Knowledge catalogue
arXiv:2505.07765v3 Announce Type: replace-cross Abstract: We propose a novel framework for solving nonlinear PDEs using sparse radial basis function (RBF) networks. Sparsity-promoting regularization i
Some notes on talkie, a new 'vintage language model' from a team including Alec Radford (yes, that Alec Radford) 'trained on 260B tokens of historical pre-1931 English text' https://simonwillison.net/
some thoughts on recent seed price movements, but nothing particularly new for ppl in the vc discourse seed rounds have always been option purchases for large firms, but the amount of $$ being thrown
Pinecone announced an upcoming product launch scheduled for the week of May 4th, with the teaser 'Something's coming.' The post was shared on X (formerly Twitter) but specific details about what produ
Erin Woo / The Information: Source: Google signed a deal allowing the US DOD to use Google's AI for “any lawful government purpose”; Google says the agreement amends an existing contract — Google and
Mark Gurman / Bloomberg: Sources: Apple plans an AI overhaul for photo editing in iOS 27, including using on-device AI models to extend, enhance, and reframe photos — Apple Inc. is planning a major ov
Financial Times: Sources: Goldman Sachs stopped its bankers in Hong Kong from using Anthropic's models; Anthropic says its models were never officially “supported” in Hong Kong — Employees were unable
Katrina Manson / Bloomberg: Sources: Google dropped out of a 100M Pentagon challenge to create tech for voice-controlled, autonomous drone swarms, following an internal ethics review — Google abruptly
Bloomberg: Sources: Polymarket has discussed lifting the prohibition on US-based customers with the CFTC, as it seeks to bring its main exchange back to the US — Polymarket is taking steps to try to b
Karen Freifeld / Reuters: Sources: the US Commerce Department last week ordered multiple chip equipment companies to halt some shipments to China's second-largest chipmaker, Hua Hong — The U.S. Depart
Nellie Peyton / Reuters: South Africa withdraws its first draft national AI policy after revelations that it contained fictitious sources that appeared to have been AI-generated — South Africa has wit
South Korean reporter after experiencing @Tesla FSD (Supervised) in the country for the first time: 'It flawlessly performed all tasks, including obeying traffic signals, staying in lanes, adhering to
arXiv:2511.17092v4 Announce Type: replace Abstract: Articulated objects are ubiquitous in daily environments, and their 3D reconstruction holds great significance across various fields. However, exist
arXiv:2512.12469v3 Announce Type: replace Abstract: We introduce Sparse Concept Anchoring, a method that biases latent space to position a targeted subset of concepts while allowing others to self-org
arXiv:2604.23551v1 Announce Type: new Abstract: Reconstructing realistic underwater scenes from underwater video remains a meaningful yet challenging task in the multimedia domain. The inherent spatio
arXiv:2511.17411v2 Announce Type: replace-cross Abstract: Robotic Foundation Models (RFMs) hold great promise as generalist, end-to-end systems for robot control. Yet their ability to generalize acros
arXiv:2604.24729v1 Announce Type: new Abstract: Specification-guided reinforcement learning (RL) provides a principled framework for encoding complex, temporally extended tasks using formal specificat
arXiv:2604.23241v1 Announce Type: cross Abstract: Human-imitated speech poses a greater challenge than AI-generated speech for both human listeners and automatic detection systems. Unlike AI-generated
arXiv:2604.24199v1 Announce Type: cross Abstract: We propose Speech Enhancement based on Drifting Models (DriftSE), a novel generative framework that formulates denoising as an equilibrium problem. Ra
arXiv:2502.12672v4 Announce Type: replace-cross Abstract: Fine-tuning speech representation models can enhance performance on specific tasks but often compromises their cross-task generalization abili
arXiv:2604.23432v1 Announce Type: cross Abstract: Reliable depth estimation from spherical images is crucial for 360{eg} vision in robotic navigation and immersive scene understanding. However, the on
arXiv:2604.24449v1 Announce Type: cross Abstract: Training machine learning models for robotic tactile sensing requires vast amounts of data, yet obtaining realistic interaction data remains a challen
Ashley Carman / Bloomberg: Spotify reports Q1 revenue up 8% YoY to €4.5B, MAUs up 12% to 761M, above 759M est., and forecasts Q2 operating income below est.; SPOT falls 10%+ pre-market — Spotify Techn
arXiv:2401.07669v2 Announce Type: replace Abstract: Adapting CLIP for videos has gained popularity due to its semantic and rich representation. While CLIP is a good starting point, it typically underg
arXiv:2505.16637v4 Announce Type: replace-cross Abstract: Large language models (LLMs) have recently demonstrated remarkable capabilities in machine translation (MT). However, most advanced MT-specifi
arXiv:2604.24003v1 Announce Type: new Abstract: Large language models (LLMs) achieve strong reasoning performance by allocating substantial computation at inference time, often generating long and ver
arXiv:2604.22892v1 Announce Type: new Abstract: Feature selection in high-dimensional genomic data (d gg n) demands methods that are simultaneously accurate, sparse, and stable. Existing approaches ei
arXiv:2604.23309v1 Announce Type: new Abstract: Remote sensing image change captioning (RSICC) aims to describe the difference between two remote sensing images. While recent methods have explored vid
Zoox approached robotaxi design by prioritizing autonomous operation requirements over traditional vehicle constraints, with sensor placement as a foundational design decision. Sensors positioned on t
Yohei Nakajima shared an exploration of cumulative charts as a visualization method for tracking portfolio growth metrics, specifically demonstrating how to display annualized revenue progression acro
Lovelace AI Inc. is emerging from stealth mode today with an approach to enterprise artificial intelligence that it says is necessary for high-stakes decision-making, particularly in environments wher
arXiv:2402.11789v5 Announce Type: replace-cross Abstract: Anomaly localization in images -- identifying regions that deviate from normal patterns -- is vital in applications such as medical diagnosis
arXiv:2511.17902v3 Announce Type: replace-cross Abstract: Distributed Fiber Optic Sensing (DFOS) is promising for long-range perimeter security, yet practical deployment faces three key obstacles: sev
arXiv:2604.24544v1 Announce Type: new Abstract: The increasing reliance on Large Language Models (LLMs) across diverse sectors highlights the need for robust domain-specific and language-specific eval
We present StereoFoley, a video-to-audio generation framework that produces semantically aligned, temporally synchronized, and spatially accurate stereo sound at 48 kHz. While recent generative video-
arXiv:2512.10959v2 Announce Type: replace Abstract: We introduce StereoSpace, a diffusion-based framework for monocular-to-stereo synthesis that models geometry purely through viewpoint conditioning,
arXiv:2604.22782v1 Announce Type: cross Abstract: Serving transformer language models with high throughput requires caching Key-Values (KVs) to avoid redundant computation during autoregressive genera
arXiv:2604.24537v1 Announce Type: new Abstract: We study the problem of global maximization of a function f given a finite number of evaluations perturbed by noise. We consider a very weak assumption
arXiv:2604.23198v1 Announce Type: new Abstract: Current video moment retrieval excels at action-centric tasks but struggles with narrative content. Models can see extit{what is happening} but fail to
arXiv:2604.24156v1 Announce Type: cross Abstract: Efficient and fair spectrum allocation is a central challenge in 6G networks, where massive connectivity and heterogeneous services continuously compe
arXiv:2604.22757v1 Announce Type: cross Abstract: We introduce StratRAG, an open-source retrieval evaluation dataset for benchmarking Retrieval-Augmented Generation (RAG) systems on multi-hop reasonin
arXiv:2601.07698v2 Announce Type: replace Abstract: As emotional support chatbots have recently gained significant traction across both research and industry, a common evaluation strategy has emerged:
arXiv:2601.20597v2 Announce Type: replace Abstract: Continual Text-to-Video Retrieval (CTVR) is a challenging multimodal continual learning setting, where models must incrementally learn new semantic
arXiv:2604.23646v1 Announce Type: new Abstract: Recent evidence suggests that frontier AI systems can exhibit agentic misalignment, generating and executing harmful actions derived from internally con
arXiv:2604.24380v1 Announce Type: new Abstract: While Large Vision Language Models (LVLMs) demonstrate impressive capabilities, their substantial computational and memory requirements pose deployment
arXiv:2604.22843v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) has been proposed to mitigate hallucinations in large language models (LLMs), where generated outputs may be fact
arXiv:2604.23475v1 Announce Type: cross Abstract: We study the organization of channel-level importance in transformer feed-forward networks (FFNs). Using a Fisher-style loss proxy (LP) based on activ
arXiv:2604.23978v1 Announce Type: new Abstract: Family-school partnerships (FSP) are critical to children's development, yet families often face barriers such as time constraints, fragmented communica
arXiv:2604.23135v1 Announce Type: new Abstract: Natural-language variation poses a key challenge in Lean autoformalization: semantically equivalent paraphrases of the same theorem statements can induc
arXiv:2402.19088v5 Announce Type: replace-cross Abstract: Live languages continuously evolve to integrate the cultural change of human societies. This evolution manifests through neologisms (new words
arXiv:2507.09245v2 Announce Type: replace Abstract: The Swa-bhasha Resource Hub provides a comprehensive collection of data resources and algorithms developed for Romanized Sinhala to Sinhala translit
arXiv:2604.22852v1 Announce Type: cross Abstract: Cloud-hosted LLM inference for autonomous driving adds round-trip delay and depends on stable connectivity, while purely local edge models struggle un
arXiv:2601.16746v3 Announce Type: replace-cross Abstract: LLM agents have demonstrated remarkable capabilities in software development, but their performance is hampered by long interaction contexts,
arXiv:2509.14635v2 Announce Type: replace Abstract: Understanding and reasoning about entire software repositories is an essential capability for intelligent software engineering tools. While existing
arXiv:2512.07538v3 Announce Type: replace Abstract: Recognizing semantic differences across documents is crucial for text generation evaluation and content alignment, especially in cross-lingual setti
arXiv:2603.26380v2 Announce Type: replace Abstract: The attention mechanism has been the core component in modern transformer architectures. However, the computation of standard full attention scales
Switched out Sonnet 4.6 for GLM 5.1 through @FireworksAI_HQ while doing some tests with @LangChain Fleet Agents Went from 0.19 per run with Sonnet to 0.07 with GLM 5.1 You can also drop Kimi K2.6 and
arXiv:2604.24346v1 Announce Type: cross Abstract: Vision-language models (VLMs) are increasingly deployed as evaluators in tasks requiring nuanced image understanding, yet their reliability in scoring
arXiv:2602.15603v2 Announce Type: replace Abstract: Models based on partial differential equations (PDEs) are powerful for describing a wide range of complex phenomena in the natural sciences. Accurat
arXiv:2604.23806v1 Announce Type: cross Abstract: The reverse process in score-based diffusion models is formally equivalent to overdamped Langevin dynamics in a time-dependent energy landscape. In ou