Knowledge catalogue
arXiv:2606.02775v1 Announce Type: new Abstract: The KV-cache is the right memory for datacenters but the wrong memory for robots. Datacenter inference batches many short requests and resets them, amor
arXiv:2606.02800v1 Announce Type: cross Abstract: We introduce Cosmos 3, a family of omnimodal world models designed to jointly process and generate language, image, video, audio, and action sequences
Google DeepMind released Gemma 4 12B, an open AI model that brings multimodal capabilities to everyday laptops by processing text, images, and audio natively without separate encoders. Small enough to
Harvey just published a study showing a hybrid setup, open source GLM 5.1 as primary worker, routing to Opus 4.7 only when needed beats pure Opus 4.7 on quality and costs less. This is the multi-model
arXiv:2511.21731v2 Announce Type: replace-cross Abstract: We present the results of cognitive tests on conceptual combinations, performed using specific Large Language Models (LLMs) as test subjects.
arXiv:2603.19551v2 Announce Type: replace-cross Abstract: We develop horizon-aware anytime-valid tests and confidence sequences for bounded means under a strict deadline N. Using the betting/e-process
At Microsoft's annual Build conference on Tuesday, the company announced a slew of new or expanded AI initiatives, including a super app, in-house reasoning models, a cybersecurity tool, and OpenClaw-
arXiv:2606.02964v1 Announce Type: cross Abstract: Large Language Model (LLM) inference relies on key-value (KV) caches to avoid redundant attention computation. While approximate KV cache retention te
Nice primer on post-training reasoning data. (bookmark it) This is one of the first primers to pull the scattered post-training reasoning-data literature into one place, synthesizing over 150 public s
arXiv:2606.03159v1 Announce Type: cross Abstract: As autonomous vehicle capabilities advance, the safe evaluation of driving policies in long-tail scenarios remains a critical bottleneck. In closed-lo
arXiv:2606.03743v1 Announce Type: new Abstract: While Large Language Models (LLMs) have shown strong performance in generating formal proofs, their outputs often remain less readable, modular, maintai
Routing and post-training open-source models won't only give you more accurate systems but also meaningfully faster and cheaper systems as most companies are currently learning (in addition to giving
arXiv:2606.03301v1 Announce Type: new Abstract: We introduce SagaQA, a long-form video benchmark for multi-hop reasoning over full-length TV series. Existing video reasoning benchmarks often emphasize
arXiv:2606.03026v1 Announce Type: cross Abstract: Spiking language models expose activation sparsity that dense Transformer runtimes do not directly exploit. This paper studies that property from a sy
Two bits here I think we're going to see a lot more: 1. custom harnesses / finetunes on smaller open source models to beat frontier models at specific skill or task 2. using frontier models as critics
arXiv:2606.03962v1 Announce Type: cross Abstract: Classical reinforcement learning (RL) typically seeks a deterministic policy that maximizes the expected sum of a scalar reward. Yet, modern applicati
Whether you use it for data preparation, real-time interactive queries, AI model training, or something entirely different, running Apache Spark at scale is demanding — you shouldn’t have to manage th
arXiv:2606.01861v1 Announce Type: new Abstract: Self-play, a type of training algorithm that enables a model to self-improve, has recently shown promising empirical results in the context of formal th
arXiv:2606.01975v1 Announce Type: new Abstract: We consider LLM-based algorithm development through a case study on contractionorder optimisation for tensor networks with OpenEvolve. We pay particular
arXiv:2606.00987v1 Announce Type: cross Abstract: Large Vision-Language Models (LVLMs) have shown strong visual understanding and language-guided grounding abilities, yet their capacity for multi-temp
At Google Cloud Next, we announced the preview of graph algorithms with Spanner Graph, bringing Google Research’s state-of-the-art graph mining capabilities natively to your database. These graph inte
arXiv:2606.01348v1 Announce Type: new Abstract: Charts are a primary medium for conveying quantitative and relational information, yet systematically evaluating chart parsing models remains difficult.
Cisco Systems Inc. today introduced a sweeping set of products and services designed to help enterprises manage, secure and automate increasingly complex information technology environments as artific
arXiv:2606.00235v1 Announce Type: cross Abstract: We argue that governance must transition from a normative discipline to an engineering discipline, and we develop a formal framework, inspired by the
arXiv:2512.13356v2 Announce Type: replace-cross Abstract: This paper proposes a reinforcement learning (RL) framework for controlling and stabilizing the Twin Rotor Aerodynamic System (TRAS) at specif
arXiv:2606.01212v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) systems are widely deployed and increasingly influential, but their reliance on external corpora exposes new secu
arXiv:2606.00759v1 Announce Type: new Abstract: Recent advances in artificial intelligence have expanded the focus from classical optimization to include equilibrium analysis in noncooperative games.
arXiv:2606.01072v1 Announce Type: cross Abstract: Imitation learning enables robots to learn how to execute tasks via observation. However, real-world environments like homes and offices are often sev
arXiv:2606.00857v1 Announce Type: cross Abstract: Accurate and reliable vehicle trajectory prediction is essential for safe autonomous driving. Recent studies have incorporated safety risk into trajec
arXiv:2606.01686v1 Announce Type: cross Abstract: As generative platforms such as Suno and Udio reach human-grade audio quality, the scope of AI's utility has expanded across the entire music producti
arXiv:2509.12263v3 Announce Type: replace Abstract: Large multimodal models (LMMs) encode physical laws observed during training, such as momentum conservation, as parametric knowledge. It allows LMMs
arXiv:2605.26102v2 Announce Type: replace Abstract: In this paper, we introduce InstructSAM, a unified and streamlined framework designed for multi-instance segmentation under arbitrary instructions.
arXiv:2606.00561v1 Announce Type: cross Abstract: Deep reinforcement learning (RL) offers a promising route to real-time power grid operation, yet large neural policies are costly to evaluate, hard to
arXiv:2606.01703v1 Announce Type: cross Abstract: We address the challenge of generating high-fidelity, long-form soundtracks that remain coherent across scene transitions. Existing AI music systems a
arXiv:2606.00049v1 Announce Type: cross Abstract: Large language models (LLMs) are widely recognised for their applications in natural language generation and are increasingly used for code generation
MiniMax-M3 combines 1M context, native multimodality, and MiniMax Sparse Attention. The next layer is serving it efficiently: KV-block-major sparse attention, paged MSA decode, optimized index scoring
arXiv:2606.01802v1 Announce Type: cross Abstract: MOSS-Audio is a unified audio-language model for speech, environmental sound, and music understanding, supporting audio captioning, time-aware questio
arXiv:2606.01241v1 Announce Type: new Abstract: Navigation and manipulation are fundamental capabilities of embodied intelligence, enabling robots to interpret natural language commands and interact p
arXiv:2606.01808v1 Announce Type: new Abstract: Accurate 3D geometric characterization of myocardial infarction (MI) is essential for building cardiac digital twins (CDTs) to precisely simulate infarc
arXiv:2606.00143v1 Announce Type: cross Abstract: Financial markets are inherently non-stationary, exhibiting frequent regime shifts and structural changes that render traditional Portfolio Management
arXiv:2606.00828v1 Announce Type: new Abstract: Vision-Language Models (VLMs) have shown strong visual understanding and are increasingly deployed in embodied AI systems, where reliable perception und
arXiv:2512.20806v3 Announce Type: replace Abstract: Ensuring the safety of language models (LMs) while maintaining their usefulness remains a critical challenge in AI alignment. Current approaches rel
arXiv:2510.09330v3 Announce Type: replace Abstract: Ensuring that large language models (LLMs) comply with safety requirements is a central challenge in AI deployment. Existing alignment approaches pr
arXiv:2503.24183v3 Announce Type: replace Abstract: The expansion of ride-sourcing services such as Uber and Lyft has reshaped urban transportation by offering flexible, on-demand mobility via mobile
arXiv:2606.00001v1 Announce Type: cross Abstract: This paper introduces Calligraphy Writing Score Representation (CWSR) and proposes Shu Dao as a framework that interprets East Asian calligraphy as a
arXiv:2503.05641v4 Announce Type: replace-cross Abstract: Combining existing pre-trained LLMs is a promising approach for diverse reasoning tasks. However, task-level expert selection is often too coa
arXiv:2606.00747v1 Announce Type: cross Abstract: For low-altitude Unmanned Aerial Vehicle (UAV) autonomy, 3D spatial understanding is not merely a perception objective, but the safety interface betwe
arXiv:2606.01020v1 Announce Type: new Abstract: Identifying logical fallacies in everyday discourse is challenging for many people. This challenge is amplified in the era of Large Language Models (LLM
This is actually one of the main advantages startups have over frontier labs, as long as there's a healthy spectrum of open-weight to closed-weight models on the cost-performance curve. Building a mod
This is disaster from Meta AI. Imagine being able to hack high profile accounts like White House, the U.S. Space Force, and Sephora simply by chatting with a support bot. why would an AI chatbot be al
arXiv:2606.01738v1 Announce Type: cross Abstract: Multi-turn jailbreak attacks pose a growing threat to LLMs by exploiting conversational dynamics such as gradual escalation and cross-turn coordinatio
arXiv:2606.00592v1 Announce Type: new Abstract: Effective visual communication stems from the harmony of multiple design principles, such as readability, contrast, alignment, overlap, and coherence, w
arXiv:2606.01810v1 Announce Type: new Abstract: Current benchmarks for embodied vision-language planning often favor linguistic next-token prediction over physically grounded next-state reasoning. Thi
arXiv:2606.01456v1 Announce Type: cross Abstract: Large language models are increasingly deployed as advisors whose objective is not aligned with the user's: recommenders optimize for engagement, sale
arXiv:2606.00704v1 Announce Type: new Abstract: Real-world image super-resolution (Real-ISR) requires balancing structural fidelity to degraded observations with realistic detail synthesis. However, e
We wrapped a live session on M3 yesterday with the @togethercompute team & our researchers @zpysky1125 and @HaohaiSun A few highlights 🧵 1. MSA (MiniMax Sparse Attention) is the star ⭐️. Unlike CSA/HC
arXiv:2606.01247v1 Announce Type: new Abstract: Humans can reproduce the viewpoint specified by a target image through active head and body motion, yet spatial intelligence in foundation models has la
arXiv:2606.02482v1 Announce Type: new Abstract: While video streaming understanding has made significant strides, real-world applications, such as live sports broadcasting, autonomous driving, and mul
arXiv:2602.01962v2 Announce Type: replace-cross Abstract: Off-policy learning methods seek to derive an optimal policy directly from a fixed dataset of prior interactions. This objective presents sign
arXiv:2605.31351v1 Announce Type: new Abstract: AI-based Visually Impaired Assistance (VIA) remains challenging, largely due to the high cost of human evaluation. The VLM-as-a-Judge paradigm may offer