evaluate…

Pre-trained large language models (LLMs) have been demonstrated to possess intrinsic reasoning capabilities that can emerge naturally when expanding the response space. However, the neural representation mechanisms underlying these…

Reasoning language models can solve increasingly complex tasks, but struggle to produce the calibrated confidence estimates necessary for reliable deployment. Existing calibration methods usually depend on labels or repeated sampling at…

Test-Time Scaling (TTS) enhances the reasoning capabilities of large language models by allocating additional inference compute to explore the solution space. However, existing parallel TTS methods typically keep branches isolated during…

Safe deployment of large language models (LLMs) may benefit from a reliable method for assessing their generated content to determine when to abstain or to selectively generate. While likelihood-based metrics such as perplexity are widely…

Diffusion Language Models (DLMs) promise parallel generation and bidirectional context, yet they underperform autoregressive (AR) models in both likelihood modeling and generated text quality. We identify that this performance gap arises…

The growing availability of generative AI technologies such as large language models (LLMs) has significant implications for creative work. This paper explores twofold aspects of integrating LLMs into the creative process - the divergence…

We revisit test-time scaling for language model reasoning and ask a fundamental question: at equal token budget and compute, is it better to run multiple independent chains in parallel, or to run fewer chains that iteratively refine through…

Scientific innovation is pivotal for humanity, and harnessing large language models (LLMs) to generate research ideas could transform discovery. However, existing LLMs often produce simplistic and repetitive suggestions due to their limited…

It has long been recognized that it is not enough for a Recommender System (RS) to provide recommendations based only on their relevance to users. Among many other criteria, the set of recommendations may need to be diverse. Diversity is…

Active learning for imbalanced classification tasks is challenging as the minority classes naturally occur rarely. Gathering a large pool of unlabelled data is thus essential to capture minority instances. Standard pool-based active…

While Large Language Models (LLMs) demonstrate remarkable capabilities in scientific tasks such as literature analysis and experimental design (e.g., accurately extracting key findings from papers or generating coherent experimental…

A line of work in planning uses LLM not to generate a plan, but to generate a formal representation in some planning language, which can be input into a symbolic solver to deterministically find a plan. While showing improved trust and…

While model serving has unlocked unprecedented capabilities, the high cost of serving large-scale models continues to be a significant barrier to widespread accessibility and rapid innovation. Compiler optimizations have long driven…

Large Language Models (LLMs) have demonstrated the ability to tackle increasingly complex tasks through advanced reasoning, long-form content generation, and tool use. Solving these tasks often involves long inference-time computations. In…

Deploying Large Language Models (LLMs) for discriminative workloads is often limited by inference latency, compute, and API costs at scale. Active distillation reduces these costs by querying an LLM oracle to train compact discriminative…

Scientific idea generation is central to discovery, requiring the joint satisfaction of novelty and scientific soundness. Unlike standard reasoning or general creative generation, scientific ideation is inherently open-ended and…