Knowledge catalogue
arXiv:2606.03189v1 Announce Type: new Abstract: Large Language Models (LLMs) as judges across various scenarios such as assessing model responses is becoming an increasingly accepted paradigm. However
arXiv:2606.01850v1 Announce Type: new Abstract: Model compression techniques such as quantization and pruning are widely used to reduce the deployment cost of large language models (LLMs), with existi
arXiv:2606.00616v1 Announce Type: cross Abstract: Recent Vision-Language Models (VLMs) struggle with grounded reasoning, temporal consistency, and context aware planning in videos. We introduce pause-
arXiv:2606.02278v1 Announce Type: cross Abstract: State-space models are traditionally based on physical knowledge, but multi-step predictions from these physical models can be poor due to model inacc
arXiv:2606.00148v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) often know the rule but pick the wrong answer: on abstract visual reasoning (AVR) tasks, a model can describe
This is actually one of the main advantages startups have over frontier labs, as long as there's a healthy spectrum of open-weight to closed-weight models on the cost-performance curve. Building a mod
arXiv:2606.02487v1 Announce Type: new Abstract: Effective 'all-team' summarization in high-complexity settings like the Neonatal Intensive Care Unit (NICU) requires aggregating insights from diverse d
arXiv:2512.20732v2 Announce Type: replace-cross Abstract: As LLMs advance their reasoning capabilities about the physical world, the absence of rigorous benchmarks for evaluating their ability to gene
arXiv:2605.31268v1 Announce Type: new Abstract: We present Mellum 2, an open-weight 12B-parameter Mixture-of-Experts (MoE) language model with 2.5B active parameters per token. Mellum 2 is a general-p
Very good advice on self-improving agents. (bookmark it) This is something I am seeing in my own experiments with coding agents and harnesses for long-horizon tasks. What I have found is that stronger
arXiv:2605.29976v1 Announce Type: cross Abstract: We evaluate the climate simulation capabilities of ArchesWeather and ArchesWeatherGen, two machine learning models originally trained for weather fore
arXiv:2605.29001v1 Announce Type: cross Abstract: A paraphrase-quality audit of MathCheck (ICLR 2025) detected 4 semantically incorrect paraphrases in 129 groups (3.1%); removing them drops GPT-4o fro
arXiv:2505.21627v4 Announce Type: replace-cross Abstract: State-of-the-art large language models require specialized hardware and substantial energy to operate. As a consequence, cloud-based services
arXiv:2605.29659v1 Announce Type: cross Abstract: Real-time safety filtering for large language model (LLM) applications requires classifiers that can detect unsafe prompts, toxic language, jailbreak
arXiv:2605.29192v1 Announce Type: new Abstract: Chain-of-thought traces from large reasoning models can span tens of thousands of tokens, yet we lack a vocabulary for describing their internal structu
arXiv:2403.09441v2 Announce Type: replace Abstract: As deep learning (DL) models are increasingly being integrated into our everyday lives, ensuring their safety by making them robust against adversar
arXiv:2605.27923v1 Announce Type: cross Abstract: The rapid growth of computer vision and increasingly complex image recognition tasks has exposed fundamental computational limitations of classical ma
arXiv:2605.27605v1 Announce Type: new Abstract: We present Laguna M.1 and Laguna XS.2, two Mixture-of-Experts foundation models built for long-horizon, agentic coding: M.1 has 225.8B total parameters
arXiv:2605.27901v1 Announce Type: cross Abstract: Chain-of-thought (CoT) monitoring has been proposed as a promising safety mechanism for detecting misaligned behavior in large language models. Howeve
arXiv:2605.28190v1 Announce Type: new Abstract: Embedding benchmarks like MTEB report a single score per model, implicitly treating robustness as a static, scalar property. We argue that embedding rob
arXiv:2510.01336v2 Announce Type: replace-cross Abstract: Speculative decoding accelerates LLM inference by using a smaller draft model to speculate tokens that a larger target model verifies. Verific
arXiv:2605.25166v1 Announce Type: cross Abstract: Time series forecasting models are increasingly scaled through large Transformer backbones, yet most existing approaches process all series through a
arXiv:2605.25246v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used for optimization modeling and solver-code generation, yet practical operations research and optimizat
arXiv:2605.24741v1 Announce Type: cross Abstract: We study the sample complexity of robust binary hypothesis testing under three standard contamination models: arepsilon-additive (Huber), arepsilon-su
arXiv:2605.25902v1 Announce Type: new Abstract: Narrowly finetuned language models memorize implanted content verbatim, but auditing what a deployed model has been taught, without access to its weight
arXiv:2605.24703v1 Announce Type: cross Abstract: Large language models (LLMs) and time-series language models (TSLMs) are increasingly applied to time-series question answering (TSQA). Unlike text-on
arXiv:2605.23281v1 Announce Type: new Abstract: Monocular metric depth estimation has achieved strong progress with large-scale training and universal-camera modeling, yet robust deployment across div
arXiv:2509.24517v2 Announce Type: replace Abstract: Development of modern deep learning methods has been driven primarily by the push for improving model efficacy (accuracy metrics). This sole focus o
arXiv:2605.21856v1 Announce Type: new Abstract: Large language models (LLMs) have demonstrated impressive reasoning abilities across a wide range of tasks, but data contamination undermines the object
arXiv:2512.14896v2 Announce Type: replace Abstract: In our study, we evaluated large language model (LLM) performance on pharmacy licensure-style question-answering tasks and developed an external kno
arXiv:2502.12120v3 Announce Type: replace-cross Abstract: Scaling laws guide the development of large language models (LLMs) by offering estimates for the optimal balance of model size, tokens, and co
arXiv:2605.21090v1 Announce Type: new Abstract: Recent advances in Multimodal Large Language Models (MLLMs) and diffusion-based generative models have substantially improved prompt-driven image editin
arXiv:2605.19645v1 Announce Type: new Abstract: Recent advancements in large language models (LLMs) have shown their remarkable capacities in many NLP tasks. However, their substantial size often pres
arXiv:2605.19568v1 Announce Type: new Abstract: Embedding models are pivotal in industrial information retrieval systems like search and advertising. However, existing pretrained models often exhibit
arXiv:2605.18956v1 Announce Type: new Abstract: Recent motion-language models unify tasks like comprehension and generation but operate at a coarse granularity, lacking fine-grained understanding and
arXiv:2605.16795v1 Announce Type: cross Abstract: Video generative models have made remarkable progress, yet they often yield visual artifacts that violate grounding in physical dynamics. Recent works
arXiv:2605.16882v1 Announce Type: new Abstract: Low-resource deployment constraints have made model quantization essential for deploying neural networks while preserving performance. Meanwhile, model
Google’s new Gemini 3.5 Flash is the clear leader on the Intelligence vs Speed Pareto frontier and makes large gains on GDPval-AA (real-world agentic tasks), but is 5x the cost of Gemini 3 Flash @Goog
arXiv:2605.17106v1 Announce Type: new Abstract: Production LLM deployments increasingly maintain heterogeneous model pools spanning order-of-magnitude cost differences. Existing routers make binary st
arXiv:2605.17949v1 Announce Type: new Abstract: Remote sensing vision-language models commonly rely on pretrained visual encoders to convert images into semantic features before language-model reasoni
arXiv:2601.12696v2 Announce Type: replace Abstract: Current guardian models are predominantly Western-centric and optimized for high-resource languages, leaving low-resource African languages vulnerab
arXiv:2605.15708v1 Announce Type: new Abstract: Recent advances in 3D datasets and multimodal models have greatly improved natural language 3D scene understanding. However, most 3D referring segmentat
arXiv:2602.14896v2 Announce Type: replace Abstract: Large-scale deep learning models are well-suited for compression. Across a variety of tasks, methods like pruning, quantization, and knowledge disti
arXiv:2605.14885v1 Announce Type: new Abstract: Scene Text Recognition requires modeling visual structures that evolve from coarse layouts to fine-grained character strokes. Training such models relie
arXiv:2605.06132v2 Announce Type: replace Abstract: In agent memory systems, the reranking model serves as the critical bridge connecting user queries with long-term memory. Most systems adopt the 're
arXiv:2605.14055v1 Announce Type: cross Abstract: Parameter-Efficient Fine-Tuning (PEFT) is widely used for adapting Large Language Models (LLMs) for various tasks. Recently, there has been an increas
arXiv:2605.14152v1 Announce Type: cross Abstract: Safety evaluations for large language models (LLMs) increasingly target high-stakes National Security and Public Safety (NSPS) risks, yet multilingual
arXiv:2605.14457v1 Announce Type: new Abstract: Chain-of-Thought (CoT) reasoning has become a foundation for eliciting multi-step reasoning in large language models, but recent studies show that its b
arXiv:2605.13986v1 Announce Type: new Abstract: Tabular data underpins most high-value prediction problems in science and industry, and TabPFN has driven the foundation model revolution for this modal
A lot of people have been wondering about Mythos, Glasswing, and the vulns we / our partners are fixing. Today, I’m excited for us to start sharing more. (For context, I lead Glasswing @AnthropicAI.)
arXiv:2605.11857v1 Announce Type: new Abstract: Federated fine-tuning of large language models is commonly formulated as a parameter aggregation problem. However, even parameter-efficient methods requ
arXiv:2605.10528v1 Announce Type: cross Abstract: We investigate the emergent collective dynamics of LLM-based multi-agent systems on a 2D square lattice and present a model-agnostic statistical-physi
arXiv:2605.08665v1 Announce Type: new Abstract: Large reasoning models achieve high accuracy through extended chain-of-thought but generate 5--8 more tokens than necessary, applying verbose reasoning
arXiv:2605.09384v1 Announce Type: cross Abstract: The reasoning gap between large and compact vision-language models (VLMs) limits the deployment of medical AI on portable clinical devices. Compact VL
arXiv:2605.10777v1 Announce Type: new Abstract: The quality of open-weight language models has dramatically improved in recent years. Sharing weights greatly facilitates model adoption by enabling the
arXiv:2605.08904v1 Announce Type: new Abstract: Large Language Models (LLMs) have demonstrated remarkable capabilities in reasoning and tool use. However, the fundamental cognitive faculties essential
arXiv:2605.06241v2 Announce Type: replace Abstract: Reinforcement learning has become the standard for improving reasoning in large language models, yet evidence increasingly suggests that RL does not
arXiv:2605.08151v1 Announce Type: cross Abstract: LLM serving platforms are increasingly deployed as multi-model cloud systems, where user demand is often long-tailed: a few popular large models recei
arXiv:2605.08412v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have made rapid progress in single-video understanding, yet their ability to reason across multiple independent
arXiv:2605.09329v1 Announce Type: new Abstract: Speculative decoding accelerates LLM inference by using a fast draft model to generate tokens and a more accurate target model to verify them. Its perfo