Related papers: mlirSynth: Automatic, Retargetable Program Raising…

Implicit neural representation (INR) models signals as continuous functions using neural networks, offering efficient and differentiable optimization for inverse problems across diverse disciplines. However, the representational capacity of…

Composed Image Retrieval (CIR) aims to retrieve target images based on a hybrid query comprising a reference image and a modification text. Early dual-tower Vision-Language Models (VLMs) struggle with cross-modality compositional reasoning…

High-Level Synthesis (HLS) enables rapid prototyping of complex hardware designs by translating C or C++ code to low-level RTL code. However, the testing and evaluation of HLS designs still typically rely on slow RTL-level simulators that…

Supervised fine-tuning (SFT) of large language models (LLMs) for specialized tasks requires high-quality datasets, but manual curation is prohibitively expensive. Synthetic data generation offers scalability, but its effectiveness relies on…

Recent advances in large language model (LLM) reasoning through reinforcement learning rely on annotated datasets for verifiable rewards, which may limit models' ability to surpass human-level performance. While self-play offers a promising…

Large Language Models (LLMs) typically excel at coding tasks involving high-level programming languages, as opposed to lower-level programming languages, such as assembly. We propose a synthetic data generation method named C-ing Clearly,…

Specializing large language models (LLMs) for local deployment in domain-specific use cases is necessary for strong performance while meeting latency and privacy constraints. However, conventional task-specific adaptation approaches do not…

Composed Image Retrieval (CIR) involves retrieving a target image based on a composed query of an image paired with text that specifies modifications or changes to the visual reference. CIR is inherently an instruction-following task, as…

Large language models excel in English but still struggle with complex reasoning in many low-resource languages (LRLs). Existing encoder-plus-decoder methods such as LangBridge and MindMerger raise accuracy on mid and high-resource…

The internalization of chain-of-thought processes into hidden states has emerged as a highly efficient paradigm for scaling test-time compute. However, existing activation steering methods rely on static control vectors that fail to adapt…

Despite significant investment in software infrastructure, machine learning systems, runtimes and compilers do not compose properly. We propose a new design aiming at providing unprecedented degrees of modularity, composability and…

Current inference scaling methods, such as Self-consistency and Best-of-N, have proven effective in improving the accuracy of LLMs on complex reasoning tasks. However, these methods rely heavily on the quality of candidate responses and are…

Cross-lingual information retrieval (CLIR) addresses the challenge of retrieving relevant documents written in languages different from that of the original query. Research in this area has typically framed the task as monolingual retrieval…

This paper explores a novel technique for improving recall in cross-language information retrieval (CLIR) systems using iterative query refinement grounded in the user's lexical-semantic space. The proposed methodology combines multi-level…

Practical cloud-edge deployment of Cross-Modal Re-identification (CM-ReID) faces challenges due to maintaining a fragmented ecosystem of specialized cloud models for diverse modalities. While Multi-Modal Large Language Models (MLLMs) offer…

As inference on Large Language Models (LLMs) emerges as an important workload in machine learning applications, weight quantization has become a standard technique for efficient GPU deployment. Quantization not only reduces model size, but…

Serving Large Language Models (LLMs) is critical for AI-powered applications, yet it demands substantial computational resources, particularly in memory bandwidth and computational throughput. Low-precision computation has emerged as a key…

Artificial Intelligence (AI) has achieved remarkable success in specialized tasks but struggles with efficient skill acquisition and generalization. The Abstraction and Reasoning Corpus (ARC) benchmark evaluates intelligence based on…

Logic synthesis is one of the most important steps in design and implementation of digital chips with a big impact on final Quality of Results (QoR). For a most general input circuit modeled by a Directed Acyclic Graph (DAG), many logic…

Static analyses play a fundamental role during compilation: they discover facts that are true in all executions of the code being compiled, and then these facts are used to justify optimizations and diagnostics. Each static analysis is…