Knowledge catalogue
arXiv:2603.22078v3 Announce Type: replace Abstract: Robot action planning in the real world is challenging as it requires not only understanding the current state of the environment but also predictin
arXiv:2604.27929v1 Announce Type: new Abstract: With the widespread adoption of large language models (LLMs), understanding their personality representation mechanisms has become critical. As a novel
arXiv:2604.27987v1 Announce Type: new Abstract: Fine-tuning pretrained models has become a standard approach to adapting pretrained knowledge to improve the accuracy on new sparse, imbalance datasets.
arXiv:2604.27004v1 Announce Type: cross Abstract: We propose EdgeSpike, a co-designed spiking neural network (SNN) framework for autonomous low-power sensing in edge Internet of Things (IoT) architect
arXiv:2602.00095v3 Announce Type: replace-cross Abstract: Multimodal Large Language Models (MLLMs) hold significant promise for revolutionizing traditional education and reducing teachers' workload. H
arXiv:2604.27534v1 Announce Type: new Abstract: In natural language processing, the entropy of a language is a measure of its unpredictability and complexity. The first study on this subject was condu
Event with @googlegemma next week! Hang out with the fellow builders and members of the Gemma + LM teams at LM Studio HQ in NYC. When: Monday, May 11th RSVP: required, link below High likelihood of pi
arXiv:2604.27996v1 Announce Type: new Abstract: This paper examines how different types of large language model (LLM) agents perform on scientific visualization (SciVis) tasks, where users generate vi
arXiv:2604.27115v1 Announce Type: new Abstract: Neuron pruning is widely used to reduce the computational cost and parameter footprint of large language models, yet it remains unclear whether neurons
arXiv:2604.27590v1 Announce Type: new Abstract: Recent advances in 3D reconstruction and neural rendering,particularly 3D Gaussian Splatting, make it feasible and simple to edit 3D scenes and re-rende
arXiv:2501.04066v2 Announce Type: replace Abstract: As a special type of multimedia data, Lithography Hotspot Detection (LHD) training often requires stronger privacy protection than conventional mult
arXiv:2604.27014v1 Announce Type: new Abstract: The scarcity of high-quality annotated medical data, particularly in mental health, poses a significant bottleneck for training robust machine learning
arXiv:2506.02515v4 Announce Type: replace-cross Abstract: Multi-step symbolic reasoning is essential for robust financial analysis; yet, current benchmarks largely overlook this capability. Existing d
arXiv:2604.27974v1 Announce Type: new Abstract: Despite the rapid progress of large vision-language models (LVLMs), fine-grained, state-conditioned GUI interaction remains challenging. Current evaluat
arXiv:2506.07180v3 Announce Type: replace-cross Abstract: As video large language models (Video-LLMs) become increasingly integrated into real-world applications that demand grounded multimodal reason
arXiv:2604.02715v2 Announce Type: replace Abstract: Mixture-of-Experts (MoE) models have become a dominant paradigm for scaling large language models, but their rapidly growing parameter sizes introdu
arXiv:2604.28115v1 Announce Type: cross Abstract: Existing learning-based occupancy prediction methods rely on large-scale 3D annotations and generalize poorly across environments. We present FreeOcc,
arXiv:2604.27969v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) are increasingly used to translate visual artifacts into code, from UI mockups into HTML to scientific plots
arXiv:2505.17056v2 Announce Type: replace-cross Abstract: As large language models (LLMs) are increasingly integrated into educational tools, current evaluations on standardized tests predominantly fo
arXiv:2604.27906v1 Announce Type: new Abstract: Persistent AI memory is often reduced to a retrieval problem: store prior interactions as text, embed them, and ask the model to recover relevant contex
arXiv:2604.27557v1 Announce Type: new Abstract: Despite advances in dexterous hand manipulation, robotic hand design is still largely decoupled from task-driven evaluation and control, limiting system
arXiv:2604.27353v1 Announce Type: new Abstract: Gait recognition has emerged as a compelling biometric modality for surveillance and security applications, offering inherent advantages such as non-int
arXiv:2604.28193v1 Announce Type: new Abstract: Reconstructing 3D scenes from sparse, unposed images remains challenging under real-world conditions with varying illumination and transient occlusions.
arXiv:2604.27155v1 Announce Type: new Abstract: Model merging aims to combine multiple models into one without additional training. Naive parameter-space averaging can be fragile under architectural s
arXiv:2604.27918v1 Announce Type: new Abstract: Existing talking avatar methods typically adopt an image-to-video pipeline conditioned on a static reference image within the same scene as the target g
arXiv:2604.28144v1 Announce Type: new Abstract: Efficient exploration is a central problem in reinforcement learning and is often formalized as maximizing the entropy of the state-action occupancy mea
arXiv:2603.25385v2 Announce Type: replace-cross Abstract: Quantization techniques such as BitsAndBytes, AWQ, and GPTQ are widely used as a standard method in deploying large language models but often
@GoogleAIStudio And this sample project was created on Canvas in @GeminiApp. It’s a high-speed rhythm game where you tap to the beat and collect power-ups to remix the track. Watch as the numbers appe
@GoogleAIStudio @GeminiApp We can’t wait to see where your creativity takes you. Vibe code your countdown idea in @GoogleAIStudio or Canvas in @GeminiApp, then submit it here: http://goo.gle/codetheco
arXiv:2601.10702v2 Announce Type: replace-cross Abstract: Deploying large language models in long-horizon, goal-oriented interactions remains challenging because similar entities and facts recur under
arXiv:2503.12844v2 Announce Type: replace Abstract: For people affected by blindness and low vision (BLV), safe and independent navigation remains a major challenge, impacting over 2.2 billion individ
arXiv:2604.27470v1 Announce Type: new Abstract: Millions of clinicians use ChatGPT to support clinical care, but evaluations of the most common use cases in model-clinician conversations are limited.
arXiv:2604.28196v1 Announce Type: new Abstract: Driving world models serve as a pivotal technology for autonomous driving by simulating environmental dynamics. However, existing approaches predominant
Hi Singapore 🇸🇬, meet Codex 🩵 With Codex, ANYONE can build and create. We’re turning that energy up this May. We’re a diamond sponsor 💎 at @aiDotEngineer Singapore, at a bunch of events, and hosting s
arXiv:2604.04306v2 Announce Type: replace-cross Abstract: The increasing frequency and severity of climate related disasters have intensified the need for real time monitoring, early warning, and info
arXiv:2604.27790v1 Announce Type: cross Abstract: Generative AI is being increasingly integrated into web search for the convenience it provides users. In this work, we aim to understand how generativ
arXiv:2604.27206v1 Announce Type: new Abstract: Semantic segmentation in remote sensing is commonly addressed using classical deep learning architectures such as U-Net, which require a large number of
I have been testing DeepSeek-V4-Pro with the Pi coding agent. I am mindblown by how well it works out of the box. A few notes: I spent a few hours building an LLM wiki with an agent powered entirely b
arXiv:2604.27462v1 Announce Type: cross Abstract: Graph few-shot learning, which focuses on effectively learning from only a small number of labeled nodes to quickly adapt to new tasks, has garnered s
Tool: iNaturalist Sightings I wanted to see my iNaturalist observations - across two separate accounts - grouped by when they occurred. I'm camping this weekend so I built this entirely on my phone us
arXiv:2604.27249v1 Announce Type: cross Abstract: When instructed to underperform on multiple-choice evaluations, do language models engage with question content or fall back on positional shortcuts?
arXiv:2604.27763v1 Announce Type: new Abstract: The emergence of Large Language Models (LLMs) offers a transformative interface for Web3, yet existing benchmarks fail to capture the complexity of tran
arXiv:2604.27419v1 Announce Type: new Abstract: With the advancement of multimodal large language models (MLLMs) and coding agents, the website development has shifted from manual programming to agent
arXiv:2604.27335v1 Announce Type: new Abstract: Web filtering systems rely on accurate web content classification to block cyber threats, prevent data exfiltration, and ensure compliance. However, cla
arXiv:2604.27724v1 Announce Type: new Abstract: Medical retrieval-augmented generation (RAG) systems typically operate on text chunks extracted from biomedical literature, discarding the rich visual c
arXiv:2604.27981v1 Announce Type: cross Abstract: Multivariate time series forecasting plays a pivotal role in numerous real-world applications, including financial analysis, energy management, and tr
arXiv:2604.27343v1 Announce Type: new Abstract: Skin lesion classification is essential for early dermatological diagnosis, yet many existing computer-aided systems rely primarily on dermoscopic image
arXiv:2604.27366v1 Announce Type: new Abstract: Recent advances in vision language action (VLA) models have shown remarkable potential for autonomous driving by directly mapping multimodal inputs to c
arXiv:2504.14602v2 Announce Type: replace-cross Abstract: The natural interaction and control performance of lower limb rehabilitation robots are closely linked to biomechanical information from vario
arXiv:2604.27865v1 Announce Type: new Abstract: Language models are saturating benchmarks for procedural tasks with narrow objectives. But they are increasingly being deployed in long-horizon, non-sta
arXiv:2604.27962v1 Announce Type: new Abstract: Designing mechanical linkages involves combinatorial topology selection and continuous parameter fitting. We show that language models can systematicall
arXiv:2604.28192v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models have increasingly incorporated reasoning mechanisms for complex robotic manipulation. However, existing approaches
arXiv:2604.25711v2 Announce Type: replace-cross Abstract: Source code and its accompanying comments are complementary yet naturally aligned modalities-code encodes structural logic while comments capt
arXiv:2604.27295v1 Announce Type: new Abstract: Learning rate scheduling has evolved from the single global fixed rate of early SGD to sophisticated layer-wise adaptive strategies. We systematize this
arXiv:2604.27063v1 Announce Type: new Abstract: Continual learning agents with finite capacity must balance acquiring new knowledge with retaining the old. This requires controlled forgetting of knowl
arXiv:2604.27128v1 Announce Type: cross Abstract: Foundation-model pipelines for individual-level livestock monitoring -- combining open-vocabulary detection, promptable video segmentation, and self-s
arXiv:2604.27032v1 Announce Type: cross Abstract: Large Language Models (LLMs) have become an integral part of many real-world workflows. However, LLMs consume a lot of energy, which becomes a large c
Clem Delangue expresses commitment to advancing local AI models to compete with Anthropic's Claude Desktop and Claude Code offerings by year-end. The statement suggests focus on improving local AI cap
arXiv:2601.22228v2 Announce Type: replace-cross Abstract: We study whether vision-language models (VLMs) can solve relative camera pose estimation (RCPE) from image pairs, a direct test of multi-view
arXiv:2604.27487v1 Announce Type: new Abstract: Low-Rank Adaptation (LoRA), which leverages the insight that model updates typically reside in a low-dimensional space, has significantly improved the t