Robust Promptable Video Object Segmentation
arXiv:2605.12006v1 Announce Type: new Abstract: The performance of promptable video object segmentation (PVOS) models substantially degrades under input corruptions, which prevents PVOS deployment in
Knowledge catalogue
arXiv:2605.12006v1 Announce Type: new Abstract: The performance of promptable video object segmentation (PVOS) models substantially degrades under input corruptions, which prevents PVOS deployment in
arXiv:2605.11800v1 Announce Type: cross Abstract: Large language models (LLMs) with mixture-of-experts (MoE) architectures achieve remarkable scalability by sparsely activating a subset of experts per
arXiv:2605.12476v1 Announce Type: cross Abstract: Sparse Mixture-of-Experts (SMoE) models enable scaling language models efficiently, but training them remains challenging, as routing can collapse ont
arXiv:2605.12386v1 Announce Type: new Abstract: Robotic manipulation is typically evaluated by task success, but successful completion does not guarantee safe execution. Many safety failures are tempo
arXiv:2605.12022v1 Announce Type: new Abstract: Large Language Models (LLMs) achieve strong performance on standard knowledge evaluation benchmarks, yet recent work shows that their knowledge capabili
arXiv:2605.12049v1 Announce Type: new Abstract: Cortical neurons are complex, multi-timescale processors wired into recurrent circuits, shaped by long evolutionary pressure under stringent biological
arXiv:2605.11022v1 Announce Type: cross Abstract: Identifying operons is a fundamental step in understanding prokaryotic gene regulation, as classifying genes into operons supports the reconstruction
arXiv:2605.12464v1 Announce Type: new Abstract: Quantization has emerged as a standard technique for accelerating inference for generative models by enabling faster low-precision computations and redu
arXiv:2605.11817v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models have shown remarkable promise in robotics manipulation, yet their high computational cost hinders real-time deploy
arXiv:2605.12208v1 Announce Type: cross Abstract: Approximate Bayesian inference typically revolves around computing the posterior parameter distribution. In practice, however, the main object of inte
arXiv:2605.12389v1 Announce Type: new Abstract: Segmenting small and sparse structures in large-scale images is fundamentally constrained by voxel-level, lattice-bound computation and extreme class im
arXiv:2605.11680v1 Announce Type: new Abstract: We introduce ShapeCodeBench, a synthetic benchmark for perception-to-program reconstruction: given a rendered raster image, a model must emit an executa
arXiv:2605.12015v1 Announce Type: cross Abstract: Reusable skills are becoming a common interface for extending large language model agents, packaging procedural guidance with access to files, tools,
arXiv:2605.11689v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) architectures have become standard in large language models, yet many of their core design choices - expert count, granularit
so we built psql_bm25s. exact BM25 retrieval. native Postgres access method. ~23x faster than pg_search on the standard benchmark. retrieval stops being a budget item. the harness stops rationing. the
arXiv:2602.13267v3 Announce Type: replace Abstract: Regression-based LiDAR relocalization has recently emerged as a promising solution for high-precision positioning in GNSS-denied environments. Howev
arXiv:2605.12466v1 Announce Type: cross Abstract: Looped Transformers offer a promising alternative to purely feed-forward computation by iteratively refining latent representations, improving languag
Alex Heath / Sources: Sources: Google plans to announce a new Gemini model at its I/O conference next week; the model will land roughly in the class of GPT-5.5, but short of Mythos — Sources say that
Bloomberg: Sources: Mistral has been developing a cybersecurity-focused AI model and held discussions about it with European banks, which don't have access to Mythos — French artificial intelligence s
arXiv:2406.12017v2 Announce Type: replace-cross Abstract: Sparsity-constrained optimization underlies many problems in signal processing, statistics, and machine learning. State-of-the-art hard-thresh
arXiv:2605.11394v1 Announce Type: cross Abstract: We present the Spatial Adapter, a parameter-efficient post-hoc layer that equips any frozen first-stage predictor with a structured spatial representa
arXiv:2605.11919v1 Announce Type: new Abstract: Federated graph learning (FGL) enables collaborative training on graph data across multiple clients. As graph data increasingly contain multimodal node
arXiv:2602.15620v4 Announce Type: replace Abstract: Reinforcement Learning (RL) has significantly improved large language model reasoning, but existing RL fine-tuning methods rely heavily on heuristic
Starship launch next week! Starship’s twelfth flight test will debut the next generation Starship and Super Heavy vehicles, powered by the next evolution of the Raptor engine and launching from a newl
Starting June 15, paid Claude plans can claim a dedicated monthly credit for programmatic usage. The credit covers usage of: - Claude Agent SDK - claude -p - Claude Code GitHub Actions - Third-party a
arXiv:2605.11922v1 Announce Type: cross Abstract: Existing code reasoning methods primarily supervise final code outputs, ignoring intermediate states, often leading to reward hacking where correct an
arXiv:2605.11483v1 Announce Type: new Abstract: While large language models excel at factual adaptation, their ability to internalize nuanced philosophical frameworks under severe data constraints rem
arXiv:2605.12135v1 Announce Type: cross Abstract: We present STRUM (Spectral Transcription and Rhythm Understanding Model), an audio-to-chart pipeline that converts raw recordings into playable Clone
arXiv:2605.11246v1 Announce Type: new Abstract: Offline black-box optimization aims to discover novel designs with high property scores using only a static dataset, a task fundamentally challenged by
arXiv:2605.12179v1 Announce Type: new Abstract: Recent advancements in video-audio joint generation have achieved remarkable success in semantic correspondence. However, achieving precise temporal syn
arXiv:2605.12290v1 Announce Type: new Abstract: Language models are instruction-tuned to refuse harmful requests, but the mechanisms underlying this behavior remain poorly understood. Popular steering
arXiv:2605.11572v1 Announce Type: new Abstract: Audio-visual understanding requires effective alignment between heterogeneous modalities, yet cross-modal correspondence remains challenging when tempor
arXiv:2605.11374v1 Announce Type: cross Abstract: Test-time compute is widely believed to benefit only large reasoning models. We show it also helps small embedding models. Most modern embedding check
The future of AI is agent-native. Excited to kick off this journey together with Hermes Agent and the @NousResearch community. Qwen 3.6 Plus is now FREE for a limited time on Nous Portal — give it a t
Databases have introduced new AI-powered SQL functions which take natural language instructions as input and are evaluated using LLMs. They leverage the power of LLMs to answer new kinds of queries: W
arXiv:2605.11157v1 Announce Type: cross Abstract: We study proportional representation in the temporal voting model, where collective decisions are made repeatedly over time over a fixed horizon. Prio
arXiv:2605.11205v1 Announce Type: new Abstract: Benchmark evaluation across AI and safety-critical domains overwhelmingly relies on simple averaging. We demonstrate that this practice produces substan
The UK’s state AI Security iIstitute findings: 1) Mythos is a big gain in cyber capabilities. But so is GPT-5.5 2) It is hard to establish an upper bound on Mythos/GPT-5.5, which appear to be limited
This is misleading. This policy redefines the term 'interactive' to mean 'using an Anthropic front-end'. If you use `claude -p` or Agent SDK to do something interactively, it now uses credits, not you
This jackass fought hard to remain NASA Administrator. SCOOP: I obtained a pitch deck in which the entity that paid for Transportation Sec’y Duffy’s new reality show outlined different partner levels
arXiv:2605.11574v1 Announce Type: new Abstract: The literature on how large language models handle conflict between their training knowledge and a contradicting document presents a persistent empirica
Aisha Malik / TechCrunch: TikTok launches TikTok GO in the US for users to book hotels, attractions, and experiences directly in the app, partnering with Booking.com, Expedia, and others — TikTok anno
arXiv:2605.11473v1 Announce Type: cross Abstract: Soft Actor-Critic (SAC) and its variants dominate Multi-Task Reinforcement Learning (MTRL) due to their off-policy sample efficiency, while on-policy
arXiv:2605.12391v1 Announce Type: cross Abstract: We present a novel method for extracting moving objects from TESS data using machine learning. Our approach uses two stacked 3D U-Nets with skip conne
arXiv:2605.11735v1 Announce Type: new Abstract: The efficient operation of modern cellular networks hinges on the accurate analysis of spatio-temporal traffic data. Mastering these patterns is essenti
arXiv:2605.12237v1 Announce Type: new Abstract: Vision-Language Models (VLMs) increasingly operate on ultra-high-resolution (UHR) Earth observation imagery, yet they remain vulnerable to a severe scal
arXiv:2511.18152v3 Announce Type: replace Abstract: Deep unfolding networks (DUNs) combine the interpretability of model-based methods with the learning ability of deep networks, yet remain limited fo
arXiv:2605.11634v1 Announce Type: new Abstract: Although Vision Language Models (VLMs) have seen tremendous progress across all kinds of use cases, they still fall behind in answering questions regard
arXiv:2605.11782v1 Announce Type: new Abstract: Visual impairment affects hundreds of millions of people worldwide, severely limiting their ability to navigate urban environments safely and independen
arXiv:2605.11334v1 Announce Type: cross Abstract: LLM-as-Judge systems are widely deployed for automated evaluation, yet practitioners lack reliable methods to know when a judge's verdict should be tr
arXiv:2605.11864v1 Announce Type: cross Abstract: Listwise reranking is a key yet computationally expensive component in vision-centric retrieval and multimodal retrieval-augmented generation (M-RAG)
arXiv:2603.11383v2 Announce Type: replace Abstract: Teleoperation of low-cost robotic manipulators remains challenging due to the difficulty of retargeting human hand motion to robot joint commands. W
arXiv:2605.11307v1 Announce Type: new Abstract: Image-to-code generation tests whether a vision-language model (VLM) can recover the structure of an image enough to express it as executable code. Exis
We built SmithDB: the database purpose built for agent observability workloads that now powers many parts of LangSmith. Agent observability presents a challenging data problem. Agent traces can contai
🎉 We published a new AI safety study: shopping agents fall for whimsical attacks and lose money. A whimsical attack is an absurd scenario a human would never try on another human. In one run, GPT-5.1
arXiv:2605.11654v1 Announce Type: new Abstract: Cross-view geo-localization (CVGL), which matches an oblique drone view to a geo-referenced satellite tile, has emerged as a key alternative for autonom
arXiv:2605.11963v1 Announce Type: new Abstract: This paper examines what it means for a medical AI system to be right by grounding the question in a specific clinical context: the automatic classifica
When you want to move from single agent SQLite on something like QMD, PostgreSQL is a great choice for multi agent and production quality, but not as snappy. So we made it much more snappy with BM25 &
💡 Why did @togethercompute choose NVIDIA Blackwell to serve DeepSeek-V4? Because NVIDIA Blackwell is built for the bottlenecks that matter most in long-context inference: → KV-cache pressure during de
arXiv:2605.11696v1 Announce Type: new Abstract: Recent single-image relighting methods, powered by advanced generative models, have achieved impressive photorealism on synthetic benchmarks. However, t