Knowledge catalogue
arXiv:2604.24043v1 Announce Type: new Abstract: Designing heuristics for combinatorial optimization problems (COPs) is a fundamental yet challenging task that traditionally requires extensive domain e
arXiv:2604.24089v1 Announce Type: new Abstract: Bridging molecular structures and natural language is essential for controllable design. Autoregressive models struggle with long-range dependencies, wh
arXiv:2604.23655v1 Announce Type: new Abstract: Videos captured in low-light and underwater conditions often suffer from distortions such as noise, low contrast, color imbalance, and blur. These issue
arXiv:2510.24941v3 Announce Type: replace Abstract: Large language models can generate long chain-of-thought (CoT) reasoning, but it remains unclear whether the verbalized steps reflect the models' in
arXiv:2604.22897v1 Announce Type: cross Abstract: Patent retrieval underpins critical decisions in innovation, examination, and IP strategy, yet progress has been hampered by the absence of benchmarks
arXiv:2604.23612v1 Announce Type: new Abstract: Partial Differential Equation (PDE)-based approaches have gained significant attention in image despeckling due to their strong capability to preserve s
arXiv:2512.03847v2 Announce Type: replace-cross Abstract: Reinforcement learning (RL) has shown strong performance in LLM post-training, but real-world deployment often involves noisy or incomplete su
arXiv:2604.24188v1 Announce Type: new Abstract: Accurately estimating friction coefficients between arbitrary material pairs is critical for robotics, digital fabrication, and physics-based simulation
arXiv:2511.09749v2 Announce Type: replace Abstract: Developing reliable iris recognition and presentation attack detection methods requires diverse datasets that capture realistic variations in iris f
arXiv:2604.23478v1 Announce Type: new Abstract: Large language models are increasingly deployed as automated judges for evaluating other models, yet the stability of their verdicts under semantically
arXiv:2604.23178v1 Announce Type: new Abstract: LLM-as-a-Judge has become the dominant paradigm for evaluating language model outputs, yet LLM judges exhibit systematic biases that compromise evaluati
arXiv:2510.10486v2 Announce Type: replace-cross Abstract: Open-source large language models (LLMs) have demonstrated considerable dominance over proprietary LLMs in resolving neural processing tasks,
arXiv:2604.23442v1 Announce Type: new Abstract: Weeds compete with crops for light, water, and nutrients, reducing yield and crop quality. Efficient weed detection is essential for site-specific weed
arXiv:2510.12826v2 Announce Type: replace-cross Abstract: As large language model (LLM) agents are deployed autonomously in diverse contexts, evaluating their capacity for strategic deception becomes
arXiv:2511.17411v2 Announce Type: replace-cross Abstract: Robotic Foundation Models (RFMs) hold great promise as generalist, end-to-end systems for robot control. Yet their ability to generalize acros
arXiv:2604.22251v1 Announce Type: new Abstract: Variable impedance model predictive control (MPC) formulations that treat joint stiffness as an instantaneous decision variable operate on a feasible se
arXiv:2604.22271v1 Announce Type: new Abstract: Large language models can detect their own errors and sometimes correct them without external feedback, but the underlying mechanisms remain unknown. We
In this post, we share how we applied Amazon Bedrock and the Amazon Nova family of models to reimagine our Title Suggestion feature. By combining metadata, computer vision, and retrieval-augmented gen
microsoft/VibeVoice VibeVoice is Microsoft's Whisper-style audio model for speech-to-text, MIT licensed and with speaker diarization built into the model. Microsoft released it on January 21st, 2026 b
arXiv:2604.22520v1 Announce Type: new Abstract: Large Language Models (LLMs) have achieved remarkable performance in Machine Translation (MT), but deploying them at scale remains prohibitively expensi
arXiv:2604.22215v1 Announce Type: cross Abstract: Verbal confidence elicitation is widely used to extract uncertainty estimates from LLMs. We tested whether seven instruction-tuned open-weight models
The Qwen 3.6-27B and 35B models are designed as open-weight models that developers can run locally on their own hardware without requiring cloud services. Alibaba released a separate cloud-only produc
arXiv:2305.01626v4 Announce Type: replace-cross Abstract: Computational models of syntax are predominantly text-based. Here we propose that the most basic first step in the evolution of syntax can be
arXiv:2604.20893v1 Announce Type: new Abstract: Wrist exoskeletons play a vital role in rehabilitation and assistive applications, yet conventional actuation mechanisms such as electric motors or pneu
arXiv:2602.16729v3 Announce Type: replace-cross Abstract: We systematically evaluate the quality of widely used adversarial safety datasets from two perspectives: in isolation and in practice. In isol
arXiv:2505.15269v2 Announce Type: replace Abstract: Recent developments in Video Large Language Models (Video LLMs) have enabled models to process hour-long videos and exhibit exceptional performance.
Release: llm 0.31 New GPT-5.5 OpenAI model: llm -m gpt-5.5. #1418 New option to set the text verbosity level for GPT-5+ OpenAI models: -o verbosity low. Values are low, medium, high. New option for se
arXiv:2604.21454v1 Announce Type: cross Abstract: Reasoning in large language models is often treated as a monolithic capability, but its observed gains may arise from more basic operations. We study
arXiv:2511.03325v3 Announce Type: replace Abstract: Video Question Answering (VideoQA) in the surgical domain aims to enhance intraoperative understanding by enabling AI models to reason over temporal
arXiv:2604.21396v1 Announce Type: cross Abstract: The advancement of Large Vision-Language Models (LVLMs) requires precise local region-based reasoning that faithfully grounds the model's logic in act
DeepSeek V4 Pro Max is a large language model released by DeepSeek AI and made available on Hugging Face, representing an advancement in their model lineup. The announcement was made by Clem Delangue,
arXiv:2601.03396v2 Announce Type: replace Abstract: Procedural content generation has enabled vast virtual worlds through levels, maps, and quests, but large-scale character generation remains underex
arXiv:2604.20523v1 Announce Type: cross Abstract: We study whether Large Language Models (LLMs) can perform feature model analysis operations (AOs) directly on semi-formal textual blueprints, i.e., co
arXiv:2604.20141v1 Announce Type: new Abstract: We introduce Fourier Weak SINDy, a minimal noise-robust and interpretable derivative-free equation learning method that combines weak-form sparse equati
arXiv:2604.20286v1 Announce Type: cross Abstract: Recent segmentation models have demonstrated promising efficiency by aggressively reducing parameter counts and computational complexity. However, the
arXiv:2604.20290v1 Announce Type: new Abstract: To enable autonomous wind estimation for energy-efficient flight in small unmanned aerial vehicles (UAVs), this study proposes a method that estimates f
This post demonstrates a DFlash implementation integrated with llama-cpp, showcasing a speculative decoding setup that uses Qwen 3.6-27B as the main model with a smaller draft model (dflash-draft-q4_k
arXiv:2604.20209v1 Announce Type: new Abstract: LLM self-play algorithms are notable in that, in principle, nothing bounds their learning: a Conjecturer model creates problems for a Solver, and both i
arXiv:2604.19888v1 Announce Type: new Abstract: Driver gaze estimation is essential for understanding the driver's situational awareness of surrounding traffic. Existing gaze estimation models use dri
arXiv:2604.20727v1 Announce Type: cross Abstract: Training large foundation models for agentic tasks is increasingly impractical due to the high computational costs, long iteration cycles, and rapid o
arXiv:2604.19643v1 Announce Type: new Abstract: AcoustoBots are mobile acoustophoretic robots capable of delivering mid-air haptics, directional audio, and acoustic levitation, but existing implementa
arXiv:2604.19533v1 Announce Type: cross Abstract: We introduce the Cyber Defense Benchmark, a benchmark for measuring how well large language model (LLM) agents perform the core SOC analyst task of th
arXiv:2508.06226v2 Announce Type: replace Abstract: Geometry problem solving (GPS) poses significant challenges for Multimodal Large Language Models (MLLMs) in diagram comprehension, knowledge applica
This post likely demonstrates running Qwen2 3.6B or 27B model in GGUF format using llama-server with default specifications, showcasing inference capabilities of quantized open-source models. The comm
arXiv:2604.19093v1 Announce Type: cross Abstract: Multi-modal test-time adaptation (TTA) enhances the resilience of benchmark multi-modal models against distribution shifts by leveraging the unlabeled
arXiv:2604.18943v1 Announce Type: new Abstract: With the rise in capabilities of large language models (LLMs) and their deployment in real-world tasks, evaluating LLM alignment with human preferences
By combining the analytical depth of Looker with Google’s Agentic Data Cloud, the potential to transform how we model, interact with, and act on our data appears limitless. This week at Google Cloud N
While generative AI sparked a revolution, the true paradigm shift is the rapid evolution from standalone AI models to multi-agent autonomous systems. In this new era, the network transcends basic conn
arXiv:2604.17130v1 Announce Type: cross Abstract: The present study aims to investigate a cluster cleaning algorithm that is both computationally simple and capable of solving the PU classification wh
arXiv:2604.17914v1 Announce Type: new Abstract: Self-supervised contrastive learning has emerged as a powerful paradigm for skeleton-based action recognition by enforcing consistency in the embedding
arXiv:2604.16719v1 Announce Type: new Abstract: Time-series forecasting is central to many scientific and industrial domains, such as energy systems, climate modeling, finance, and retail. While forec
arXiv:2506.01732v2 Announce Type: replace Abstract: Large Language Models (LLMs) are pre-trained on large data from different sources and domains. These datasets often contain trillions of tokens, inc
arXiv:2604.17398v1 Announce Type: new Abstract: We present a methodological framework to discover linguistic and discursive patterns associated to different social groups through contrastive synthetic
arXiv:2601.03066v2 Announce Type: replace Abstract: Large language models solve complex tasks by generating long reasoning chains, achieving higher accuracy at the cost of increased computational cost
arXiv:2604.16918v1 Announce Type: new Abstract: Reinforcement Learning (RL) has achieved impressive success in post-training Large Language Models (LLMs) and Vision-Language Models (VLMs), with on-pol
arXiv:2604.17371v1 Announce Type: cross Abstract: This paper investigates communication-efficient neural network transmission by exploiting structured symmetry constraints in convolutional kernels. In
arXiv:2604.16808v1 Announce Type: new Abstract: Current lip-sync deepfake detectors rely on pixel-level artifacts or audio-visual correspondence, failing to generalize across languages because these c
arXiv:2604.16419v1 Announce Type: cross Abstract: Fairness-aware recommender systems often mitigate bias by increasing exposure to under-represented or long-tail content, commonly through mechanisms t
arXiv:2604.18326v1 Announce Type: new Abstract: Recent advancements in audio-video joint generation models have demonstrated impressive capabilities in content creation. However, generating high-fidel
arXiv:2505.19237v2 Announce Type: replace-cross Abstract: Self-recognition -- the ability to maintain an internal representation of one's own body within the environment -- underpins intelligent, auto