Knowledge catalogue
arXiv:2605.07550v1 Announce Type: new Abstract: 3D vision systems are fundamentally constrained by their reliance on visual overlap: reconstruction methods require it for geometric alignment, while ge
arXiv:2601.04731v2 Announce Type: replace Abstract: Current critic-free RL methods for large reasoning models suffer from severe inefficiency when training on positive homogeneous prompts (where all r
arXiv:2602.00513v3 Announce Type: replace Abstract: Cyber threat intelligence (CTI) analysts routinely convert noisy, unstructured security artifacts into standardized, automation-ready representation
arXiv:2603.09652v3 Announce Type: replace Abstract: With the rapid advancement of Large Language Models (LLMs) in code generation, human-AI interaction is evolving from static text responses to dynami
arXiv:2605.05927v2 Announce Type: replace Abstract: Speech large language models (SLMs) are typically built from text large language model (TLM) checkpoints, yet they still suffer from a substantial m
arXiv:2605.06384v2 Announce Type: replace-cross Abstract: We show that the MinMax algebra provides a form of recurrence that is expressively powerful, efficiently implementable, and most importantly i
arXiv:2605.07269v1 Announce Type: new Abstract: Indirect prompt injection remains a persistent weakness in retrieval-augmented and tool-using LLM systems, and the problem becomes harder to characteris
arXiv:2605.07363v1 Announce Type: cross Abstract: DeepSeek Sparse Attention (DSA) sets the state of the art for fine-grained inference-time sparse attention by introducing a learned token-wise indexer
arXiv:2605.06897v1 Announce Type: cross Abstract: The rise of Internet of Things (IoT) devices in the physical world necessitates voice-based interfaces capable of handling complex user experiences. W
MIT and IBM have renewed their long-standing research collaboration, focusing on advancing computing research and technology development. The partnership brings together expertise from both institutio
arXiv:2605.06895v1 Announce Type: new Abstract: How can we make models robust to even imperfect human feedback? In reinforcement learning from human feedback (RLHF), human preferences over model outpu
arXiv:2602.04447v2 Announce Type: replace-cross Abstract: Modern chess language models are dense transformers trained on millions of games played by thousands of high-rated individuals. However, these
arXiv:2603.24946v2 Announce Type: replace-cross Abstract: Large language models (LLMs) have shown strong performance on automated software engineering tasks, yet existing benchmarks focus primarily on
arXiv:2605.08050v1 Announce Type: new Abstract: Talking-head generation requires joint modeling of identity, head pose, facial expression, and mouth dynamics. Existing methods typically address only a
arXiv:2602.07026v2 Announce Type: replace-cross Abstract: Despite the success of multimodal contrastive learning in aligning visual and linguistic representations, a persistent geometric anomaly, the
arXiv:2605.07520v1 Announce Type: new Abstract: Differentiable planning enables gradient-based optimization of decision-making problems by leveraging differentiable models of system dynamics. However,
arXiv:2605.07075v1 Announce Type: new Abstract: The open-source model ecosystem now contains hundreds of thousands of pretrained models, yet picking the best model for a new dataset is increasingly in
arXiv:2605.06709v1 Announce Type: new Abstract: This paper addresses PDE-based control for flexible multibody robotic systems, presenting a subsystem-based framework for serial manipulators with arbit
arXiv:2605.07233v1 Announce Type: new Abstract: This work focuses on the question of learning from a large number of devices with each device holding only a single sample of data. Several real-world a
arXiv:2605.06672v1 Announce Type: new Abstract: Chain-of-thought (CoT) reasoning and reasoning-tuned models such as DeepSeek-R1 are commonly assumed to reduce shallow heuristic biases by thinking care
arXiv:2605.07370v1 Announce Type: cross Abstract: V2X can warn an autonomous vehicle about hazards beyond line-of-sight, but it also brings uncertainty: messages may be delayed, dropped, or even forge
arXiv:2603.18856v2 Announce Type: replace-cross Abstract: Recent video reasoning models increasingly produce spatio-temporal evidence chains that localize objects at specific timestamps. While these t
arXiv:2605.08024v1 Announce Type: new Abstract: Learning-to-defer (L2D) can make glaucoma screening safer by routing difficult/uncertain cases to humans, yet standard formulations overlook expert avai
arXiv:2605.07635v1 Announce Type: new Abstract: Automated assistants for Grammatical Error Correction are now embedded in educational platforms serving millions of learners, yet three critical gaps re
arXiv:2601.07247v2 Announce Type: replace-cross Abstract: Learning models that can handle distribution shifts is a key challenge in domain generalization. Invariance learning, an approach that focuses
arXiv:2605.07537v1 Announce Type: new Abstract: Partially Observable Markov Decision Processes (POMDPs) are systems in which one agent interacts with a stochastic environment, and receives only partia
arXiv:2603.16876v2 Announce Type: replace-cross Abstract: We propose MARL-Rad, a multi-modal multi-agent reinforcement learning framework for radiology report generation that trains the entire agentic
arXiv:2605.06951v1 Announce Type: new Abstract: Constraint inference is widely considered essential to align reinforcement learning agents with safety boundaries and operational guidelines by observin
arXiv:2605.06864v1 Announce Type: new Abstract: We study multi-objective multi-agent multi-armed bandits (MO-MA-MAB) under stochastic rewards, where agents observe heterogeneous reward vectors and com
arXiv:2106.09636v2 Announce Type: replace Abstract: Deep learning methods are powerful tools in classifying multivariate time series data. Despite their high performance, these methods are hard to int
arXiv:2411.16748v5 Announce Type: replace Abstract: Long-duration talking video synthesis faces enduring challenges in achieving high video quality, portrait consistency, temporal coherence, and compu
arXiv:2602.05359v2 Announce Type: replace Abstract: The advancement of multimodal large language models (MLLMs) has enabled impressive perception capabilities. However, their reasoning process often r
arXiv:2605.07561v1 Announce Type: new Abstract: Pathological complete response (pCR) is a key prognostic factor in breast cancer patients undergoing neoadjuvant therapy, strongly associated with long-
arXiv:2605.06699v1 Announce Type: cross Abstract: We propose a multimodal latent diffusion model that jointly synthesizes volumetric magnetic resonance imaging (MRI) and tabular clinical data within a
arXiv:2605.06940v1 Announce Type: new Abstract: Annotation automation via Large Language Models (LLMs) is the core approach for scaling NLP datasets; however, LLM behavior with respect to closed-set i
arXiv:2309.01751v3 Announce Type: replace-cross Abstract: The increasing frequency and severity of wildfires necessitates advanced methods for effective surveillance and management, as traditional gro
arXiv:2604.04891v2 Announce Type: replace-cross Abstract: Gradient normalization stabilizes deep-learning optimization, and spectral normalizations are especially natural for matrix-shaped parameter b
arXiv:2605.06884v1 Announce Type: cross Abstract: Most first-order optimizers treat matrix-valued parameters as vectors, ignoring the intrinsic geometry of hidden-layer weights in neural networks. Muo
Rachel Metz / Bloomberg: Musk v. Altman: Ilya Sutskever testifies that his OpenAI stake is worth ~7B and he had concerns about Altman for a year before Altman's brief ouster as CEO — OpenAI co-founder
CNBC: Musk v. Altman: Satya Nadella says Elon Musk never contacted him with concerns that Microsoft's investments in OpenAI violated any special terms or commitments — Microsoft CEO Satya Nadella took
My @aiDotEngineer talk is live: 'On-device Intelligence using MLX' 🎥 Huge thanks to @swyx and the team for having me — hands down the best tech event I've been to. And a shoutout to the community ship
Nous Research is recruiting a UI/UX designer for an immediate opening, offering competitive compensation and other benefits. The job posting was shared on X (formerly Twitter) and appears to have been
My latest interview with @Capgemini, sharing my view on AI sovereignty: For countries, the clearest error is believing that the only two choices are to accept an American model or to build one from sc
My Mac had less available memory than I expected, turned out the 'claude' Claude Code processes on this machine (running in various terminal windows) were consuming ~30GB on their own! The largest one
Swyx shared a talk that was presented at an AI Engineer event, where the speaker discussed their research and the future direction of BFL ML, with credit given to Swyx for the invitation. The full tal
Mythos identified one genuine vulnerability in cURL while also reporting three false positives and one issue classified as a bug during their security analysis. The post references cURL's founder or l
@NameInteger @GaryMarcus @geoffreyhinton Hinton's argument was about encoding: LLMs don't encode text as text, but as weighted matrices. It makes no difference. Memorised data is memorised data no mat
arXiv:2605.06846v1 Announce Type: cross Abstract: Recent work identifies secret loyalties as a distinct threat from standard backdoors. A secret loyalty causes a model to covertly advance the interest
arXiv:2605.06317v2 Announce Type: replace-cross Abstract: Existing Vision-Language Navigation (VLN) methods typically adopt an egocentric, step-by-step paradigm, which struggles with error accumulatio
arXiv:2603.08256v2 Announce Type: replace Abstract: Word sense plausibility rating requires predicting the human-perceived plausibility of a given word sense on a 1-5 scale in the context of short nar
arXiv:2512.12116v3 Announce Type: replace Abstract: Learned time-series models, whether continuous or discrete, are widely used for forecasting the states of dynamical systems but suffer from error ac
arXiv:2601.19831v2 Announce Type: replace-cross Abstract: Neural scaling laws predict how language model performance improves with increased training inputs. While aggregate metrics like validation lo
arXiv:2605.07792v1 Announce Type: cross Abstract: Neural operators (NOs) are designed to learn maps between infinite-dimensional function spaces. We propose a novel reframing of their use. By introduc
arXiv:2605.07140v1 Announce Type: cross Abstract: Skeleton-based human activity recognition has achieved strong empirical performance, yet most existing models remain black boxes and difficult to inte
arXiv:2605.07166v1 Announce Type: new Abstract: Imitation learning is widely used for learning to act in complex environments. While pure neural-based methods handle high dimensional data effectively,
New episode of the @chain_ofthought Podcast with @jerryjliu0 of @llama_index coming soon! https://chainofthought.show/ We just wrapped recording with @jerryjliu0 of @llama_index 👀 His thesis: the AI f
Simon Willison discovered how to use an LLM command-line interface tool in Unix shebang lines, enabling the creation of executable scripts written in English or natural language. This technique allows
News organizations are increasingly blocking the Wayback Machine even as their reporters still depend on it 📰 In PRESERVING THE WEB IN THE AGE OF AI, Mark Graham, Director of the Wayback Machine at th
arXiv:2503.04638v3 Announce Type: replace Abstract: Most Continual Learning (CL) methods maintain performance on earlier tasks by storing exemplars in a replay buffer, introducing memory overhead that
arXiv:2605.07794v1 Announce Type: new Abstract: World Action Models (WAMs) are an emerging family of policies that tie robot action generation to future-observation modeling. In this work, we focus on