Latest

Audio-Visual Question Answering (AVQA) is a challenging multimodal reasoning task requiring intelligent systems to answer natural language queries based on paired audio-video inputs accurately. However, existing AVQA approaches often suffer from overfitting to dataset biases, leading to poor...

Pre-training large language models (LLMs) necessitates enormous diverse textual corpora, making effective data selection a key challenge for balancing computational resources and model performance. Current methodologies primarily emphasize data quality metrics and mixing proportions, yet they fail to...

Computer use agents automate digital tasks by directly interacting with graphical user interfaces (GUIs) on computers and mobile devices, offering significant potential to enhance human productivity by completing an open-ended space of user queries. However, current agents face significant...

Test-time scaling has emerged as a powerful technique for enhancing the reasoning capabilities of large language models. However, its effectiveness in medical reasoning remains uncertain, as the medical domain fundamentally differs from mathematical tasks in terms of knowledge representation and...

As language models improve and become capable of performing more complex tasks across modalities, evaluating them automatically becomes increasingly challenging. Developing strong and robust task-specific automatic metrics gets harder, and human-annotated test sets -- which are expensive to create --...

Academic writing requires both coherent text generation and precise citation of relevant literature. Although recent Retrieval-Augmented Generation (RAG) systems have significantly improved factual accuracy in general-purpose text generation, their capacity to adequately support professional academic...

This study focuses on Embodied Complex-Question Answering task, which means the embodied robot need to understand human questions with intricate structures and abstract semantics. The core of this task lies in making appropriate plans based on the perception of the visual environment. Existing...

Large Language Models (LLMs) have been increasingly used to optimize the analysis and synthesis of legal documents, enabling the automation of tasks such as summarization, classification, and retrieval of legal information. This study aims to conduct a systematic literature review to identify the...

Recent advances in Multi-modal Large Language Models (MLLMs) have shown significant progress in open-world Visual Question Answering (VQA). However, integrating visual information increases the number of processed tokens, leading to higher GPU memory usage and computational overhead. Images often...

Large Language Models (LLMs) have provided a new pathway for Named Entity Recognition (NER) tasks. Compared with fine-tuning, LLM-powered prompting methods avoid the need for training, conserve substantial computational resources, and rely on minimal annotated data. Previous studies have achieved...

Embodied agents operating in real-world environments must interpret ambiguous and under-specified human instructions. A capable household robot should recognize ambiguity and ask relevant clarification questions to infer the user intent accurately, leading to more effective task execution. To study...

We introduce a novel large language model (LLM)-driven agent framework, which iteratively refines queries and filters contextual evidence by leveraging dynamically evolving knowledge. A defining feature of the system is its decoupling of external sources from an internal knowledge cache that is...

In this paper, we propose Text-based Open Molecule Generation Benchmark (TOMG-Bench), the first benchmark to evaluate the open-domain molecule generation capability of LLMs. TOMG-Bench encompasses a dataset of three major tasks: molecule editing (MolEdit), molecule optimization (MolOpt), and...

Reasoning before action and imagining potential outcomes (i.e., world models) are essential for embodied agents operating in complex open-world environments. Yet, prior work either incorporates only one of these abilities in an end-to-end agent or integrates multiple specialized models into an agent...

Visual Self-Supervised Learning (SSL) currently underperforms Contrastive Language-Image Pretraining (CLIP) in multimodal settings such as Visual Question Answering (VQA). This multimodal gap is often attributed to the semantics introduced by language supervision, even though visual SSL and CLIP...

Multimodal Large Language Models (MLLMs) suffer from high computational costs due to their massive size and the large number of visual tokens. In this paper, we investigate layer-wise redundancy in MLLMs by introducing a novel metric, Layer Contribution (LC), which quantifies the impact of a layer’s...

Composed Image Retrieval (CIR) is the task of retrieving images matching a reference image augmented with a text, where the text describes changes to the reference image in natural language. Traditionally, models designed for CIR have relied on triplet data containing a reference image, reformulation...

Hardware limitations and satellite launch costs make direct acquisition of high temporal-spatial resolution remote sensing imagery challenging. Remote sensing spatiotemporal fusion (STF) technology addresses this problem by merging high temporal but low spatial resolution imagery with high spatial...

Recent advancements in Large Language Models (LLMs) have shown that it is promising to utilize Process Reward Models (PRMs) as verifiers to enhance the performance of LLMs. However, current PRMs face three key challenges: (1) limited process supervision and generalization capabilities, (2) dependence...

This thesis employs a hybrid CNN-Transformer architecture, in conjunction with a detailed anthropological framework, to investigate potential historical connections between the visual morphology of the Indus Valley script and pictographic systems of the Tibetan-Yi Corridor. Through an ensemble...

A new survey has revealed that 51% of companies have deployed AI agents, with another 35% planning to do so within the next two years.

The Washington Post reports that members of the White House’s National Security Council have used personal Gmail accounts to conduct government business. National security advisor Michael Waltz and a senior aide of his both used their own accounts to discuss sensitive information with colleagues,...

Creatives in the UK are once again speaking out against AI developers accessing copyrighted material. The Society of Authors have published an open letter calling for UK Secretary of State Lisa Nandy to hold Meta accountable for possible copyright infringement regarding its LLM, Llama 3. Signatories...

Amazon has delivered on its promise to launch an upgraded Alexa experience, Alexa+, by the end of March. But the service reportedly lacks many of the features Amazon demoed at a press event in late February. Alexa+ can’t yet perform certain “agentic” AI tasks showcased in the company’s marketing,...

Starting Wednesday, Meta says it will begin combining the Instagram accounts of the Second Lady of the United States, Usha Vance, and the former Second Gentleman of the United States, Doug Emhoff. As a result, the 1.2 million people who were previously following the Instagram account of Kamala...

As it prepares to transition from a nonprofit corporation to a for-profit, OpenAI says it’s convening a group of experts to “help OpenAI’s philanthropy understand the most urgent and intractable problems nonprofits face today.” This group, which OpenAI says will incorporate feedback from “leaders and...

Amazon has submitted a bid to acquire all of TikTok, according to a new report from The New York Times. The last-minute bid comes as TikTok faces an April 5 deadline to shed its Chinese ownership or face a ban in the U.S. However, the parties involved in the deal talks do not appear to […]

Google DeepMind on Wednesday published an exhaustive paper on its safety approach to AGI, roughly defined as AI that can accomplish any task a human can. AGI is a bit of a controversial subject in the AI field, with naysayers suggesting that it’s little more than a pipe dream. Others, including major...

Anthropic announced on Wednesday that it’s launching a new Claude for Education tier, an answer to OpenAI’s ChatGPT Edu plan. The new tier is aimed at higher education, and gives students, faculty, and other staff access to Anthropic’s AI chatbot, Claude, with a few additional capabilities. One piece...

Amazon has reportedly joined the growing list of suitors angling to acquire TikTok as a new ban deadline approaches. According to The New York Times, the retailer has made a “last-minute bid” to buy the app, and has approached Vice President JD Vance and Commerce Secretary Howard Lutnick about the...

The VidTok method can enable AI systems to process and generate videos more effectively. Compact tokenization reduces computational costs while maintaining video quality across a potentially diverse set of applications. The post VidTok introduces compact, efficient tokenization to enhance AI video...

The past few years have witnessed the rise in popularity of generative AI and large language models (LLMs), as part of a broad AI revolution. As LLM-based...

Nicole L. Rose is a lead front-end Commerce Cloud developer and architect at Capgemini North America. Her career in Salesforce Commerce Cloud spans more than 12 years during which time she’s worked with…

Innovative AI research often depends on access to resources. Microsoft wants to help. Technical Advisor Evelyne Viegas and distinguished faculty from two Minority Serving Institutions discuss the benefits of Microsoft’s Accelerating Foundation Models Research program in their lives and research. The...

NotebookLM interface showing a "Discover sources" workflow with a search bar and a hand cursor clicking a blue "Discover sources" button. The interface suggests adding and exploring various document sources.

The 2025 Coachella music festival will once again be livestreamed exclusively on YouTube, starting Friday, April 11th at 4 PM PT/7 PM ET. The livestream will include six…

Ornate hall of the Italian Ministry of Foreign Affairs

The compute demands for large language model (LLM) inference are growing rapidly, fueled by the combination of growing model sizes, real-time latency...

A video still showing Thomas Wagner seated at a table, speaking to the camera. Behind him are plants and a large window.

A still of a white and black robot in a kitchen packing a blue lunchbox