Knowledge catalogue
I've been wanting to test out LLM inference on FPGAs for a while now, but didn't have a big reason too since there were no frontier class models at 9B-27B scale (3.6 27B was great still but it didn't
arXiv:2610.01944v1 Announce Type: new Abstract: Few-shot personalization enables large vision--language models (LVLMs) to learn user-specific visual concepts for applications such as personalized retr
arXiv:2610.01687v1 Announce Type: cross Abstract: Test-time scaling often seeks better answers by sampling multiple responses from a frozen model, yet conventional temperature sampling generates every
arXiv:2610.01989v1 Announce Type: new Abstract: Concept erasure removes copyright-protected, privacy-sensitive, or otherwise undesirable concepts from pretrained text-to-image diffusion models to supp
arXiv:2610.01963v1 Announce Type: new Abstract: Emergency department (ED) triage is a high-stakes prioritization task in which demographic, socioeconomic, and system-context information may improperly
arXiv:2610.00661v1 Announce Type: cross Abstract: Diffusion large language models (dLLMs) generate text by denoising a sequence or successive blocks, allowing several tokens to be revealed in parallel
arXiv:2307.12226v3 Announce Type: replace-cross Abstract: Machine learning models -- including prominent zero-shot models -- are often trained on datasets whose labels are only a small proportion of a
arXiv:2610.00722v1 Announce Type: new Abstract: World models enable agents to plan by predicting future states of the environment, but their predictions can become unreliable when test-time dynamics d
arXiv:2610.01079v1 Announce Type: cross Abstract: Machine-learning Network Intrusion Detection Systems (IDS) depend on substantial labeled datasets and task-specific training, whereas Large Language M
Multilingual self-supervised speech models can benefit from sharing information across languages, but under a matched total pretraining data budget they still fall short of monolingual models. We show
arXiv:2610.00095v1 Announce Type: new Abstract: Tutoring systems use mastery thresholds to decide when students can stop practicing and advance, but the same numerical threshold can lead to very diffe
arXiv:2610.01143v1 Announce Type: cross Abstract: Despite strong mean accuracy, tabular foundation models (TFMs) can perform poorly on underrepresented groups under subpopulation shift, where group pr
arXiv:2502.14994v2 Announce Type: replace Abstract: The rapid advancement of AI-generated video poses challenges to digital authenticity and security. Current detection methods, often trained on speci
arXiv:2610.01962v1 Announce Type: cross Abstract: The ability of vision-language models (VLMs) to associate visual identities with biographical information creates a need for selective unlearning of p
arXiv:2609.39188v1 Announce Type: new Abstract: Developmental psychology holds that certain priors are given to infants prior to experience rather than induced from data, and that the influence of suc
arXiv:2609.38810v1 Announce Type: cross Abstract: As vision language models are increasingly deployed in clinical diagnosis, understanding how they internally resolve competing visual and textual sign
arXiv:2609.38193v1 Announce Type: cross Abstract: Patient world models and clinical agents aim to predict changes in patients' health and support clinical work. Developing these systems requires relia
arXiv:2609.39178v1 Announce Type: cross Abstract: Recently, Vision-Language-Action (VLA) models have revolutionized robotic manipulation by seamlessly integrating visual perception, language understan
arXiv:2609.39453v1 Announce Type: cross Abstract: Speech emotion recognition (SER) is the task of assigning emotion labels to utterances. Early systems relied on acoustic features, whereas recent appr
arXiv:2609.39871v1 Announce Type: new Abstract: Hyperspectral remote sensing has advanced across diverse deep learning paradigms, including spectral spatial CNNs, Vision Transformers, Mamba, graph neu
arXiv:2609.40063v1 Announce Type: cross Abstract: Low-Rank Adaptive Residual Connections (LARC) give a frozen model a compact numerical state that can learn from feedback. The map h+BAh adds a low-ran
arXiv:2609.39548v1 Announce Type: cross Abstract: Backdoor attacks pose a serious threat to the secure deployment of text-to-image (T2I) diffusion models. Existing defenses typically detect backdoors
arXiv:2609.39071v1 Announce Type: new Abstract: Legal language models require reward signals that capture not only answer correctness but also the multidimensional quality of legal responses. Existing
arXiv:2609.39107v1 Announce Type: new Abstract: Large Language Models (LLMs) have been applied in various fields. However, ensuring compliance and safety of LLMs, such as avoiding discrimination and b
arXiv:2609.39483v1 Announce Type: new Abstract: Ownership establishes rights over the use, control, and transfer of objects. Understanding these relations is essential for AI systems to interact appro
arXiv:2609.37616v1 Announce Type: cross Abstract: Language models tend to agree with whatever a user asserts, and post-training increasingly targets this sycophancy so that models evaluate claims on t
arXiv:2609.35831v1 Announce Type: new Abstract: Modern large language models now support context windows of more than one million tokens, which has raised the question of whether retrieval-augmented g
🪽DFlash draft models are available for Ornith-1.5 9B, 35B-A3B, and 397B. DFlash and Ornith 1.5 make a dynamic duo: DFlash performs as the draft model, accelerating inference by drafting multiple token
arXiv:2609.37378v1 Announce Type: cross Abstract: Latent world models are trained to predict what happens next, so nothing in their objective separates what an action caused from what merely co-occurr
arXiv:2609.33401v2 Announce Type: replace-cross Abstract: Model-based judges support agent security by detecting prompt injections, assessing interaction risks, and screening harmful requests. System
Amazon Bedrock now supports Anthropic's Claude Opus 5 and Claude Sonnet 5 with in-region inference in Seoul, and Claude Sonnet 5 in Singapore. If you have local data processing requirements in South K
arXiv:2609.36288v1 Announce Type: new Abstract: EEG foundation models (EEG-FMs) are intended to generalize across different datasets by learning representations that, ideally, are invariant to dataset
System one models are extremely useful for a variety of document tasks that require fast decisions: * orientation detection * language detection * classification * splitting We benchmarked Jev with ot
arXiv:2609.37250v1 Announce Type: cross Abstract: World-action models (WAMs) couple future visual-state prediction with action generation. By adapting video generators or image-editing models pretrain
arXiv:2609.34585v1 Announce Type: new Abstract: We propose Tiny Recursive Models for Combinatorial Optimization (ours{}), a general neural method for combinatorial optimization that scales both depth
arXiv:2609.31792v1 Announce Type: cross Abstract: While Vision-Language-Action (VLA) models perform strongly on manipulation tasks, their responses to invalid task premises remain underexplored. Exist
arXiv:2609.35269v1 Announce Type: cross Abstract: The rising number of concept unlearning techniques for text-to-image (T2I) diffusion models has produced a fragmented evaluation landscape. Methods ar
arXiv:2603.15033v4 Announce Type: replace Abstract: Machine unlearning for vision models is rapidly becoming a practical requirement, driven by privacy regulations, data errors, and the need to remove
arXiv:2609.33269v1 Announce Type: cross Abstract: World Action Models (WAMs) jointly generate video and robot actions through iterative diffusion and perform strongly in robotic manipulation. However,
arXiv:2609.35553v1 Announce Type: new Abstract: Diffusion models have revolutionized generative modeling for continuous data through the gradual refinement of a belief state. This iterative refinement
arXiv:2609.33575v1 Announce Type: new Abstract: Vision-Language-Action models are increasingly effective for robotic manipulation, yet most predict actions directly from current observations without e
arXiv:2609.32813v1 Announce Type: new Abstract: Large vision-language models (VLMs) have emerged as a powerful paradigm for urban and spatial AI. However, current state-of-the-art large VLMs still str
arXiv:2609.34300v1 Announce Type: new Abstract: World models offer a powerful substrate for safety reasoning in high-dimensional robotic systems, but they are also fallible: their predictions can be b
arXiv:2609.34065v1 Announce Type: cross Abstract: Names are personal identifiers, but they also carry social meaning and are widely used to evaluate how language models treat different people. Such ev
arXiv:2609.35560v1 Announce Type: new Abstract: Interactive world models require responding in real time to versatile controls and maintaining long-horizon consistency. However, modeling heterogeneous
arXiv:2609.30993v1 Announce Type: cross Abstract: We present FLIP, a final-layer inference-time probe for testing whether a logit-facing intervention site in an open-weight vision-language model (VLM)
arXiv:2609.31154v1 Announce Type: new Abstract: Recent advances in text-to-image (T2I) generation have substantially improved visual synthesis, but have also raised increasing safety concerns due to t
arXiv:2609.31461v1 Announce Type: new Abstract: Background: Large volumes of unlabeled knee MRI scans are available across repositories but remain insufficiently leveraged. We developed KneePreM, a kn
arXiv:2609.30770v1 Announce Type: cross Abstract: General-purpose robot models increasingly rely on large and diverse datasets. For embodied 3D navigation, however, existing data sources face a fundam
arXiv:2609.30946v1 Announce Type: cross Abstract: Action-conditioned video world models aim to predict scene evolution under different actions, a capability that is essential for reliable planning, de
arXiv:2609.31403v1 Announce Type: cross Abstract: Vision-language models (VLMs), despite their success in optical character recognition (OCR) tasks, are vulnerable to typographic attacks and have a fr
arXiv:2509.26473v2 Announce Type: replace Abstract: Unified Multimodal Understanding and Generation Models (UMMs) increasingly combine visual understanding and image generation within a single interac
arXiv:2609.31341v1 Announce Type: new Abstract: Whether an information extraction pipeline should process page images or parsed text depends on the document, and the answer flips across the layout spe
Simon Willison defines “Fable class models” as a lineage of generative AI systems that began with Claude Fable 5, progressed to Claude Opus 5.5, and later included GPT‑Astra 6 (with a possible additio
Meta came out with a banger paper https://arxiv.org/pdf/2606.00206, but it did not look at various quantizations supported in llama.cpp. So I did a run on 50 random MATH-500 questions (https://hugging
An interesting idea is to continually train specialized models on skills. This paper explores that idea. They propose SkillGym which turns human-written skills into 2,756 training environments with co
Sometimes it’s easy to forget that this sub and others like it are probably the extreme minority when it comes to this hobby. Most people, I would think, don’t use or can’t afford one good GPU, let al
arXiv:2609.28670v1 Announce Type: cross Abstract: Graph-based world models have recently emerged as a means of learning transitions over relational state representations. However, existing approaches
arXiv:2609.30167v1 Announce Type: new Abstract: Audio language models pass speech and text through a single decoder. We ask whether that decoder represents a distinctive feature in the same direction
arXiv:2609.29410v1 Announce Type: new Abstract: Recent studies have shown that Large Language Models can effectively solve problems and fix bugs in diverse programming environments, including competit