Knowledge catalogue
arXiv:2604.18512v1 Announce Type: new Abstract: Vision-Language Models (VLMs) have demonstrated remarkable progress in single-image understanding, yet effective reasoning across multiple images remain
arXiv:2604.16926v1 Announce Type: new Abstract: Electroencephalography (EEG) foundation models have shown strong potential for learning generalizable representations from large-scale neural data, yet
arXiv:2604.17318v1 Announce Type: new Abstract: Vision-Language Models (VLMs) are increasingly used in clinical diagnostics, yet their robustness to adversarial attacks remains largely unexplored, pos
arXiv:2604.16916v1 Announce Type: new Abstract: Safety alignment in large language models (LLMs) is primarily evaluated under open-ended generation, where models can mitigate risk by refusing to respo
arXiv:2507.13868v2 Announce Type: replace Abstract: Vision-language models (VLMs) increasingly combine visual and textual information to perform complex tasks. However, conflicts between their interna
arXiv:2604.15622v1 Announce Type: new Abstract: Language-aligned vision foundation models (VFMs) enable versatile visual understanding for always-on contextual AI, but their deployment on edge devices
arXiv:2604.15488v1 Announce Type: cross Abstract: Large language models (LLMs) often exhibit undesirable behaviors, such as safety violations and hallucinations. Although inference-time steering offer
arXiv:2604.15873v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly studied as repositories of linguistic knowledge. In this line of work, models are commonly evaluated both
arXiv:2604.15701v1 Announce Type: new Abstract: The significant computational demands of large language models have increased interest in distilling reasoning abilities into smaller models via Chain-o
arXiv:2604.16123v1 Announce Type: new Abstract: Accurate molecular property prediction is central to drug discovery, catalysis, and process design, yet real-world applications are often limited by sma
I gave two MoE models the same vibe coding challenge Qwen3.6 35B A3B (31.8GB) vs Gemma4 26B A4B (23.3GB) Stack: > Unsloth Q6_K_XL > llama.cpp > Model-card recommended sampling for each 4 prompts, side
Fireworks AI published a compilation of insights on achieving training-inference parity in Mixture of Experts (MoE) models, addressing fundamental challenges in aligning model behavior between trainin
arXiv:2604.14739v1 Announce Type: new Abstract: Large-scale renewable energy deployment introduces pronounced volatility into the electricity system, turning grid operation into a complex stochastic o
arXiv:2604.14314v1 Announce Type: cross Abstract: This manuscript introduces DharmaOCR Full and Lite, a pair of specialized small language models (SSLMs) for structured OCR that jointly optimize trans
arXiv:2503.21432v2 Announce Type: replace-cross Abstract: We propose a method to explore the flavor structure of leptons using diffusion models, which are known as one of generative artificial intelli
arXiv:2403.10559v3 Announce Type: replace Abstract: This report investigates the history and impact of Generative Models and Connected and Automated Vehicles (CAVs), two groundbreaking forces pushing
arXiv:2604.14591v1 Announce Type: new Abstract: We address the problem of prompt-guided image editing in visual autoregressive models. Given a source image and a target text prompt, we aim to modify t
arXiv:2506.03487v3 Announce Type: replace-cross Abstract: Reranking is fundamental to information retrieval and retrieval-augmented generation, with recent Large Language Models (LLMs) significantly a
arXiv:2604.14463v1 Announce Type: new Abstract: Large language models (LLMs) emulate a consistent human-like behavior that can be shaped through activation-level interventions. This paradigm is conver
arXiv:2604.15151v1 Announce Type: new Abstract: Large language models have demonstrated strong performance on general-purpose programming tasks, yet their ability to generate executable algorithmic tr
arXiv:2512.23578v3 Announce Type: replace Abstract: In this paper, we show that when spoken language models (SLMs) are instructed to speak in a specific speaking style at the beginning of a multi-turn
Google DeepMind released MedGemma, a collection of medical vision-language foundation models based on Gemma 3 in 4B and 27B parameter sizes, demonstrating advanced medical understanding and reasoning
arXiv:2604.13602v1 Announce Type: new Abstract: Reinforcement Learning from Human Feedback (RLHF) and related alignment paradigms have become central to steering large language models (LLMs) and multi
arXiv:2602.01738v2 Announce Type: replace Abstract: While specialized detectors for AI-Generated Images (AIGI) achieve near-perfect accuracy on curated benchmarks, they suffer from a dramatic performa
This guide covers how to train and fine-tune multimodal embedding and reranker models using the Sentence Transformers library, enabling systems to work with both text and image data simultaneously. It
arXiv:2603.08639v2 Announce Type: replace Abstract: Ensuring trustworthiness in open-world visual recognition requires models that are interpretable, fair, and robust to distribution shifts. Yet moder
arXiv:2506.14092v3 Announce Type: replace Abstract: Large language models (LLMs) are increasingly deployed in decision-support systems for high-stakes domains such as hiring and university admissions,
arXiv:2512.19728v2 Announce Type: replace Abstract: Large language models (LLMs) continue to struggle with mathematical reasoning, and common post-training pipelines often reduce each generated soluti
arXiv:2604.12229v1 Announce Type: new Abstract: Small language models (SLMs) often struggle with complex mathematical reasoning due to limited capacity to maintain long chains of intermediate steps an
arXiv:2604.12477v1 Announce Type: cross Abstract: Large language models (LLMs) are trained on data contributed by low-resource language communities, yet the linguistic knowledge encoded in these model
arXiv:2604.12995v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly integrated into real-world decision-making, including in the domain of public policy. Yet, their ability t
arXiv:2604.09921v1 Announce Type: new Abstract: Much work has been done on designing fast and accurate sampling for diffusion language models (dLLMs). However, these efforts have largely focused on th
arXiv:2604.09619v1 Announce Type: cross Abstract: The integration of Large Language Models (LLMs) into educational ecosystems promises to democratize access to personalized tutoring, yet the readiness
arXiv:2604.11560v1 Announce Type: cross Abstract: 1. Natural sounds have been recorded for millions of hours over the previous decades using passive acoustic monitoring. Improvements in deep learning
arXiv:2604.10825v1 Announce Type: new Abstract: We introduce CheeseBench, a benchmark that evaluates large language models (LLMs) on nine classical behavioral neuroscience paradigms (Morris water maze
arXiv:2604.10316v1 Announce Type: new Abstract: Background: Large Language Models (LLMs) are transforming artificial intelligence applications in healthcare due to their ability to understand, generat
arXiv:2604.11572v1 Announce Type: new Abstract: Vision-Language-Action models (VLAs) have demonstrated strong potential for embodied AI, yet their deployment on resource-limited robots remains challen
arXiv:2604.11299v1 Announce Type: cross Abstract: In recent years, rapid advances in Multimodal Large Language Models (MLLMs) have increasingly stimulated research on ancient Chinese scripts. As the e
arXiv:2509.04334v4 Announce Type: replace Abstract: Geographic reasoning is a fundamental cognitive capability that requires models to infer plausible locations by synthesizing visual evidence with sp
arXiv:2604.11133v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly being explored for clinical question answering and decision support, yet safe deployment critically requir
arXiv:2510.02311v2 Announce Type: replace Abstract: We study the task of predicting dynamic physical properties from videos. More specifically, we consider physical properties that require temporal in
arXiv:2501.06416v3 Announce Type: replace-cross Abstract: Designing a reinforcement learning from human feedback (RLHF) algorithm to approximate a human's unobservable reward function requires assumin
arXiv:2604.09841v1 Announce Type: cross Abstract: Vision-language models (VLMs) are increasingly adapted through domain-specific fine-tuning, yet it remains unclear whether this improves reasoning bey
arXiv:2406.13621v2 Announce Type: replace Abstract: Commonsense reasoning often requires both textual and visual knowledge, yet Large Language Models (LLMs) trained solely on text lack visual groundin
arXiv:2604.07382v2 Announce Type: replace-cross Abstract: The geometric structure of latent representations in large language models (LLMs) is an active area of research, driven in part by its implica
arXiv:2511.18373v2 Announce Type: replace Abstract: Vision Language Models (VLMs) perform well on standard video tasks but struggle with physics-related reasoning involving motion dynamics and spatial
arXiv:2604.11543v1 Announce Type: cross Abstract: Novelty is a core requirement in academic publishing and a central focus of peer review, yet the growing volume of submissions has placed increasing p
arXiv:2602.21428v2 Announce Type: replace Abstract: Medical Vision Language Models (VLMs) can change their answers when clinicians rephrase the same question, a failure mode that threatens deployment
arXiv:2604.11399v1 Announce Type: cross Abstract: Multimodal adaptation equips large language models (LLMs) with perceptual capabilities, but often weakens the reasoning ability inherited from languag
arXiv:2604.09548v1 Announce Type: cross Abstract: Older adults commonly experience chronic conditions such as pain and sleep disturbances and may consider cannabidiol for symptom management. Safe use
arXiv:2604.11711v1 Announce Type: new Abstract: Occlusion, where target structures are partially hidden by surgical instruments or overlapping tissues, remains a critical yet underexplored challenge f
arXiv:2604.03873v2 Announce Type: replace-cross Abstract: Black-box knowledge distillation for large language models presents a strict trade-off. Simple off-policy methods (e.g., sequence-level knowle
arXiv:2504.06313v5 Announce Type: replace Abstract: This paper investigates how popular text-to-image (T2I) models, DALL-E 3 and Gemini 3 Pro Preview, depict people from 206 nationalities when prompte
arXiv:2505.17682v2 Announce Type: replace-cross Abstract: Predicting user behavior is essential for intelligent assistant services, yet deep learning models often struggle to capture long-tailed behav
We've tested new OSS models the moment they're released for a while at Lindy. Inference is our #1 cost by a lot (more than payroll) — cutting it by 2-5x would be transformative. Last year, OSS models
arXiv:2604.10079v1 Announce Type: new Abstract: Supervised Fine-Tuning (SFT) is the standard approach for adapting large language models (LLMs) to downstream tasks. However, we observe a persistent fa
arXiv:2604.08964v1 Announce Type: new Abstract: Diffusion Large Language Models (dLLMs) have recently become a promising alternative to autoregressive large language models (ARMs). Semi-autoregressive
arXiv:2602.22918v2 Announce Type: replace Abstract: Vision-language models (VLMs) can read text from images, but where does this optical character recognition (OCR) information enter the language proc
OpenAI should probably bite the bullet and just name their next set of models something more human sounding. Everyone anthropomorphizes their AIs anyway, and 'Claude' is an easier name to refer to tha
arXiv:2604.07166v1 Announce Type: cross Abstract: Although visual foundation models like DINOv2 provide state-of-the-art performance as feature extractors, their complex, high-dimensional representati