Related papers: DiffBench Meets DiffAgent: End-to-End LLM-Driven D…

Drivers' visual attention provides critical cues for anticipating latent hazards and directly shapes decision-making and control maneuvers, where its absence can compromise traffic safety. To emulate drivers' perception patterns and advance…

Ensuring the safety and robustness of autonomous driving systems necessitates a comprehensive evaluation in safety-critical scenarios. However, these safety-critical scenarios are rare and difficult to collect from real-world driving data,…

We propose a new finetuning method to provide pre-trained large language models (LMs) the ability to scale test-time compute through the diffusion framework. By increasing the number of diffusion steps, we show our finetuned models achieve…

Diffusion-based generative models (DBGMs) perturb data to a target noise distribution and reverse this process to generate samples. The choice of noising process, or inference diffusion process, affects both likelihoods and sample quality.…

The paradigm shift toward structure-driven molecule generation has been propelled by advances in deep generative models, such as variational auto-encoders and diffusion models. However, these generative models for molecular design remain…

Diffusion language models (DLMs) have emerged as a promising alternative to autoregressive models for faster inference via parallel token generation. We provide a rigorous foundation for this advantage by formalizing a model of parallel…

Can continuous diffusion models bring the same performance breakthrough on natural language they did for image generation? To circumvent the discrete nature of text data, we can simply project tokens in a continuous space of embeddings, as…

Recent progress in Large Language Models (LLMs) has drawn attention to their potential for accelerating drug discovery. However, a central problem remains: translating theoretical ideas into robust implementations in the highly specialized…

The rapid advancements in artificial intelligence (AI), particularly the Large Language Models (LLMs), have profoundly affected our daily work and communication forms. However, it is still a challenge to deploy LLMs on resource-constrained…

Diffusion large language models (dLLMs) have recently emerged as a promising alternative to autoregressive (AR) models, offering advantages such as accelerated parallel decoding and bidirectional context modeling. However, the vanilla…

Deep learning (DL) models have become core modules for many applications. However, deploying these models without careful performance benchmarking that considers both hardware and software's impact often leads to poor service and costly…

Benchmarks are the de facto standard for tracking progress in large language models (LLMs), yet static test sets can rapidly saturate, become vulnerable to contamination, and are costly to refresh. Scalable evaluation of open-ended items…

Diverse and controllable scenario generation (e.g., wind, solar, load, etc.) is critical for robust power system planning and operation. As AI-based scenario generation methods are becoming the mainstream, existing methods (e.g.,…

Vision-language models (VLMs) predominantly rely on autoregressive decoding, which generates tokens one at a time and fundamentally limits inference throughput. This limitation is especially acute in physical AI scenarios such as robotics…

Although autoregressive models have dominated language modeling in recent years, there has been a growing interest in exploring alternative paradigms to the conventional next-token prediction framework. Diffusion-based language models have…

Diffusion language models (DLMs) have emerged as a promising paradigm for large language models (LLMs), yet the non-deterministic behavior of DLMs remains poorly understood. The existing non-determinism evaluations for LLMs predominantly…

Large Language Model (LLM) Agents have demonstrated remarkable capabilities in task automation and intelligent decision-making, driving the widespread adoption of agent development frameworks such as LangChain and AutoGen. However, these…

Agent systems powered by large language models (LLMs) have demonstrated impressive performance on repository-level code-generation tasks. However, for tasks such as website codebase generation, which depend heavily on visual effects and…

Discrete diffusion language models (DLMs) generate text by iteratively denoising all positions in parallel, offering an alternative to autoregressive models. Controlled generation methods for DLMs, imported from autoregressive models, apply…

Recently, diffusion-based image generation methods are credited for their remarkable text-to-image generation capabilities, while still facing challenges in accurately generating multilingual scene text images. To tackle this problem, we…