Related papers: AdapTrack: Constrained Decoding without Distorting…

Recent work has shown that inference-time reasoning and reflection can improve text-to-image generation without retraining. However, existing approaches often rely on implicit, holistic critiques or unconstrained prompt rewrites, making…

Generating executable code from natural language instructions using Large Language Models (LLMs) poses challenges such as semantic ambiguity and understanding taskspecific contexts. To address these issues, we propose a system called…

Large Language Models (LLMs) (e.g., ChatGPT) have shown impressive performance in code generation. LLMs take prompts as inputs, and Chain-of-Thought (CoT) prompting is the state-of-the-art prompting technique. CoT prompting asks LLMs first…

Parallel trajectory optimization via the Alternating Direction Method of Multipliers (ADMM) has emerged as a scalable approach to long-horizon motion planning. However, existing frameworks typically decompose the problem into parallel…

Large language models (LLMs) have recently demonstrated the potential in acting as autonomous agents for sequential decision-making tasks. However, most existing methods either take actions greedily without planning or rely on static plans…

We argue that diffusion models' success in modeling complex distributions is, for the most part, coming from their input conditioning. This paper investigates the representation used to condition diffusion models from the perspective that…

Automated code completion, aiming at generating subsequent tokens from unfinished code, has been significantly benefited from recent progress in pre-trained Large Language Models (LLMs). However, these models often suffer from coherence…

Recent studies have adopted pre-trained language models, such as CodeT5 and CodeGPT, for automated program generation tasks like code generation, repair, and translation. Numerous language model-based approaches have been proposed and…

Today, an increasing number of Adaptive Deep Neural Networks (AdNNs) are being used on resource-constrained embedded devices. We observe that, similar to traditional software, redundant computation exists in AdNNs, resulting in considerable…

Retrieval-Augmented Generation (RAG) enhances coding tasks by incorporating retrieved code examples into prompts. However, lengthy prompts, often exceeding tens of thousands of tokens, introduce challenges related to limited context windows…

We introduce MathConstraint, a hard, adaptive benchmark for evaluating the combinatorial reasoning capabilities of LLMs. We combine constraint satisfaction problems with rigorous solver-based verification and design an adaptive generator to…

While deep neural networks have demonstrated remarkable performance across various tasks, they typically require massive training data. Due to the presence of redundancies and biases in real-world datasets, not all data in the training…

As one of the key tools in many security tasks, decompilers reconstruct human-readable source code from binaries. Yet, despite recent advances, their outputs often suffer from syntactic and semantic errors and remain difficult to read.…

Recently, 3D generative models have shown promising performances in structure-based drug design by learning to generate ligands given target binding sites. However, only modeling the target-ligand distribution can hardly fulfill one of the…

Diffusion language models (DLMs) have emerged as a promising alternative to autoregressive language generation due to their potential for parallel decoding and global refinement of the entire sequence. To unlock this potential, DLM…

Instructions augmentation is a crucial step for unleashing the full potential of large language models (LLMs) in downstream tasks. Existing Self-Instruct methods primarily simulate new instructions from a few initial instructions with…

Diffusion language models (DLMs) have recently emerged as a strong alternative to autoregressive models by enabling parallel text generation. To improve inference efficiency and KV-cache compatibility, prior work commonly adopts block-based…

Alignment techniques enable Large Language Models (LLMs) to generate outputs that align with human preferences and play a crucial role in their effectiveness. However, their impact often diminishes when applied to Small Language Models…

Retrieval-augmented code generation utilizes Large Language Models as the generator and significantly expands their code generation capabilities by providing relevant code, documentation, and more via the retriever. The current approach…

Retrieval-augmented generation (RAG) has emerged as a pivotal method for expanding the knowledge of large language models. To handle complex queries more effectively, researchers developed Adaptive-RAG (A-RAG) to enhance the generated…