Knowledge catalogue
arXiv:2602.07399v2 Announce Type: replace Abstract: Vision--Language--Action (VLA) models bridge multimodal reasoning with physical control, but adapting them to new tasks with scarce demonstrations r
Gary Marcus discusses how alignment instructions in large language models often fail to work as intended, and argues that the emotional attachment some people develop toward LLMs can create additional
@GaryMarcus @hendrycks @Yoshua_Bengio We recently tested all of the major LLMs with tic-tac-toe, modified chess, and a novel game -- even the top models all failed: illegal moves, claiming a win when
arXiv:2511.10619v2 Announce Type: replace Abstract: The improving multi-armed bandits problem is a formal model for allocating effort under uncertainty, motivated by scenarios such as investing resear
arXiv:2605.21560v1 Announce Type: new Abstract: Deploying neural networks on microcontroller units (MCUs) is critical for edge intelligence but remains challenging due to tight memory, storage, and co
arXiv:2510.10129v2 Announce Type: replace Abstract: Retrieval-Augmented Generation (RAG) systems suffer from severe time-to-first-token (TTFT) bottlenecks due to long input sequences. Existing KV cach
arXiv:2605.21514v1 Announce Type: cross Abstract: Many complex systems can be modeled by temporal networks, whose organization often evolves through distinct structural phases. Detecting the change po
arXiv:2605.22749v1 Announce Type: new Abstract: Modern smart grids rely on dense measurement infrastructures, communication links, and intelligent field devices. Although this improves supervision and
arXiv:2605.22266v1 Announce Type: new Abstract: Federated learning enables collaborative training across distributed clients with heterogeneous data, but such heterogeneity often leads to unstable upd
arXiv:2510.11339v2 Announce Type: replace Abstract: Real-world graph typically evolve via a series of events, modeling dynamic interactions between objects across various domains. For dynamic graph le
arXiv:2605.21552v1 Announce Type: new Abstract: Confidence calibration for classification models is vital in safety-critical decision-making scenarios and has received extensive attention. General con
arXiv:2512.11587v2 Announce Type: replace Abstract: Even for the gradient descent (GD) method applied to neural network training, understanding its optimization dynamics, including convergence rate, i
arXiv:2605.21502v1 Announce Type: cross Abstract: Graph neural networks (GNNs) are increasingly used to model biological systems, yet the reliability of post-hoc explanation methods for recovering mea
arXiv:2605.21516v1 Announce Type: new Abstract: Harness engineering has emerged as an important inference-time technique for large language model (LLM) agents, aiming to improve long-term performance
The shift from on-premises computing to software as a service changed the technology model and forced information technology organizatios to modernize how it builds, buys and operates software. It als
arXiv:2605.21565v1 Announce Type: new Abstract: Multimodal Emotion Recognition in Conversations (MERC) is a crucial task for understanding human interactions, where multimodal approaches integrating l
arXiv:2506.21035v5 Announce Type: replace Abstract: Continual learning (CL) with large pre-trained models aims to incrementally acquire knowledge without catastrophic forgetting. Existing LoRA-based M
arXiv:2605.21762v1 Announce Type: new Abstract: Non-contrast computed tomography calcium scoring (CTCS) is a cost-effective imaging modality widely used to detect coronary artery calcifications. This
arXiv:2603.19310v3 Announce Type: replace Abstract: Reinforcement learning has emerged as a powerful paradigm for improving large language model (LLM) reasoning, where rollouts are sampled from the po
arXiv:2605.21783v1 Announce Type: new Abstract: Test-time adaptation (TTA) methods improve model performance under distribution shift but lack formal guarantees connecting shift magnitude to predictio
arXiv:2605.21851v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards has become the standard recipe for improving LLM reasoning, but the dominant algorithm GRPO assigns a sin
arXiv:2605.22338v1 Announce Type: new Abstract: Reconstructing continuous physical fields from sparse measurements is a central inverse problem, but data-driven generative models can produce states th
arXiv:2605.22731v1 Announce Type: new Abstract: Large language model post-training methods such as supervised fine-tuning (SFT), reinforcement learning (RL), and distillation are often analyzed throug
arXiv:2605.22561v1 Announce Type: new Abstract: Bayesian optimization (BO) is a widely used iterative black-box optimization method that utilizes Gaussian process (GP) surrogate models. In practice, B
arXiv:2605.22195v1 Announce Type: new Abstract: Graph of Thoughts (GoT), a generalized form of recent prompting paradigms for large language models (LLMs), has been shown to be useful for elaborate pr
arXiv:2605.22263v1 Announce Type: new Abstract: On-policy self-distillation (OPSD) is an emerging LLM post-training paradigm in which the model serves as its own teacher: conditioned on privileged inf
arXiv:2605.21490v1 Announce Type: new Abstract: We introduce the Temporal Contrastive Transformer (TCT), a representation learning framework designed to capture contextual temporal dynamics in sequenc
arXiv:2605.22496v1 Announce Type: new Abstract: Deep generative models offer a natural foundation for out-of-distribution (OOD) detection, yet prior work has shown that their assigned likelihoods are
arXiv:2511.14220v3 Announce Type: replace Abstract: Model-based reinforcement learning (RL) methods that leverage search are responsible for many milestone breakthroughs in RL. Sequential Monte Carlo
arXiv:2605.22257v1 Announce Type: new Abstract: Formal theorem provers based on large language models (LLMs) are highly sensitive to superficial variations in problem representation: semantically equi
arXiv:2605.22472v1 Announce Type: new Abstract: Winner-take-all (WTA) networks constitute a central circuit motif in cortical networks of the brain. In addition, WTA-like activations are abundant in m
arXiv:2605.21850v1 Announce Type: new Abstract: Recent development of agents has renewed demand for long-context reasoning capacity of LLMs. However, training LLMs for this capacity requires costly lo
arXiv:2605.22183v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models have emerged as a promising paradigm for generalist robotic manipulation. A common design in current architectures m
arXiv:2605.20734v1 Announce Type: cross Abstract: A large language model (LLM) agent that sends messages can leak data inside them. Destination allowlists and content scanners do not police whether an
Ollama has added MLX support for Qwen3.5 and Gemma 4 , with both MLX and NVFP4 quantization variants available for these models. There have been issues with broken Qwen3.6 NVFP4 generation on Ollama ,
arXiv:2605.22435v1 Announce Type: new Abstract: Hate speech and misinformation frequently co-occur online, amplifying prejudice and polarization. Given their scale, using Large Language Models (LLMs)
arXiv:2605.21932v1 Announce Type: new Abstract: Multi-Robot Task Allocation (MRTA) is a central challenge in decentralized multi-agent systems, where teams of robots must cooperatively assign and exec
arXiv:2605.21082v1 Announce Type: new Abstract: Large Language Model (LLM) based agents have demonstrated proficiency in multi-step interactions with graphical user interfaces (GUIs). While most resea
llama.cpp build b9276 introduces support for hybrid DNA tokenization with new pre-type dispatching and tokenizer implementations, alongside fixes for VRAM leaks in Multi-Token Prediction (MTP) models
arXiv:2605.21766v1 Announce Type: new Abstract: Being able to relight human performance is a fundamental task for post production and content creation. We present BodyReLux, a subject-specific video d
arXiv:2605.22411v1 Announce Type: new Abstract: Large language model (LLM) agents still struggle with long-term memory question answering, where answer-supporting evidence is often scattered across lo
arXiv:2510.17991v3 Announce Type: replace-cross Abstract: Flow Matching (FM) underpins many state-of-the-art generative models, yet recent results indicate that Transition Matching (TM) can achieve hi
arXiv:2605.21540v1 Announce Type: cross Abstract: The proliferation of large language models has introduced a new paradigm of synthetic political communication in which narratives may be generated, se
arXiv:2602.08028v1 Announce Type: cross Abstract: To address the instability of unguided reasoning paths in standard Chain-of-Thought prompting, recent methods guide large language models (LLMs) by fi
arXiv:2605.22051v1 Announce Type: new Abstract: Generating high-fidelity visual effects (VFX) typically demands massive datasets and prohibitive computational power due to the intricate coupling of sp
arXiv:2509.09215v2 Announce Type: replace Abstract: Large language models (LLMs)-empowered autonomous agents are transforming both digital and physical environments by enabling adaptive, multi-agent c
arXiv:2605.22208v1 Announce Type: new Abstract: Multimodal Large Language Model (MLLM)-driven image restoration agent demonstrates effectiveness in degradation coupling scenarios by flexibly selecting
arXiv:2605.22273v1 Announce Type: new Abstract: Vision-language models (VLMs) have achieved strong performance across diverse multimodal tasks, but their adversarial robustness in visible-infrared (VI
arXiv:2605.22057v1 Announce Type: new Abstract: Enterprise routers assign queries to expert agents, yet deployed profiles stay static while agents evolve (prompts, tools, models), and developers rarel
Great to see @CommonCrawl using and recommending @huggingface Buckets for large constantly evolving training datasets! If you have private models or datasets, try it and let us know what you think abo
arXiv:2605.22695v1 Announce Type: new Abstract: Viewpoint change invariance and action temporal consistency are critical aspects for the effective deployment of human action detection of untrimmed vid
arXiv:2605.22189v1 Announce Type: new Abstract: Occlusion-aware prediction remains a critical challenge in autonomous driving due to the inherent uncertainty of unobserved regions. Existing approaches
arXiv:2605.12321v2 Announce Type: replace Abstract: Large language models (LLMs) show strong potential for Intelligent Transportation Systems (ITS), particularly in tasks requiring situational reasoni
arXiv:2605.22269v1 Announce Type: new Abstract: Long streaming video QA remains challenging due to growing visual tokens and limited reasoning length of large language models (LLMs). KV-caching stores
Nicki Minaj template dropped… so I became the baddie. 🔥🚀 @Grok @Imagine Media Template Drop @SpaceX Starship Baddie (inspired by @NICKIMINAJ) Modeled by @SadieSupaDoge https://grok.com/imagine/templat
Open-source clinical AI is a niche that most days feels like shouting into a PubMed-shaped void. And yet. 5,000 of you are here, building OpenMed in the open with me. Thank you. More models, more data
arXiv:2605.22015v1 Announce Type: new Abstract: Diffusion Transformer (DiT) has emerged as a powerful model architecture for generating high-quality images and videos. In the case of video DiT, 3D Spa
arXiv:2605.22013v1 Announce Type: new Abstract: Understanding 3D point clouds through language remains a fundamental challenge in computer graphics and visual computing, due to the irregular structure
arXiv:2605.22231v1 Announce Type: new Abstract: We introduce a novel 3D hand pose estimator that can accurately recover the shape and pose of people's hands in a room from afar, typically from fixed c
arXiv:2605.22771v1 Announce Type: new Abstract: Large language models (LLMs) exhibit systematic political bias across a variety of sensitive contexts. We find that LLMs handle counterpart topics from