Knowledge catalogue
arXiv:2605.25344v1 Announce Type: cross Abstract: Large language models (LLMs) are dominated by dense linear transformations, whose storage, memory and computational overheads hinder efficient adaptat
arXiv:2605.24383v1 Announce Type: new Abstract: Ethical constraints on open-weight AI models are both a reflection of societal concerns and a foundation for AI governance policy. They are expected to
arXiv:2605.25901v1 Announce Type: cross Abstract: 3D Visual Grounding (3DVG) is an essential capability for embodied AI, requiring agents to localize objects in 3D scenes based on natural language des
arXiv:2605.24381v1 Announce Type: cross Abstract: Time series forecasting drives operational decisions in areas like finance, transportation, and energy. While supervised learning approaches achieve s
arXiv:2605.24652v1 Announce Type: new Abstract: Rapid advances in audio-video (AV) generation have enabled high-fidelity synthesis with synchronized sound, particularly for human-related scenarios inv
arXiv:2605.24517v1 Announce Type: cross Abstract: CLI agents are the closest thing language models have to an embodied setting: the model emits commands, the terminal executes them, and the returned s
arXiv:2605.24192v1 Announce Type: cross Abstract: The neural-network denoising functions which form the backbone of image diffusion models are remarkably consistent in their generalization behaviour a
arXiv:2506.09199v2 Announce Type: replace-cross Abstract: Integrating Low-Rank Adaptation (LoRA) into federated learning offers a promising solution for parameter-efficient fine-tuning of Large Langua
arXiv:2605.26097v1 Announce Type: new Abstract: Models trained on a new task typically degrade on prior tasks, a phenomenon known as forgetting. Traditionally, mitigating forgetting has required repla
I think folk are underestimating how much of AI models are actually engineering at scale versus breakthrough research. See how @cursor_ai caught up to Anthropic / OpenAI models run at a fraction of th
arXiv:2605.25123v1 Announce Type: cross Abstract: We study inference-time alignment for diffusion-based generative models, aiming to steer a base model toward high-reward outputs without updating its
arXiv:2510.01389v2 Announce Type: replace-cross Abstract: Recent Vision-Language-Action (VLA) models show strong generalization capabilities, yet they lack introspective mechanisms for anticipating fa
arXiv:2603.29123v2 Announce Type: replace Abstract: The next-token prediction (NTP) objective trains language models to predict a single token at each step, even though many continuations can express
arXiv:2507.03159v2 Announce Type: replace Abstract: We present exttt{MathOptAI.jl}, an open-source Julia library for embedding trained machine learning predictors into a JuMP model. exttt{MathOptAI.jl
arXiv:2510.05699v4 Announce Type: replace-cross Abstract: Membership inference attacks (MIAs) are widely used to assess the privacy risks associated with machine learning models. However, when these a
arXiv:2605.24562v1 Announce Type: cross Abstract: Pedestrian intention and trajectory prediction are critical for the safe deployment of autonomous driving systems, directly influencing navigation dec
arXiv:2605.24004v1 Announce Type: new Abstract: Large language models (LLMs) are promising for autonomous driving, but semantics-only decision policies can yield physically unsafe behavior in dynamic
arXiv:2605.25525v1 Announce Type: new Abstract: Continual learning enables large language models to adapt to evolving tasks without retraining from scratch, yet catastrophic forgetting remains a centr
arXiv:2603.06687v2 Announce Type: replace-cross Abstract: Geo-temporal understanding, the ability to infer location, time, and contextual properties from visual input alone, underpins applications suc
arXiv:2605.24977v1 Announce Type: cross Abstract: Medical vision-language models (VLMs) often hallucinate findings when generating chest X-ray reports: they fabricate findings that are not present in
arXiv:2605.26081v1 Announce Type: new Abstract: Deep research agents face vast, interdependent, and pervasively uncertain information. Existing systems explore what evolving intermediate representatio
arXiv:2602.17653v2 Announce Type: replace Abstract: Recent work has shown that language models (LMs) trained on synthetic corpora can exhibit typological preferences that resemble cross-linguistic reg
arXiv:2605.23065v1 Announce Type: cross Abstract: Vision foundation models are widely used as frozen backbones across many downstream tasks, making them a single point of failure under adversarial att
arXiv:2605.22882v1 Announce Type: new Abstract: Video world models can generate realistic futures from a single instruction, but they often fail to preserve consistent point-level motion over time. As
arXiv:2605.23651v1 Announce Type: new Abstract: While factual correctness and task-performance have been in focus of Large Language Model (LLM) research for a long time, the fundamental question of ho
arXiv:2605.22939v1 Announce Type: new Abstract: We aim to improve the reasoning capabilities of diffusion language models (DLMs). While SFT is a popular post-training recipe for autoregressive models,
arXiv:2605.23158v1 Announce Type: cross Abstract: The deployment of large language models (LLMs) on resource-constrained devices remains challenging, spurring interest in split inference, where models
arXiv:2601.21025v3 Announce Type: replace-cross Abstract: Score-based generative models have recently achieved remarkable success. While they are usually parameterized by the score, an alternative way
arXiv:2511.18159v2 Announce Type: replace Abstract: Masked diffusion models (MDMs) are a promising alternative to autoregressive models (ARMs), but they suffer from inherently much higher training var
arXiv:2510.00319v2 Announce Type: replace Abstract: Large Language Models (LLMs) have been demonstrating strong reasoning capability with their chain-of-thoughts (CoT), which are routinely used by hum
arXiv:2603.16077v3 Announce Type: replace Abstract: Masked diffusion models (MDM) exhibit superior generalization when learned using a Partial masking scheme (Prime). This approach converts tokens int
arXiv:2601.11079v2 Announce Type: replace Abstract: This paper proposes the soft Bayesian context tree model (Soft-BCT), which is a novel BCT model for real-valued time series. The Soft-BCT considers
arXiv:2505.16416v3 Announce Type: replace Abstract: Rotary Position Embedding (RoPE) is widely adopted in large language models, but when applied to vision-language models (VLMs) it couples text and i
arXiv:2410.12771v2 Announce Type: replace-cross Abstract: The ability to discover new materials with desirable properties is critical for numerous applications from helping mitigate climate change to
arXiv:2605.21427v1 Announce Type: new Abstract: Large language model (LLM) inference has become a dominant workload in modern data centers, driving significant GPU utilization and energy consumption.
arXiv:2605.21919v1 Announce Type: new Abstract: Assessing progress toward the Sustainable Development Goals (SDGs) requires multi-step reasoning over visual cues, contextual knowledge, and development
Today, Zyphra Research is sharing fundamental work extending Equilibrium Propagation beyond Energy-Based Models to biologically realistic neuron models. A step toward more efficient AI, local learning
arXiv:2605.06597v2 Announce Type: replace Abstract: Self-distillation (SD) offers a promising path for adapting large language models (LLMs) without relying on stronger external teachers. However, SD
arXiv:2603.14184v2 Announce Type: replace Abstract: Multimodal large language models (MLLMs) often suffer from perceptual impairments under extended reasoning modes, particularly in visual question an
arXiv:2502.17518v2 Announce Type: replace Abstract: This paper presents a comprehensive study on the use of ensemble Reinforcement Learning (RL) models in financial trading strategies, leveraging clas
arXiv:2510.05942v3 Announce Type: replace Abstract: We present EvalMORAAL, a transparent chain-of-thought (CoT) framework that uses two scoring methods (log-probabilities and direct ratings) plus a mo
arXiv:2602.16608v2 Announce Type: replace Abstract: Transformer models achieve state-of-the-art performance across domains and tasks, yet their deeply layered representations make their predictions di
arXiv:2605.20197v1 Announce Type: new Abstract: Medical concept extraction from electronic health records underpins many downstream applications, yet remains challenging because medically meaningful c
arXiv:2605.20416v1 Announce Type: new Abstract: We study whether multimodal large language models (MLLMs) can leverage crystallographic plane indices (Miller indices) as a structured latent representa
arXiv:2605.20187v1 Announce Type: new Abstract: Understanding dependencies between variables is critical for interpretability and efficient generation in masked diffusion models (MDMs), yet these mode
arXiv:2605.20813v1 Announce Type: new Abstract: Inference in diffusion large language models (dLLMs) is computationally expensive, as full self-attention must be repeatedly executed at each step of th
arXiv:2605.21072v1 Announce Type: new Abstract: Autoregressive video diffusion models (ARVDs) have emerged as a promising architecture for streaming video generation, paving the way for real-time inte
arXiv:2605.20914v1 Announce Type: new Abstract: Vision-language models (VLMs) have achieved strong multimodal reasoning capabilities, but further improving them still relies heavily on large-scale hum
arXiv:2605.20356v1 Announce Type: new Abstract: Full-duplex spoken dialogue models (SDMs) can listen and speak simultaneously, enabling interaction dynamics closer to human conversation than turn-base
arXiv:2605.20202v1 Announce Type: new Abstract: I study whether emotionally framed evaluation follow-ups change both the behavior and the calm-relative internal representations of small, locally deplo
arXiv:2605.19711v1 Announce Type: new Abstract: Automatic speech recognition (ASR) has improved substantially in recent years, yet performance remains limited for low-resource languages. Large languag
arXiv:2507.15698v2 Announce Type: replace-cross Abstract: Process Reward Models (PRMs) play a central role in evaluating and guiding multi-step reasoning in large language models (LLMs), especially fo
arXiv:2605.18813v1 Announce Type: cross Abstract: World models aim to predict plausible futures consistent with past observations, a capability central to planning and decision-making in reinforcement
arXiv:2605.19224v1 Announce Type: new Abstract: Neuroscientists have recently turned to intracranial brain recording methods, like electrocorticography (ECoG), for human experiments because of the fin
arXiv:2510.00600v2 Announce Type: replace-cross Abstract: Using Large Language Models to produce intermediate thoughts, a.k.a. Chain-of-thought (CoT), before providing an answer has been a successful
arXiv:2605.19284v1 Announce Type: new Abstract: In the training data used by large language models (LLMs), the same latent concept is often presented in multiple distinct ways: the same facts appear i
arXiv:2605.18931v1 Announce Type: cross Abstract: Heavy-tailed distributions are prevalent in performance evaluation, network traffic, and risk modeling. This behavior poses a fundamental challenge fo
arXiv:2605.19752v1 Announce Type: new Abstract: Accurately identifying metabolites i.e. small molecules from mass spectrometry data remains a core challenge in metabolomics, with broad applications in
arXiv:2605.19207v1 Announce Type: cross Abstract: Deep learning models have shown strong performance in medical image analysis, but deploying them in low-resource clinical environments remains difficu
arXiv:2503.19877v2 Announce Type: replace Abstract: As language model (LM) outputs get more and more natural, it is becoming more difficult than ever to evaluate their quality. Simultaneously, increas