Related papers: let (rec) insertion without Effects, Lights or Mag…

This paper presents INGRESS, a robot system that follows human natural language instructions to pick and place everyday objects. The core issue here is the grounding of referring expressions: infer objects and their relationships from input…

Quasi-quotation (or, code templates) has long been used as a convenient tool for code generation, commonly implemented as a pre-processing/translation into code-generation combinators. The original MetaOCaml was also based on such…

The application of zero-shot learning in computer vision has been revolutionized by the use of image-text matching models. The most notable example, CLIP, has been widely used for both zero-shot classification and guiding generative models…

We propose RecaLLM, a set of reasoning language models post-trained to make effective use of long-context information. In-context retrieval, which identifies relevant evidence from context, and reasoning are deeply intertwined: retrieval…

Reinforcement Learning (RL) can enable agents to learn complex tasks. However, it is difficult to interpret the knowledge and reuse it across tasks. Inductive biases can address such issues by explicitly providing generic yet useful…

Beyond representing the external world, humans also represent their own cognitive processes. In the context of perception, this metacognition helps us identify unreliable percepts, such as when we recognize that we are seeing an illusion.…

We present evidence that language models (LMs) of code can learn to represent the formal semantics of programs, despite being trained only to perform next-token prediction. Specifically, we train a Transformer model on a synthetic corpus of…

Some effects are considered to be higher-level than others. High-level effects provide expressive and succinct abstraction of programming concepts, while low-level effects allow more fine-grained control over program execution and…

FIRRTL is an intermediate representation language for Register Transfer Level (RTL) hardware designs. In FIRRTL programs, the bit widths of many components are not specified explicitly and must be inferred during compilation. In mainstream…

Implicit computational complexity, which aims at characterizing complexity classes by machine-independent means, has traditionally been based, on the one hand, on programs and deductive formalisms for free algebras, and on the other hand on…

The powerful generative capacity of Large Language Models (LLMs) has instigated a paradigm shift in recommendation. However, existing generative models (e.g., OneRec) operate as implicit predictors, critically lacking the capacity for…

Synthesizing 3D scenes from open-vocabulary text descriptions is a challenging, important, and recently-popular application. One of its critical subproblems is layout generation: given a set of objects, lay them out to produce a scene…

Our aim here is to illustrate how the benefits of structural corecursion can be found in a broader swath of the programming landscape than previously thought. Beginning from a tutorial on structural corecursion in the total, pure functional…

Existing retrieval-augmented code generation (RACG) methods typically use an external retrieval module to fetch semantically similar code snippets used for generating subsequent fragments. However, even for consecutive code fragments, the…

A lens is a single program that specifies two data transformations at once: one transformation converts data from source format to target format and a second transformation inverts the process. Over the past decade, researchers have…

Existing large language model (LLM)-based embeddings typically adopt an encoder-only paradigm, treating LLMs as static feature extractors and overlooking their core generative strengths. We introduce GIRCSE (Generative Iterative Refinement…

We present a generative model of images that explicitly reasons over the set of objects they show. Our model learns a structured latent representation that separates objects from each other and from the background; unlike prior works, it…

While large language models (LLMs) have demonstrated impressive performance in question-answering tasks, their performance is limited when the questions require knowledge that is not included in the model's training data and can only be…

Before implementing a function, programmers are encouraged to write a purpose statement i.e., a short, natural-language explanation of what the function computes. A purpose statement may be ambiguous i.e., it may fail to specify the…

Writing a readme is a crucial aspect of software development as it plays a vital role in managing and reusing program code. Though it is a pain point for many developers, automatically creating one remains a challenge even with the recent…