Knowledge catalogue
arXiv:2604.08627v1 Announce Type: cross Abstract: Pretrained models have become standard in both vision and language, yet they typically do not provide reliable measures of confidence. Existing uncert
arXiv:2601.18150v2 Announce Type: replace-cross Abstract: Reinforcement learning (RL) for large language models (LLMs) is increasingly bottlenecked by rollout (generation), where long output sequence
arXiv:2508.16165v2 Announce Type: replace-cross Abstract: Usability evaluation is an essential method to support the design of effective and intuitive user interfaces (UIs). However, it commonly relie
arXiv:2604.08801v1 Announce Type: cross Abstract: Prompt optimization improves language models without updating their weights by searching for a better system prompt, but its effectiveness varies wide
arXiv:2604.08986v1 Announce Type: cross Abstract: Persona prompting has been widely adopted to steer large language models (LLMs) behavior and improve their instruction performance by assigning specif
arXiv:2604.09386v1 Announce Type: new Abstract: Instruction-guided image editing requires balancing target modification with non-target preservation. Recently, flow-based models have emerged as a stro
arXiv:2604.09237v1 Announce Type: new Abstract: Many disciplines pose natural-language research questions over large document collections whose answers typically require structured evidence, tradition
arXiv:2604.08555v1 Announce Type: new Abstract: Physician-physician discussions of patient cases represent a rich source of clinical knowledge and reasoning that could feed AI agents to enrich and eve
arXiv:2604.07720v2 Announce Type: replace Abstract: Deep Research (DR) requires LLM agents to autonomously perform multi-step information seeking, processing, and reasoning to generate comprehensive r
After seeing that Claude Mythos marketing turned out to be, as expected, a scam, I wanted to make a master list of tricks being used to market LLMs. The master list includes statements directly from l
MiniMax-M1 is a large-scale open-weight reasoning model developed by MiniMax, featuring a hybrid Mixture-of-Experts (MoE) architecture with 456 billion total parameters (activating 45.9 billion per to
Auto-generated index of all companies mentioned across the wiki.
llama.cpp release **b8744**, published on April 10, 2026, is a build of the ggml-org/llama.cpp C/C++ LLM inference engine. Its primary change enables the reasoning budget sampler for Gemma 4 by add...
arXiv:2604.06233v1 Announce Type: new Abstract: Safety-trained language models routinely refuse requests for help circumventing rules. But not all rules deserve compliance. When users ask for help eva
arXiv:2508.13993v2 Announce Type: replace Abstract: Long-context modeling is critical for a wide range of real-world tasks, including long-context question answering, summarization, and complex reason
arXiv:2601.22451v2 Announce Type: replace-cross Abstract: Despite progress in Large Vision Language Models (LVLMs), object hallucination remains a critical issue in image captioning task, where models
arXiv:2604.07070v1 Announce Type: new Abstract: While Large Language Models (LLMs) demonstrate remarkable reasoning capabilities, their potential for purpose-driven exploration in dynamic geo-spatial
arXiv:2604.07430v1 Announce Type: new Abstract: We introduce HY-Embodied-0.5, a family of foundation models specifically designed for real-world embodied agents. To bridge the gap between general Visi
arXiv:2604.07941v1 Announce Type: new Abstract: Post-training has become central to turning pretrained large language models (LLMs) into aligned and deployable systems. Recent progress spans supervise
arXiv:2604.06950v2 Announce Type: replace Abstract: Multimodal Large Language Models (MLLMs) are increasingly being deployed as automated content moderators. Within this landscape, we uncover a critic
arXiv:2604.06180v1 Announce Type: cross Abstract: Medical diagnosis using Large Multimodal Models (LMMs) has gained increasing attention due to capability of these models in providing precise diagnose
arXiv:2604.07741v1 Announce Type: new Abstract: Audio-visual deepfake detection typically employs a complementary multi-modal model to check the forgery traces in the video. These methods primarily ex
arXiv:2604.07296v2 Announce Type: replace Abstract: Spatial understanding is a fundamental cornerstone of human-level intelligence. Nonetheless, current research predominantly focuses on domain-specif
arXiv:2604.06912v1 Announce Type: cross Abstract: MLLMs require high-resolution visual inputs for fine-grained tasks like document understanding and dense scene perception. However, current global res
arXiv:2604.07774v1 Announce Type: cross Abstract: This paper focuses on embodied task planning, where an agent acquires visual observations from the environment and executes atomic actions to accompli
arXiv:2604.07737v1 Announce Type: new Abstract: While transformer-based Large Language Models (LLMs) theoretically support massive context windows, they suffer from severe performance degradation when
arXiv:2604.06714v1 Announce Type: new Abstract: AI applications driven by multimodal large language models (MLLMs) are prone to hallucinations and pose considerable risks to human users. Crucially, su
arXiv:2412.10437v3 Announce Type: replace Abstract: Generating high-quality Scalable Vector Graphics (SVGs) from text remains a significant challenge. Existing LLM-based models that generate SVG code
arXiv:2604.06502v1 Announce Type: new Abstract: Vision-Language Models (VLMs) face significant safety vulnerabilities from malicious prompt attacks due to weakened alignment during visual integration.
arXiv:2604.06422v1 Announce Type: cross Abstract: Understanding when Vision-Language Models (VLMs) will behave unexpectedly, whether models can reliably predict their own behavior, and if models adher
arXiv:2604.06829v2 Announce Type: cross Abstract: Synthetic data rephrasing has emerged as a powerful technique for enhancing knowledge acquisition during large language model (LLM) pretraining. Howev
FlowInOne is a vision-centric multimodal image generation framework that reformulates multimodal generation as a purely visual flow, converting all inputs into visual prompts and enabling a clean i...
Stop trusting LLMs just because they're useful. 🛑 Our Head of DevRel @RoieSchwabco breaks down the two essential parts of a reliable AI stack: ⚙️ Reasoning: What the LLM does (logic/synthesis/formatti
Visually rich documents are especially challenging for agents. Tables, charts, and images often break traditional document pipelines, making complex reasoning difficult📄 So we teamed up with @lancedb
I ran five coding tasks against nine models on one RX 9060 XT (16 GB). Each run gets a single spec file in an empty directory and has to produce solution.py and test_solution.py, run its own tests, an
model : add Kolibri-1 (Aleph-Alpha) support (#30673) model : add Kolibri-1 (Aleph-Alpha) support Kolibri-1 is a bilingual German/English MoE reasoning model with 78B parameters and 3.46B active per to
Hey everyone, English is not my native language (Dutch), but I write in my own words without assistance. So please let me know if any sentence flows weird, etc. A mate of mine told me how amazing loca
arXiv:2610.21323v1 Announce Type: new Abstract: Most vision-language models (VLMs) treat the vision encoder as a static feature extractor: it encodes an image once, independently of the question, and
arXiv:2610.22306v1 Announce Type: new Abstract: Multi-object tracking in sports broadcasts is hard for two reasons: athletes move fast and change direction abruptly, and the camera pans and zooms at t
arXiv:2610.21218v1 Announce Type: new Abstract: Agentic large language models have been documented to lose reasoning capability when placed inside a harness, the software that mediates their observati
arXiv:2610.22017v1 Announce Type: new Abstract: Retrieval-augmented generation over text-rich knowledge graphs requires identifying evidence that contributes to answering a question, rather than merel
arXiv:2610.21424v1 Announce Type: new Abstract: Scientific agents must connect research problems, methods, and findings dispersed through narrative articles. We introduce SPRA (Structured Paper Repres
arXiv:2610.20989v1 Announce Type: cross Abstract: Improving the reasoning capabilities of vision-language models (VLMs) often relies on post-training with supervision from stronger models. Two common
arXiv:2610.22290v1 Announce Type: new Abstract: Reinforcement learning has become a common post-training technique to improve the accuracy of LLMs on verifiable tasks. However, such training can narro
arXiv:2610.22195v1 Announce Type: new Abstract: Orchestrating multiple agents on a complex task requires reconciling local subtask execution with global task planning. Dynamic dispatch approaches prov
Knowledge graphs are becoming a critical context and reasoning layer for agentic AI, helping enterprises connect data and ground agents in key areas of business expertise. For diversified financial se
arXiv:2602.18891v2 Announce Type: replace-cross Abstract: Advances in large language models (LLMs) are rapidly transforming scientific work, yet empirical evidence on how these systems reshape researc
arXiv:2610.21220v1 Announce Type: cross Abstract: Recommender systems often need to balance multiple conflicting objectives. Controllable Multi-Objective Recommendation (CMOR) enables dynamic adjustme
arXiv:2602.09432v2 Announce Type: replace Abstract: Current one-pass 3D scene synthesis methods often suffer from spatial hallucinations, such as collisions, due to a lack of deliberative reasoning. T
arXiv:2610.21082v1 Announce Type: new Abstract: Large language model (LLM) agents can keep scientific experiments running for months with little human supervision, but reliable autonomous research als
arXiv:2610.21244v1 Announce Type: cross Abstract: Large language models (LLMs) often make discrete decisions, such as flagging phishing or escalating to a human. System-1 models, such as Jev and the O
arXiv:2610.21128v1 Announce Type: cross Abstract: Label-free evaluation methods, such as self-consistency filtering, majority-vote aggregation, and agreement-based reliability scoring, rely on an impl
arXiv:2610.20731v1 Announce Type: cross Abstract: Humans interpret multimodal observations of the world and forecast how it will evolve. Recent multimodal generative systems have demonstrated similar
arXiv:2610.19007v1 Announce Type: new Abstract: World models are a powerful means of reasoning and planning, but many of these action-conditioned predictive models are high dimensional and computation
arXiv:2604.03925v2 Announce Type: replace Abstract: Large language models (LLMs) struggle to accumulate evidence across multiple rounds of user interactions, failing to update their beliefs in a manne
arXiv:2610.19624v1 Announce Type: new Abstract: Visual recognition models usually process a fixed view under a fixed computation budget, although images often benefit from different scales and amounts
arXiv:2610.14542v1 Announce Type: new Abstract: Multimodal benchmarks are central to evaluating whether models can reason over information from multiple modalities. However, existing literature has re
arXiv:2610.15855v1 Announce Type: new Abstract: We study how to detect and mitigate visual attention sinks in vision-language models (VLMs). Visual attention sinks are image tokens that absorb a large
arXiv:2610.19704v1 Announce Type: new Abstract: Large language models (LLMs) increasingly help users arrange appointments, plan journeys, and allocate limited resources. These tasks require models to
arXiv:2610.19882v1 Announce Type: new Abstract: Instruction-driven image editing has reached native 4K, yet how such editors are trained remains undisclosed, and pretraining one from scratch is beyond