Related papers: Mapping Semantic & Syntactic Relationships with Ge…
Human conversations contain many types of information, e.g., knowledge, common sense, and language habits. In this paper, we propose a conversational word embedding method named PR-Embedding, which utilizes the conversation pairs $…
Researchers have recently suggested that models share common representations. In our work, we find numerous geometric similarities across the token embeddings of large language models. First, we find ``global'' similarities: token…
State-of-the-art embedding models are increasingly derived from decoder-only Large Language Model (LLM) backbones adapted via contrastive learning. Given the emergence of reasoning models trained via Reinforcement Learning with Verifiable…
Evaluating automatically-generated text summaries is a challenging task. While there have been many interesting approaches, they still fall short of human evaluations. We present RISE, a new approach for evaluating summaries by leveraging…
Open-vocabulary object detection with vision-language models (VLMs) such as Grounding DINO suffers from performance degradation under test-time distribution shifts, primarily due to semantic misalignment between text embeddings and shifted…
One of the most important problems in machine translation (MT) evaluation is to evaluate the similarity between translation hypotheses with different surface forms from the reference, especially at the segment level. We propose to use word…
Words have been represented in a high-dimensional vector space that encodes their semantic similarities, enabling downstream applications such as retrieving synonyms, antonyms, and relevant contexts. However, despite recent advances in…
Humans convey their intentions through the usage of both verbal and nonverbal behaviors during face-to-face communication. Speaker intentions often vary dynamically depending on different nonverbal contexts, such as vocal patterns and…
Large Language Models (LLMs) excel in many areas but continue to face challenges with complex reasoning tasks, such as Multi-Hop Question Answering (MHQA). MHQA requires integrating evidence from diverse sources while managing intricate…
Language models demonstrate fundamental abilities in syntax, semantics, and reasoning, though their performance often depends significantly on the inputs they process. This study introduces TSIS (Simplified TSID) and its variants:TSISD…
Recent diffusion-based text-to-speech (TTS) models achieve high naturalness and expressiveness, yet often suffer from speaker drift, a subtle, gradual shift in perceived speaker identity within a single utterance. This underexplored…
Evaluating sign language generation is often done through back-translation, where generated signs are first recognized back to text and then compared to a reference using text-based metrics. However, this two-step evaluation pipeline…
Document-level relation extraction has attracted much attention in recent years. It is usually formulated as a classification problem that predicts relations for all entity pairs in the document. However, previous works indiscriminately…
What does a world model learn from physical exploration, without any linguistic supervision? We argue the answer is organized by a single principle: the geometric structure of the physical world. Training a VAE-based world model on random…
Establishing dense correspondence across 3D shapes is crucial for fundamental downstream tasks, including texture transfer, shape interpolation, and robotic manipulation. However, learning these mappings without manual supervision remains a…
Many recent works have demonstrated the benefits of knowledge graph embeddings in completing monolingual knowledge graphs. Inasmuch as related knowledge bases are built in several different languages, achieving cross-lingual knowledge…
A metric-accurate semantic 3D representation is essential for many robotic tasks. This work proposes a simple, yet powerful, way to integrate the 2D embeddings of a Vision-Language Model in a metric-accurate 3D representation at real-time.…
Many AI researchers and cognitive scientists have argued that analogy is the core of cognition. The most influential work on computational modeling of analogy-making is Structure Mapping Theory (SMT) and its implementation in the Structure…
Semantic distillation in radiance fields has spurred significant advances in open-vocabulary robot policies, e.g., in manipulation and navigation, founded on pretrained semantics from large vision models. While prior work has demonstrated…
Time series with missing data are signals encountered in important settings for machine learning. Some of the most successful prior approaches for modeling such time series are based on recurrent neural networks that transform the input and…