Search: “research”

Long-horizon execution in Large Language Models (LLMs) remains unstable even when high-level strategies are provided. Evaluating on controlled algorithmic puzzles, we demonstrate that while decomposit

Scientists today face challenges of extraordinary scale and complexity. From shaping and simulating the intricate dynamics of fusion plasma, to exploring the vast search space of new materials, to mak

Recent diffusion models enable high-quality video generation, but suffer from slow runtimes. The large transformer-based backbones used in these models are bottlenecked by spatiotemporal attention. In

Retrieval-augmented generation (RAG) enhances large language models (LLMs) with external knowledge but still suffers from long contexts and disjoint retrieval–generation optimization. In this work, we

Visual generative models (e.g., diffusion models) typically operate in compressed latent spaces to balance training efficiency and sample quality. In parallel, there has been growing interest in lever

SensorFM is a foundation model that analyzes multimodal wearable sensor signals from devices like smartwatches and fitness trackers to generate insights into health and activities. The model was train

While large language models (LLMs) and coding agents are often applied to user interface (UI) development, developers find it difficult to reliably assess their proficiency in visual and interaction d

This study focuses on Text-to-Sounding-Video (T2SV) generation, which aims to generate a video with synchronized audio from text, with both modalities aligned to the text conditions. Despite progress

The web is complex, open-ended, and constantly changing, making it challenging to scale training data for visual web agents. Existing data collection attempts remain limited to offline trajectories fo

Sparse Mixture-of-Experts (MoE) architectures route each token through a subset of experts at each layer independently. We propose viewing MoE computation through the lens of expert paths—the sequence

Language models play a central role in automatic speech recognition (ASR), yet most methods rely on text-only models unaware of ASR error patterns. Recently, large language models (LLMs) have been app

Maximum inner product search (MIPS) is a crucial subroutine in machine learning, requiring the identification of a vector taken within a database (the keys) that best aligns with a given query. We pro

The problem of domain generalization concerns learning predictive models that are robust to distribution shifts when deployed in new, previously unseen environments. Existing methods typically require

Large language models can exhibit emergent reasoning behaviors, often manifested as recurring lexical patterns (e.g., “wait,” indicating verification). However, complex reasoning trajectories remain s

Diffusion (Large) Language Models (dLLMs) now match the downstream performance of their autoregressive counterparts on many tasks, while holding the promise of being more efficient during inference. O

Understanding how transformer components operate in LLMs is important, as it is at the core of recent technological advances in artificial intelligence. In this work, we revisit the challenges associa

Reinforcement learning (RL) finetuning has become a key technique for enhancing large language models (LLMs) on reasoning-intensive tasks, motivating its extension to vision language models (VLMs). Wh

Diffusion Large Language Models (dLLMs) have emerged as a promising alternative to purely autoregressive language models because they can decode multiple tokens in parallel. However, state-of-the-art

TabFM is a foundation model designed for tabular data classification and regression that eliminates the need for manual model training, hyperparameter tuning, and complex feature engineering by framin

IBM announced the development of sub-1 nanometer computer chips, representing a significant advancement in semiconductor miniaturization beyond previous technological limits. This breakthrough in chip

Linear Elastic Caching addresses the problem of minimizing total cache cost by accounting for both cache misses and memory footprint over time. The approach connects this problem to ski rental algorit

When annotators disagree on a label, the disagreement itself carries signal—and the number of annotators needed to capture it depends on the evaluation metric. We fine-tune NLI models on label distrib

SQL Data Insights Pro is an IBM tool that applies semantic AI capabilities to IBM DB2 databases, enhancing data analysis and insights generation. The solution leverages advanced AI techniques to help

Qiskit Fall Fest 2026 is an event organized by IBM that focuses on quantum computing education and community engagement through the open-source Qiskit framework. The event likely provides opportunitie

Qiskit Global Summer School 2026 is an educational program offered by IBM that focuses on quantum computing and the Qiskit framework, with registration now available for interested participants. The s

Streaming vision-language models (VLMs) continuously generate responses given an instruction prompt and an online stream of input frames. This is a core mechanism for real-time visual assistants. Exis

We introduce a framework for learning latent representations of 4D objects which are descriptive, faithfully capturing object geometry and appearance; compressive, aiding in downstream efficiency; and

This article provides firsthand observations and insights into the operations, research directions, and technical capabilities of artificial intelligence laboratories within China. It likely covers de

One of the major differentiators unlocked by learned codecs relative to their hard-coded traditional counterparts is their ability to be optimized directly to appeal to the human visual system. Despit

Mixture-of-Experts (MoE) models enable sparse expert activation, meaning that only a subset of the model’s parameters is used during each inference. However, to translate this sparsity into practical

Sample-based quantum diagonalization is a quantum algorithm technique that estimates the eigenvalues and eigenvectors of matrices using measurements from quantum hardware, rather than requiring full q

AI-driven sign language interpretation is limited by a lack of high-quality annotated data. New datasets including ASL STEM Wiki and FLEURS-ASL contain professional interpreters and 100s of hours of d

Normalizing flows (NFs) are end-to-end likelihood-based generative models for continuous data, and have recently regained attention with encouraging progress on image generation. Yet in the video gene

Recent advances in large language models (LLMs) test-time computing have introduced the capability to perform intermediate chain-of-thought (CoT) reasoning (thinking) before generating answers. While

Large Language Models (LLMs) demonstrate their reasoning ability through chain-of-thought (CoT) generation. However, LLM’s autoregressive decoding may limit the ability to revisit and refine earlier t

We present StereoFoley, a video-to-audio generation framework that produces semantically aligned, temporally synchronized, and spatially accurate stereo sound at 48 kHz. While recent generative video-

Understanding and predicting motion is a fundamental component of visual intelligence. Although modern video models exhibit strong comprehension of scene dynamics, exploring multiple possible futures

The theme of NTT Research Inc.‘s annual user event, Upgrade, in San Jose this week was “Research to Reality,” a reflection of NTT’s desire to balance the academic nature of research with the practical

This paper was accepted at the Workshop on Navigating and Addressing Data Problems for Foundation Models (NADPFM) at ICLR 2026. Principled domain reweighting can substantially improve sample efficienc

This paper provides a theoretical framework for interpreting acoustic neighbor embeddings, which are representations of the phonetic content of variable-width audio or text in a fixed-dimensional embe

ConvApparel is a human-AI conversation dataset and comprehensive evaluation framework designed to quantify the 'realism gap' in LLM-based user simulators and improve the training of robust conversa...

IBM Research has presented a new approach that scales AI‑driven chip design by employing open “agent factories,” lowering inference cost by 11.5 × compared to fully proprietary setups. The method enab

On Friday I gave the closing keynote at the WeAreDevelopers World Congress North America in San Jose. I tied together the key trends from the past year into a chronological exploration of everything t

The agentic AI era is here, transforming how higher education institutions innovate, operate, and fundamentally empower learners, faculty, and researchers. AI agents can deliver unprecedented efficien

Researchers say they’ve found a new way to extract lithium, a crucial metal used in the lithium-ion batteries that power electric vehicles and energy storage arrays. This new technique could be more e

IBM has introduced new classroom accounts that provide educators with expanded access to quantum computing resources for teaching and research purposes. These accounts are designed to make quantum tec