Search: “model-releases”

arXiv:2407.13193v4 Announce Type: replace Abstract: Large language models (LLMs) have achieved strong empirical performance in various fields, benefiting from their huge amount of parameters that stor

arXiv:2510.14261v2 Announce Type: replace Abstract: We present an experimental recipe for studying the relationship between training data and language model (LM) behavior. We outline steps for interve

arXiv:2605.19328v1 Announce Type: cross Abstract: Recent advances in Vision-Language Models (VLMs) facilitate a new class of embodied AI systems, where these models are integrated into physical platfo

arXiv:2604.07303v2 Announce Type: replace Abstract: Understanding and modeling animal behavior is essential for studying collective motion, decision-making, and bio-inspired robotics. Yet, evaluating

arXiv:2605.18794v1 Announce Type: cross Abstract: Decoupling is a powerful modeling paradigm for representing multivariate functions as compositions of linear transformations and univariate nonlinear

arXiv:2605.19014v1 Announce Type: new Abstract: Microsimulation models used by ministries of finance and central banks rely on parametric processes for lifetime earnings that capture only first and se

arXiv:2605.19095v1 Announce Type: cross Abstract: Schedule-Free Learning has shown promise as a practical anytime training method for machine learning, showing success across dozens of standard benchm

arXiv:2605.19357v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly applied to scientific research, yet existing evaluations often fail to reflect the fine-grained capabiliti

arXiv:2510.18821v3 Announce Type: replace Abstract: Reinforcement learning with verifiable rewards (RLVR) has become the mainstream technique for training LLM agents. However, RLVR highly depends on w

arXiv:2510.05431v4 Announce Type: replace Abstract: Organizing large-scale patent corpora according to classification schemes is a core information management task that determines the accuracy and eff

Self-improving AI is a big deal! As a first step, I've been exploring how much of the post-training can be automated. Here is a first post on how I am using @FireworksAI_HQ Agent to automate LLM fine-

arXiv:2605.19342v1 Announce Type: new Abstract: Multimodal latent-space reasoning aims to replace explicit thinking with images by performing visual reasoning directly in a compact latent space. Howev

arXiv:2605.19193v1 Announce Type: new Abstract: Multi-agent LLM debate improves factuality and reasoning, but most recipes pick a fixed round count, over-spending on easy items and under-spending on h

arXiv:2408.12385v3 Announce Type: replace-cross Abstract: We study the problem of approximately recovering a probability distribution given noisy measurements of its Chebyshev polynomial moments. This

arXiv:2605.18797v1 Announce Type: cross Abstract: Scaling model performance typically requires increasing model size. Looped Transformer offers a compelling alternative by iteratively reusing the same

arXiv:2507.18902v2 Announce Type: replace Abstract: There are more than 7,000 languages around the world, and current Large Language Models (LLMs) only support hundreds of languages. Dictionary-based

arXiv:2605.19823v1 Announce Type: cross Abstract: Neural operators have achieved strong performance in learning solution operators of partial differential equations (PDEs), but their inherently contin

arXiv:2602.17001v2 Announce Type: replace Abstract: Natural Language Querying for Time Series Databases (NLQ4TSDB) aims to assist non-expert users retrieve meaningful events, intervals, and summaries

arXiv:2605.18791v1 Announce Type: cross Abstract: Existing spectral benchmarks are limited in scale, modality alignment, and evaluation scope, and typically focus on either specialized models or multi

arXiv:2605.19338v1 Announce Type: cross Abstract: Frontier AI models and multi-agent systems have led to significant improvements in mathematical reasoning. However, for problems requiring extended, l

arXiv:2605.18765v1 Announce Type: cross Abstract: To augment Large Language Models (LLMs) for multi-hop question answering, a mainstream solution within Graph Retrieval Augmented Generation (GraphRAG)

arXiv:2602.18718v2 Announce Type: replace-cross Abstract: For approximating a target distribution given only its unnormalized log-density, stochastic gradient-based variational inference (VI) algorith

arXiv:2605.19895v1 Announce Type: new Abstract: Constraint programming practitioners accelerate hard problems through a layered set of techniques applied in order of risk. Standard hardening (symmetry

arXiv:2605.19866v1 Announce Type: new Abstract: Vision-Language Models (VLMs) parse documents end-to-end but frequently break down on layouts unlike those seen in training. We attribute this to a two-

Subagents running locally and simultaneously on MacBook Pro M5 with Codex CLI + @lmstudio to review code and find bugs using Qwen 3.6 Powered by the updated MLX engine with batching in beta in the app

arXiv:2605.18920v1 Announce Type: cross Abstract: Generative Recommendation (GR) has emerged as a promising paradigm by formulating item recommendation as a sequence-to-sequence generation task over i

arXiv:2605.19766v1 Announce Type: cross Abstract: An effective healthcare agent must be able to recall and reason over a patient's longitudinal medical history. However, the absence of datasets with r

arXiv:2603.12296v2 Announce Type: replace-cross Abstract: Deep learning has achieved transformative performance across diverse domains, largely driven by large-scale and high-quality training data. In

arXiv:2602.11910v2 Announce Type: replace-cross Abstract: Audio diffusion models can synthesize high-fidelity music from text, yet achieving fine-grained control over specific musical attributes remai

arXiv:2605.20068v1 Announce Type: cross Abstract: Standard generative models struggle with heavy-tailed data: Lipschitz architectures cannot produce power-law tails from Gaussian noise, and interpolat

arXiv:2605.19358v1 Announce Type: new Abstract: Entropy-based deep reasoning has emerged as a promising direction for improving the reasoning capabilities of Large Language Models (LLMs), but existing

arXiv:2603.29501v2 Announce Type: replace-cross Abstract: Many value-based deep reinforcement learning algorithms rely on target networks - lagged copies of the online network - to stabilize training.

arXiv:2605.19446v1 Announce Type: cross Abstract: Recently, pre-trained encoders have gained widespread use due to their strong capability in representation extraction. However, they are vulnerable to

arXiv:2605.19320v1 Announce Type: new Abstract: Faithful text rendering remains a persistent weakness of large text-to-image generative models, as it requires both semantic instruction following and f

arXiv:2605.19066v1 Announce Type: new Abstract: Over the past decade, low-resource natural language processing (NLP) has experienced explosive growth, propelled by cross-lingual transfer, massively mu

arXiv:2605.19377v1 Announce Type: cross Abstract: As jailbreaks, adversarially crafted inputs that bypass safety constraints, continue to be discovered in Large Language Models, practitioners increasi

The frontier is still jagged though (here is Gemini 3.5 Flash messing up counting letters in words) https://x.com/RRiscio37389/status/2057193260745883962?s=20 @emollick Proof: https://gemini.google.co

The future of biology shouldn’t stay behind black-box APIs. Especially when it touches personal health. Whether you’re @bryan_johnson measuring every biomarker, or @sytses openly sharing and analyzing

arXiv:2605.18840v1 Announce Type: cross Abstract: Leaderboards rank frontier models on independent axes but do not reveal whether capabilities reinforce or trade off across releases -- and at the fron

The proof came from a general-purpose reasoning model, not a system built specifically to solve math problems or this problem in particular, and represents an important milestone for the math and AI c

arXiv:2605.19537v1 Announce Type: new Abstract: Progress in LLMs is increasingly measured through standardized benchmarks, where state-of-the-art improvements are often separated by fractions of a per

arXiv:2603.05910v2 Announce Type: replace Abstract: LLM-powered tool-calling agents fulfill user requests by interacting with environments, querying data, and invoking tools in a multi-turn process. Y

arXiv:2605.18800v1 Announce Type: cross Abstract: Post-training quantization has emerged as a widely adopted technique for compressing and accelerating the inference of Large Language Models (LLMs). T

This result points to something larger: AI systems are becoming capable of holding together long, difficult chains of reasoning, connecting ideas across distant fields, and surfacing paths researchers

arXiv:2605.20150v1 Announce Type: new Abstract: Training 3D Gaussian Splatting (3DGS) at billion-primitive scale is fundamentally memory-bound: each Gaussian primitive carries a large attribute vector

arXiv:2503.17581v2 Announce Type: replace-cross Abstract: A computational method for the synthesis of time-optimal feedback control laws for linear nilpotent systems is proposed. The method is based o