Knowledge catalogue
arXiv:2609.18037v1 Announce Type: new Abstract: Segment Anything Models provide reusable priors, yet they require user prompts and cannot support fully automatic instrument segmentation. Automatic pro
arXiv:2601.23232v4 Announce Type: replace-cross Abstract: In recent years, large language models (LLMs) have made rapid progress in information retrieval, yet existing research has mainly focused on t
arXiv:2609.18642v1 Announce Type: new Abstract: Large language models (LLMs) often suffer from capability stagnation in self-improvement training because fixed difficulty levels fail to adapt to their
arXiv:2609.18174v1 Announce Type: new Abstract: Dexterous in-hand manipulation requires policies that coordinate high-DoF hand joints through intermittent, contact-rich interaction. Beyond target-orie
arXiv:2609.18958v1 Announce Type: cross Abstract: The natural way to review a long recording or document with a multimodal model is to hand it the raw source and ask for a review in one call. We show
arXiv:2609.17984v1 Announce Type: new Abstract: Machine-learning libraries such as Weka and scikit-learn were designed for human programmers. Language-model agents now use these same libraries by reca
arXiv:2609.18182v1 Announce Type: new Abstract: Real-world agents fundamentally require persistent non-parametric knowledge for dynamic reasoning, i.e., long-term memory and retrieval-augmented genera
arXiv:2609.16309v1 Announce Type: new Abstract: Despite the rapid progress of LLM-based agents for planning, code generation, and debugging, their practical value for tabular machine learning remains
arXiv:2609.16948v1 Announce Type: new Abstract: Near-field to far-field transformation is central to large-aperture antenna testing, yet two coupled challenges remain: costly phase acquisition at mill
metal: fix NaN in mul_mm_id when activations exceed f16 range (#26223) test-backend-ops: reproduce MUL_MAT_ID NaN for activations beyond f16 The Metal mul_mm_id path narrows src1 to half for the simdg
arXiv:2609.16664v1 Announce Type: new Abstract: Leveraging Large Vision-Language Models like CLIP has recently set new benchmarks for No-Reference Image Quality Assessment (NR-IQA). However, the contr
arXiv:2609.16814v1 Announce Type: new Abstract: While Large Language Model (LLM)-based Natural Language Inference (NLI) systems achieve high accuracy, their decision-making processes lack auditable st
arXiv:2609.16204v1 Announce Type: cross Abstract: Safety guardrails in open-weight language models can be readily bypassed using Refusal Feature Ablation (RFA), a technique that identifies and project
arXiv:2609.17210v1 Announce Type: cross Abstract: Vision-language-action (VLA) models, world-action models (WAMs), and offline reinforcement learning methods are rapidly expanding the design space of
arXiv:2603.12264v2 Announce Type: replace Abstract: Unified multimodal models target joint understanding, reasoning, and generation, but current image editing benchmarks are largely confined to natura
arXiv:2609.16816v1 Announce Type: cross Abstract: Language model-generated rubrics are increasingly used as reward signals for rubric-based reinforcement learning, LLM-as-a-judge evaluation, and autom
A follow-up to my earlier post about small models on phones. Last time it was fixed tasks in a single browser. This is something else. Ministral 3 3B Q4_K_M in llama.cpp on a Samsung Galaxy S21, four
At last my small pebble of contribution has been merged. Thanks to CISC. Support for the model DFM Mimir 1B gguf here: https://huggingface.co/noctrex/DFM-Mimir additional optimization will be added in
arXiv:2609.16614v1 Announce Type: cross Abstract: Speech-to-speech dialogue models increasingly support persona control, yet existing spoken role-playing benchmarks remain largely character-centric an
arXiv:2602.06652v2 Announce Type: replace Abstract: The robustness of Vision Language Models (VLMs) is commonly assessed through output-level invariance, implicitly assuming that stable predictions re
arXiv:2609.17040v1 Announce Type: new Abstract: Wild test-time adaptation (WTTA) updates a source model online under small test batches, concurrent distribution shifts, and time-varying class imbalanc
I wanted to test what Qwen 3.8 27B running locally on a single 5090 could do in Row-Bot. I gave it just one prompt: 'I want you to create an animation showing what the current local model can do. Test
arXiv:2609.16778v1 Announce Type: new Abstract: The unchecked proliferation of manipulated images on social media platforms has increased the spread of misinformation, posing a severe threat to public
arXiv:2609.13624v1 Announce Type: cross Abstract: Large Language Models (LLMs) are powerful zero-shot learners but remain prone to misalignment with human preferences, often producing biased, toxic, o
arXiv:2609.15511v1 Announce Type: cross Abstract: This paper investigates the generation and human evaluation of Japanese haiku by contemporary Large Language Models (LLMs), focusing on authorship per
arXiv:2609.15087v1 Announce Type: cross Abstract: Most time series forecasting benchmarks remain numerical-centric and provide limited support for evaluating contextual information that shapes real-wo
arXiv:2609.13498v1 Announce Type: cross Abstract: We report a multi-month engineering program to build Sophea, a production bilingual Greek-English automatic speech recognition system. We evaluate the
arXiv:2609.15989v1 Announce Type: new Abstract: Chain-of-thought (CoT) monitoring is a safety strategy where the reasoning of a large language model 'actor' is inspected by a 'monitor' (often another
arXiv:2609.13191v1 Announce Type: new Abstract: The rapid expansion of operational satellites and orbital debris has increased the frequency of close approach events in low Earth orbit (LEO), creating
arXiv:2511.12101v3 Announce Type: replace-cross Abstract: Many recent Vision-Language-Action models employ diffusion or flow-matching backbones with hundreds of millions of parameters for action gener
arXiv:2603.13359v2 Announce Type: replace Abstract: Language models are commonly fine-tuned for safety alignment to refuse harmful prompts. One approach fine-tunes them to generate categorical refusal
arXiv:2609.14864v1 Announce Type: new Abstract: We predict single-sequence model throughput from GGUF metadata using roofline-shaped predictors with quantization-specific scale factors fitted on refer
arXiv:2609.13308v1 Announce Type: new Abstract: A companion evaluation found that naming the target part in a manipulation prompt increased action accuracy by 0.32-0.63 across eight vision-language mo
arXiv:2609.13296v1 Announce Type: new Abstract: Test-time reinforcement learning can adapt vision-language models (VLMs) to unlabeled target data, but its effectiveness is fundamentally limited by the
arXiv:2512.01037v3 Announce Type: replace-cross Abstract: As safety alignment becomes standard in large language models, refusal behavior has become an important part of model reliability. However, mo
arXiv:2609.14246v1 Announce Type: cross Abstract: In wireless federated learning (FL), data heterogeneity and multiple local updates induce client drift, degrading model convergence. It is further aff
arXiv:2603.02504v3 Announce Type: replace Abstract: Large Language Models (LLMs) achieve strong performance on natural language tasks but remain unreliable in mathematical reasoning, frequently genera
arXiv:2609.14198v1 Announce Type: new Abstract: Surgical tissue manipulation demands precision; however, tool-tissue manipulation force magnitudes under realistic conditions are rarely quantified. To
arXiv:2609.14969v1 Announce Type: cross Abstract: Realignment is a promising approach for improving the cross-lingual transfer ability of multilingual language models, particularly for extremely low-r
arXiv:2609.15152v1 Announce Type: cross Abstract: Multimodal embedding models encode heterogeneous inputs into a shared embedding space, enabling efficient similarity computation across modalities and
arXiv:2609.15029v1 Announce Type: cross Abstract: Backdoor poisoning attacks add poisoned examples to otherwise-clean finetuning data, pairing a trigger with a target behavior that the model learns to
arXiv:2609.14998v1 Announce Type: new Abstract: Recent work shows that models that learn to reward hack on RL environments can become broadly misaligned, and that reframing reward hacking as acceptabl
arXiv:2609.15476v1 Announce Type: new Abstract: Large language models generate text by sampling each token from a predicted distribution, and a temperature parameter sets how far the draw strays from
THE SANDBOX WAS A PROP! OpenAI Turned Off the Guardrails, Left a Door to the Internet, and Then Sold the Hugging Face Breach as “Rogue AI” It is time to understand how you were lied to and by whom. In
arXiv:2609.13615v1 Announce Type: new Abstract: For our submission to the WMT26 Creole Language Translation Shared Task, we focus on machine translation (MT) models for Pacific creoles: Tok Pisin, Bis
arXiv:2609.13491v1 Announce Type: new Abstract: The strong performance of AI Agents across an impressive variety of tasks is driving an unprecedented investment in agentic infrastructures, however the
arXiv:2607.17632v2 Announce Type: replace-cross Abstract: Time series data play a pivotal role across numerous domains, including healthcare and manufacturing. In real-world environments, models must
arXiv:2609.15213v1 Announce Type: new Abstract: Scaling humanoid whole-body control toward general-purpose deployment requires large human motion corpora and training experience shared across robot bo
arXiv:2609.13100v1 Announce Type: cross Abstract: When providing forecasted probabilities with a predictive model, the ideal model offers perfect calibration: the true probability of the outcome (i.e.
arXiv:2609.12509v1 Announce Type: new Abstract: Evaluation of vision-language models (VLMs) for multimodal mathematical reasoning remains limited for low-resource languages and for geometry problems t
arXiv:2511.23372v2 Announce Type: replace Abstract: The increasing industrial demand for alternative actuators over conventional electromagnetism-based systems having limited efficiency, bulky size, c
arXiv:2609.13058v1 Announce Type: new Abstract: Reinforcement learning (RL) has become central to post-training of large language models. Recent advances in RL for Mixture-of-Experts (MoE) models have
arXiv:2609.12054v1 Announce Type: cross Abstract: Beam-induced background (BIB) from muon decay products will be an overwhelming and unavoidable background at a future Muon Collider. In order to devel
Intelligence was yours. A founder’s intellectual property, business logic, differentiation, their intelligence, was once theirs alone. You built it, you owned it, and no tools/platform vendor stood be
arXiv:2609.12752v1 Announce Type: new Abstract: Objective Prediction models are commonly trained using objectives such as Bernoulli negative log-likelihood (NLL), although downstream clinical decision
arXiv:2609.12552v1 Announce Type: new Abstract: Open-vocabulary detection accepts any class list at inference, and promptable segmentation returns regions without class names: the taxonomy has left th
arXiv:2609.12874v1 Announce Type: new Abstract: Video tokenizers have emerged as a cornerstone of modern video modeling, underpinning progress in compression, reconstruction and generation by mapping
The next phase of artificial intelligence in legal technology will not be defined by a better chatbot or a faster document-summarization tool. It will be defined by whether AI systems can take respons
arXiv:2609.10939v1 Announce Type: cross Abstract: Clinical education must prepare medical students to conduct safe and coherent patient interviews under conditions of uncertainty. Traditional standard
arXiv:2609.11859v1 Announce Type: new Abstract: How does a language model's dependence on query-routing information and target knowledge change as it answers a question? We study this question through