Explainably Safe Reinforcement Learning
arXiv:2606.04634v1 Announce Type: new Abstract: Trust in a decision-making system requires both safety guarantees and the ability to interpret and understand its behavior. This is particularly importa
Knowledge catalogue
arXiv:2606.04634v1 Announce Type: new Abstract: Trust in a decision-making system requires both safety guarantees and the ability to interpret and understand its behavior. This is particularly importa
arXiv:2408.01382v3 Announce Type: replace Abstract: Originating in game theory, Shapley values are widely used for explaining a machine learning model's prediction by quantifying the contribution of e
arXiv:2606.04315v1 Announce Type: new Abstract: LLM agents accumulate histories that outgrow their context windows, motivating a growing literature on memory systems. Yet most existing designs are tun
arXiv:2606.04197v1 Announce Type: cross Abstract: How much should an LLM agent remember, and how should multi-agent systems be connected when trying to reach consensus? We show these two design choice
arXiv:2510.20042v3 Announce Type: replace Abstract: Generative image models produce striking visuals yet often misrepresent culture. Prior work has examined cultural bias mainly in text-to-image (T2I)
arXiv:2511.03304v2 Announce Type: replace-cross Abstract: With the on-going integration of machine learning systems into the everyday social life of millions the notion of fairness becomes an ever inc
arXiv:2606.05145v1 Announce Type: cross Abstract: When post-trained language models fail on reasoning problems, the common test-time-scaling response is to spend more compute on additional attempts, a
arXiv:2606.04751v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed as autonomous agents in scientific tasks. Yet whether these systems can effectively engage in for
arXiv:2606.04801v1 Announce Type: new Abstract: We present Flash Cubical, a highly efficient computation of cubical persistence on a V-filtration for 2D and 3D images over F_2. The implementation is b
arXiv:2606.05079v1 Announce Type: new Abstract: Function vectors (FVs) are task representations elicited during in-context learning that can be used to steer Large Language Models (LLMs). However, des
arXiv:2606.04338v1 Announce Type: new Abstract: Privacy-sensitive and distributed characteristics of multi-center medical data bring severe obstacles to centralized modeling for accurate early predict
Feels like a good time to resurface this one Mine and @jaswu_'s basic point: cheaper AI complicates the narrative for OpenAI and Anthropic when they eventually try to go public. Could also ripple acro
arXiv:2603.07445v2 Announce Type: replace Abstract: Large language models (LLMs) often require fine-tuning (FT) to perform well on downstream tasks, but FT can induce safety-alignment drift even when
Fidelity has announced that it is making the SpaceX IPO available to any customer with a retail brokerage account with 2,000 or more in the account (down from up to 500k before). 'SpaceX has decided t
Finally! the first eval ship from cog!!!!!!!!!! 👼🏼 To contextualize: @METR_Evals cap out at ~16 hours. Cog has private enterprise evals up to 100hrs, and is confident enough to put a financial guarant
Ramp Inc., a provider of cloud services that help companies manage their spending, today revealed it has raised 750 million in late-stage funding. ICONIQ, GIC and the Ontario Teachers’ Pension Plan jo
arXiv:2606.04282v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) are predominantly evaluated on free-form vision-language tasks such as visual question answering, captioning, a
arXiv:2606.04591v1 Announce Type: new Abstract: With the widespread adoption of multi-modal communication platforms, long-form dialogues interleaving text and images have become increasingly common. U
arXiv:2606.04065v1 Announce Type: cross Abstract: We study simultaneous alternating power iteration for fixed-order asymmetric rank-one spiked tensor models. Our main contribution is a finite-iteratio
arXiv:2603.19225v3 Announce Type: replace-cross Abstract: Real-world financial decision-making is a challenging problem that requires reasoning over heterogeneous signals, including company fundamenta
Fireworks was named to @Redpoint's InfraRed 100 which recognizes the companies building the foundation for the next wave of AI. We're just getting started. Come build with us: https://fireworks.ai/car
arXiv:2606.04670v1 Announce Type: cross Abstract: This paper presents a method of multivariate scattered data interpolation and approximation that produces optimal Lipschitz-continuous approximation,
At Cisco Systems Inc.‘s annual event, Cisco Live, this week in Las Vegas, it was no surprise that artificial intelligence was the top theme of the show and dominated most of the news and product innov
arXiv:2601.19449v2 Announce Type: replace Abstract: Graph neural networks (GNNs) are widely believed to excel at node representation learning through trainable neighborhood aggregations. We challenge
arXiv:2606.05067v1 Announce Type: new Abstract: The Deep Graph Generation's panorama spans two extremes: one-shot and sequential models. The former generates nodes and edges jointly, while the latter
arXiv:2606.04429v1 Announce Type: cross Abstract: A common heuristic used to explain the generalization of first-order gradient methods on non-convex neural networks is that 'flat interpolators genera
arXiv:2509.23385v5 Announce Type: replace-cross Abstract: Simulation-based inference (SBI) is transforming experimental sciences by enabling parameter estimation in complex non-linear models from simu
arXiv:2606.05101v1 Announce Type: cross Abstract: Audio deepfake detection (ADD) models are critical for countering the malicious use of text-to-speech (TTS) models. Evaluating and strengthening ADD m
arXiv:2606.04750v1 Announce Type: new Abstract: Instilling virtuous behavior in artificial intelligence has seen increasing interest. One of the techniques proposed is known as affinity-based reinforc
arXiv:2606.04307v1 Announce Type: new Abstract: Bayesian models with finite symmetry - mixture models with exchangeable components, structural identification with closely-spaced modes - define posteri
arXiv:2606.04986v1 Announce Type: new Abstract: Recent studies have explored Vision-Language Models (VLMs) for food analysis. However, most existing methods rely primarily on supervised fine-tuning (S
foom! Our internal data shows Claude is accelerating AI development—a possible path to recursive self-improvement, or AI autonomously building a more capable successor. It’s happening faster than we t
June’s forecast with GeForce NOW: 100% chance of gaming. GeForce NOW is lining up new adventures for the month, from big-name blockbusters to quirky indies ready for the spotlight. Members can dive in
arXiv:2603.24747v2 Announce Type: replace Abstract: The emergence of large language model agents capable of invoking external tools has created urgent need for formal verification of agent protocols.
Tom Dotan / Newcomer: Founders Fund launches a TV-style game show featuring A-list founders and investors, including Sam Altman and Palmer Luckey, playing a game of Mafia — Do people want to watch the
arXiv:2606.04990v1 Announce Type: cross Abstract: Large language model (LLM)-based agents increasingly solve complex tasks by interacting with external tools, retrieval systems, memory modules, enviro
From idea to live store, in minutes. 🛍️ Tomorrow on the Friday Showcase: → Replit's new Shopify partnership, with @Davidizek . Tell Replit Agent what you want to sell and it builds your storefront, cr
arXiv:2107.01629v3 Announce Type: replace-cross Abstract: Livestreaming has evolved into a thriving industry where creators can directly monetize and engage with their audiences and followers. In prac
arXiv:2503.06525v2 Announce Type: replace-cross Abstract: Analyzing student behavior in educational scenarios is crucial for enhancing teaching quality and student engagement. Existing AI-based models
arXiv:2606.04967v1 Announce Type: cross Abstract: AI tools for programming are no longer just autocomplete or chat assistants: they organize themselves as development frameworks, with process, roles,
arXiv:2606.04381v1 Announce Type: cross Abstract: Recent large language models (LLMs) often appear to exhibit spatial reasoning ability; however, this capability is largely symbolic, arising from patt
arXiv:2606.04275v1 Announce Type: cross Abstract: We present a novel theoretical framework for deep reinforcement learning (RL) in continuous environments by modeling the problem as a continuous-time
arXiv:2606.04329v1 Announce Type: cross Abstract: Memory is a core component of AI agents, enabling them to accumulate knowledge across interactions and improve performance. However, persistent memory
arXiv:2606.05002v1 Announce Type: new Abstract: LLM-based multi-agent systems are increasingly used for strategic decision-making tasks. In such settings, performance depends not only on individual mo
arXiv:2606.05142v1 Announce Type: cross Abstract: Recent developments in multi-view image editing with generative models have brought us a step closer toward general 3D content generation and customiz
arXiv:2606.04525v1 Announce Type: new Abstract: Progress in genomic foundation models is difficult to assess due to fragmented benchmarks, incompatible evaluation protocols, and task-specific reportin
Artificial intelligence startup Generalist AI Inc., a startup building embodied robotics intelligence, said today it has raised 400 million in new funding, bringing the company’s valuation to 2 billio
arXiv:2606.04328v1 Announce Type: cross Abstract: Future wireless networks demand rapid adaptation to highly heterogeneous environments and dynamic task configurations, necessitating a shift from conv
arXiv:2606.05015v1 Announce Type: new Abstract: World models, learned generative models that predict how an environment evolves, have become a promising tool for sample-efficient robot learning. Yet h
arXiv:2606.05138v1 Announce Type: new Abstract: Generating realistic financial time series is challenging as training data is often limited to a single historical path. With such scarce data, overfitt
arXiv:2603.22121v2 Announce Type: replace-cross Abstract: Video Corpus Moment Retrieval (VCMR) aims to retrieve both the correct video and its temporal segment corresponding to a natural-language quer
arXiv:2606.04922v1 Announce Type: cross Abstract: Current prompt-based and adapter-based tuning of vision-language models (VLMs) is attractive for medical imaging, where clinical data sensitivity favo
arXiv:2601.06196v3 Announce Type: replace-cross Abstract: Large language models (LLMs) frequently generate factually incorrect or unsupported content, commonly referred to as hallucinations. Prior wor
arXiv:2606.05124v1 Announce Type: cross Abstract: After the success of 3D Gaussian Splatting (3DGS) for novel view synthesis, many works have explored how to also use it for geometric surface represen
arXiv:2501.09876v3 Announce Type: replace-cross Abstract: Generative modeling aims to generate new data samples that resemble a given dataset. When using diffusion models for this task, one of the mai
arXiv:2606.04385v1 Announce Type: new Abstract: Foundation models have driven rapid progress in computer vision, yet the two dominant paradigms, vision-language foundation models (VLMs) and vision-onl
arXiv:2606.04516v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) significantly advances LLM reasoning, yet it faces a dilemma: standard supervised scaling is thr
arXiv:2505.24528v3 Announce Type: replace Abstract: Foundation Models (FMs) are large-scale, pre-trained artificial intelligence (AI) systems that have revolutionized natural language processing and c
arXiv:2601.05633v2 Announce Type: replace Abstract: Recent LLMs excel at formal tasks such as mathematical reasoning and code generation, but still struggle with broader abilities such as planning, cr
arXiv:2606.04486v1 Announce Type: cross Abstract: Watermarking methods for language models have been studied extensively in the autoregressive setting, where tokens are generated sequentially. These w