Knowledge catalogue
arXiv:2604.20174v1 Announce Type: new Abstract: Reinforcement learning (RL) policies are typically trained for fixed objectives, making reuse difficult when task requirements change. We study inferenc
arXiv:2604.20428v1 Announce Type: new Abstract: Motion planning for autonomous vehicles often requires satisfying multiple conditionally conflicting specifications. In situations where not all specifi
arXiv:2604.20800v1 Announce Type: new Abstract: Reconstructing 3D Human-Object Interaction from an RGB image is essential for perceptive systems. Yet, this remains challenging as it requires capturing
arXiv:2604.20745v1 Announce Type: cross Abstract: Federated continual learning (FCL) allows distributed autonomous fleets to adapt collaboratively to evolving terrain types across extended mission lif
arXiv:2604.07798v3 Announce Type: replace Abstract: Although LLM agents can leverage tools for complex tasks, they still need memory to maintain cross-turn consistency and accumulate reusable informat
LiteParse is really neat! It does a great job of extracting text from annoying layouts in PDFs (multiple columns for example) It's only available as a Node.js CLI app, so I vibe-coded up this version
arXiv:2604.17931v2 Announce Type: replace Abstract: Reinforcement Learning (RL) has emerged as a powerful training paradigm for LLM-based agents. However, scaling agentic RL for deep research remains
arXiv:2604.20796v1 Announce Type: new Abstract: We present LLaDA2.0-Uni, a unified discrete diffusion large language model (dLLM) that supports multimodal understanding and generation within a nativel
arXiv:2501.03624v2 Announce Type: replace-cross Abstract: Large language models (LLMs) excel on many NLP benchmarks, but their behavior on real-world, semi-structured prediction remains underexplored.
arXiv:2411.10109v2 Announce Type: replace Abstract: Machine learning can predict human behavior well when substantial structured data and well-defined outcomes are available, but these models are typi
arXiv:2604.19787v1 Announce Type: cross Abstract: Social media platforms mediate how billions form opinions and engage with public discourse. As autonomous AI agents increasingly participate in these
arXiv:2604.20304v1 Announce Type: cross Abstract: Constructing phase diagrams for multicomponent alloys requires extensive experimental measurements and is a time-consuming task. Here we investigate w
arXiv:2604.20193v1 Announce Type: new Abstract: Ensuring functional safety in human-robot interaction is challenging because AI perception is inherently probabilistic, whereas industrial standards req
arXiv:2604.20560v1 Announce Type: new Abstract: Automatically filling Case Report Forms (CRFs) from clinical notes is challenging due to noisy language, strict output contracts, and the high cost of f
arXiv:2510.13928v2 Announce Type: replace-cross Abstract: We propose and test the LLM Brain Rot Hypothesis: continual exposure to junk web text induces lasting cognitive decline in large language mode
arXiv:2508.06614v2 Announce Type: replace Abstract: As a class of generative artificial intelligence frameworks inspired by statistical physics, diffusion models have shown extraordinary performance i
arXiv:2510.04225v2 Announce Type: replace-cross Abstract: The rapid growth of AI-generated imagery has blurred the boundary between real and synthetic content, raising practical concerns for digital i
arXiv:2603.04950v2 Announce Type: replace-cross Abstract: Differential medical VQA models compare multiple images to identify clinically meaningful changes and rely on vision encoders to capture fine-
looks like new Pareto frontiers across everything: - Context: 400K context in Codex and a 1M in API - API Pricing: 5/m input and 30/m output tokens. - Codex improved its own inference speed 20% lol -
arXiv:2308.03303v2 Announce Type: replace Abstract: Fine-tuning large language models (LLMs) is crucial for improving their performance on downstream tasks, but full-parameter fine-tuning (Full-FT) is
LTX released an HDR IC-LoRA beta that enables precise control over video generation by transferring structure and motion from reference videos, supporting features like EXR output for professional wor
arXiv:2604.19976v1 Announce Type: new Abstract: While the human eye can perceive an impressive twenty stops of dynamic range, smartphone camera sensors remain limited to about twelve stops despite dec
arXiv:2604.20236v1 Announce Type: new Abstract: High-performance TSP solvers like LKH search within a sparsified candidate graph rather than over all possible edges. Graph sparsification is non-trivia
arXiv:2604.20143v1 Announce Type: cross Abstract: This is our fourth work in the series on machine learning (ML) moment closure models for the radiative transfer equation (RTE). In the first three pap
UC Santa Cruz astronomers using GPU-accelerated simulations have discovered rotating disk galaxies resembling the Milky Way appearing far earlier in the universe than expected, breaking records for th
arXiv:2604.20286v1 Announce Type: cross Abstract: Recent segmentation models have demonstrated promising efficiency by aggressively reducing parameter counts and computational complexity. However, the
Kate Park / TechCrunch: Manila-based Salmon, a consumer finance app targeting underbanked Filipinos, raised 60M in equity and 40M in debt; it raised 310M to date, 160M in equity — The Philippines has
arXiv:2604.20650v1 Announce Type: new Abstract: 6D object pose estimation in cluttered scenes remains challenging due to severe occlusion and sensor noise. We propose MAPRPose, a two-stage framework t
arXiv:2604.20221v1 Announce Type: new Abstract: This study applies symbolic time series analysis and Markov modeling to explore the phonological structure of Evgenij Onegin-as captured through a graph
arXiv:2509.08607v3 Announce Type: replace-cross Abstract: The geodesy of irregularly shaped small bodies presents fundamental challenges for gravitational field modeling, particularly as deep space ex
arXiv:2511.11931v2 Announce Type: replace Abstract: This paper proposes MATT-Diff: Multimodal Active Target Tracking by Diffusion Policy, a control policy for active multi-target tracking using a mobi
arXiv:2604.20074v1 Announce Type: new Abstract: A popular approach to apprenticeship learning (AL) is to formulate it as an inverse reinforcement learning (IRL) problem. The MaxEnt-IRL algorithm succe
arXiv:2604.20154v1 Announce Type: cross Abstract: Multi-look acquisition is a widely used strategy for reducing speckle noise in coherent imaging systems such as digital holography. By acquiring multi
AI investment is surging to manic heights, but C-suites have yet to see it translate into measurable business outcomes — a gap that is now one of the defining strategic challenges of the current techn
arXiv:2604.20317v1 Announce Type: new Abstract: GAN-based facial attribute editing is widely used in virtual avatars and social media but often suffers from attribute entanglement, where modifying one
arXiv:2604.19799v1 Announce Type: cross Abstract: Generative AI is rapidly transforming how organizations create value and evaluate talent. While large language models enhance baseline output quality,
arXiv:2604.20545v1 Announce Type: new Abstract: In measurement theory, instruments do not simply record reality; they help constitute what is observed. The same holds for generative AI evaluation: ben
arXiv:2601.02989v2 Announce Type: replace Abstract: Large language models (LLMs), despite strong performance on complex mathematical problems, exhibit systematic limitations in counting tasks. This is
arXiv:2604.20467v1 Announce Type: cross Abstract: Artificial Intelligence (AI) weather models are improving rapidly, and their forecasts are already competitive with long-established traditional Numer
arXiv:2604.20441v1 Announce Type: new Abstract: Background: Agent skills are increasingly deployed as modular, reusable capability units in AI agent systems. Medical research agent skills require safe
Meet Kimi K2.6 Agent Swarm 👋 Highlights： 🔹 Swarms, elevated - 300 parallel sub-agents × 4,000 steps per run (up from 100 / 1,500 in K2.5). 🔹 Outputs are real files, not chat - one run delivers 100+ fi
arXiv:2603.14222v2 Announce Type: replace-cross Abstract: Contrastive pretraining models such as CLIP and CLAP, serve as the ubiquitous perceptual backbones for modern multimodal large models, yet the
Kurt Wagner / Bloomberg: Memo: Meta plans to cut 10% of workers, or ~8,000 jobs, on May 20 and won't fill 6,000 open roles, in an effort to offset its AI spending and boost efficiency — Meta Platforms
Financial Times: Memo: White House says it has info indicating “foreign entities, principally based in China” are engaged in “industrial scale distillation” of American AI tech — Trump official Michae
arXiv:2601.02931v2 Announce Type: replace Abstract: Autoregressive LLMs perform well on relational tasks that require linking entities via relational words (e.g., father/son, friend), but it is unclea
arXiv:2604.20261v1 Announce Type: new Abstract: Automated feature generation extracts informative features from raw tabular data without manual intervention and is crucial for accurate, generalizable
arXiv:2604.20111v1 Announce Type: cross Abstract: Sparse additive models have attracted much attention in high-dimensional data analysis due to their flexible representation and strong interpretabilit
Meta Platforms Inc. told staff today that it’s planning to lay off about 8,000 employees, or roughly 10% of its workforce, and cancel 6,000 open roles in an efficiency drive aimed at offsetting a mass
Meta is planning to layoff around 10 percent of employees in May, according to a memo from the company's chief people officer, Janelle Gale, published by Bloomberg. That means approximately 8,000 peop
arXiv:2604.20148v1 Announce Type: cross Abstract: Can small language models achieve strong tool-use performance without complex adaptation mechanisms? This paper investigates this question through Met
arXiv:2601.11505v2 Announce Type: replace-cross Abstract: Progress in Type 1 Diabetes (T1D) algorithm development is limited by the fragmentation and lack of standardization across existing T1D manage
arXiv:2604.20685v1 Announce Type: new Abstract: Aligning large language models (LLMs) to desirable human values requires balancing multiple, potentially conflicting objectives such as helpfulness, tru
Jordan Novet / CNBC: Microsoft announces its first voluntary retirement program, for staff whose years of employment and age add up to 70+; source: 7% of US employees are eligible — Microsoft will off
Tom Warren / The Verge: Microsoft announces the first voluntary retirement program in its 50-year history, for US staffers whose combined years of service added to their age totals 70+ — Microsoft is
Microsoft is rolling out a new Agent Mode inside Office apps like Word, Excel, and PowerPoint this week. Previously described by Microsoft as 'vibe working,' the Agent Mode is a more powerful version
arXiv:2604.19809v1 Announce Type: new Abstract: We introduce MIRROR, a benchmark comprising eight experiments across four metacognitive levels that evaluates whether large language models can use self
arXiv:2604.14785v2 Announce Type: replace Abstract: Recent progress in Multimodal Large Language Models (MLLMs) has demonstrated remarkable advances in perception and reasoning, suggesting their poten
arXiv:2604.20366v1 Announce Type: new Abstract: Large Vision-Language Models (LVLMs) exhibit powerful generative capabilities but frequently produce hallucinations that compromise output reliability.
arXiv:2604.16756v2 Announce Type: replace-cross Abstract: Prompt-induced cognitive biases are changes in a general-purpose AI (GPAI) system's decisions caused solely by biased wording in the input (e.
arXiv:2412.14590v2 Announce Type: replace Abstract: Quantization has become one of the most effective methodologies to compress LLMs into smaller size. However, the existing quantization solutions sti