Knowledge catalogue
A discussion of progressive training approaches for diffusion models where training begins at lower scale factors and progressively increases to target scale factors, leveraging previously trained mod
arXiv:2601.10348v2 Announce Type: replace Abstract: Efficient distillation is a key pathway for converting expensive reasoning capability into deployable efficiency, yet in the frontier regime where t
arXiv:2603.28103v2 Announce Type: replace-cross Abstract: Parliamentary proceedings represent a rich yet challenging resource for computational analysis, particularly when preserved only as scanned hi
arXiv:2605.22355v1 Announce Type: new Abstract: Public transit route planning traditionally depends on structured map infrastructure and complex routing engines, and no existing dataset supports train
arXiv:2605.22403v1 Announce Type: new Abstract: Surface electromyography (sEMG) signal-based activity recognition has attracted increasing research attention in recent years. To develop accurate sEMG
arXiv:2602.12952v2 Announce Type: replace-cross Abstract: Adapting large pre-trained models to downstream tasks often produces task-specific parameter updates that are expensive to relearn for every m
arXiv:2605.22709v1 Announce Type: cross Abstract: Electromagnetic (EM) side-channel analysis traditionally assumes a stationary, close-proximity probe - a threat model that underestimates aerial adver
U.S. President Donald Trump has delayed the signing of an executive order designed to regulate advanced artificial intelligence models. “I didn’t like certain aspects of it. I postponed it,” Trump tol
The Trump-appointed FCC chairman Brendan Carr initiated an inquiry into whether ABC's daytime talk show 'The View' qualifies as a 'bona fide news program' exempt from political equal-time rules. The p
Together AI announced the availability of Qwen3.7-Max, a large language model, on their platform. The announcement promotes users to try the model through Together AI's interface. Qwen3.7-Max is part
This is a humorous post by Elon Musk on X (Twitter) making a joke about the pronunciation of 'Retatrutide,' a pharmaceutical compound, by mishearing it as 'Retardatide' and joking about the implied tr
arXiv:2605.22069v1 Announce Type: new Abstract: Novel view synthesis from sparse-view inputs poses a significant challenge in 3D computer vision, particularly for achieving high-quality scene reconstr
arXiv:2605.22620v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) has substantially improved the reasoning ability of LLMs, but often depends on external supervis
arXiv:2605.21869v1 Announce Type: new Abstract: We present our submission to the Hume-ABAW10 Emotional Mimicry Intensity (EMI) Challenge, which aims to predict six continuous emotion intensity dimensi
arXiv:2601.07603v3 Announce Type: replace Abstract: We present UIKA, a feed-forward animatable Gaussian head model from an arbitrary number of pose-free inputs, including a single image, multi-view ca
arXiv:2605.22192v1 Announce Type: new Abstract: Blind image quality assessment (BIQA) for ultrahighdefinition (UHD) images remains challenging because native-resolution inference is computationally ex
arXiv:2605.22769v1 Announce Type: new Abstract: Large language models (LLMs) are typically trained on shuffled corpora, yielding models whose knowledge is frozen at train time and whose temporal groun
arXiv:2605.22493v1 Announce Type: cross Abstract: Behavioral cloning becomes difficult when the same observation admits several valid actions. We study this problem for action-chunking policies and sh
arXiv:2605.22389v1 Announce Type: new Abstract: Effectively training Large Language Models (LLMs) for complex, long-CoT reasoning is often bottlenecked by the need for massive high-quality reasoning d
arXiv:2602.02112v2 Announce Type: replace-cross Abstract: Masked diffusion models (MDMs) are a potential alternative to autoregressive models (ARMs) for language generation, but generation quality dep
arXiv:2605.06597v2 Announce Type: replace Abstract: Self-distillation (SD) offers a promising path for adapting large language models (LLMs) without relying on stronger external teachers. However, SD
arXiv:2605.21906v1 Announce Type: new Abstract: Computed tomography (CT) is a central to three-dimensional medical imaging, yet CT-based artificial intelligence remains fragmented across task-specific
arXiv:2605.21611v1 Announce Type: new Abstract: We introduce spatially grounded contextual image generation, a controllable image generation task that reframes the conditioning paradigm. Instead of su
Gary Marcus responds to Ethan Mollick's post about AI capabilities, noting that while he objects to claims made in the top-level post, Mollick does provide important caveats and nuance in subsequent r
Gary Marcus notes that researcher @thestalwart has found more recent AI models to be less vulnerable to certain attacks or exploits, and suggests that a comprehensive study across multiple models woul
Sergiu Gatlan / BleepingComputer: US and Canadian authorities arrest 23-year-old Jacob Butler, known online as “Dort”, for allegedly operating the Kimwolf DDoS botnet, which infected ~2M devices — U.S
Cursor provides SDK documentation and a /sdk skill to help developers get started with Python integration. The resource links to their official documentation at cursor.com/docs/sdk/python for setup in
ID-LoRA (Identity-Driven In-Context LoRA) enables identity-preserving audio-video generation by simultaneously dictating the scene's visual content, environmental acoustics, and speaking style while p
This article discusses how organizations can leverage observability data—including metrics, logs, and traces—to proactively identify and prevent incidents before they impact systems and users. It like
arXiv:2605.21654v1 Announce Type: cross Abstract: Reinforcement learning substantially improves pretrained language models, but it remains understudied why critic-free methods such as PPO and GRPO wor
arXiv:2605.20742v1 Announce Type: new Abstract: With the rapid proliferation of electric vehicles, the safety and reliability of lithium-ion batteries have become critical concerns. Effective anomaly
arXiv:2510.05094v2 Announce Type: replace Abstract: Recent video generation models can produce smooth and visually appealing clips, but they often struggle to synthesize complex dynamics with a cohere
arXiv:2602.00122v2 Announce Type: replace Abstract: In recent years, image editing models have made significant progress, enabling users to manipulate visual content in a flexible and interactive mann
arXiv:2605.22817v1 Announce Type: cross Abstract: Language models must now generalize out of the box to novel environments and work inside inference-scaling search procedures, such as AlphaEvolve, tha
arXiv:2605.22357v1 Announce Type: new Abstract: Accurate segmentation of hepatic and portal vessels in contrast-enhanced computed tomography angiography (CTA) remains challenging due to complex vascul
arXiv:2602.10062v2 Announce Type: replace-cross Abstract: Out-of-distribution (OOD) detection is critical for the safe deployment of machine learning systems. Existing post-hoc detectors typically rel
arXiv:2605.22570v1 Announce Type: new Abstract: Spatio-temporal reasoning is a core capability for Multimodal Large Language Models (MLLMs) operating in the real world. As such, evaluating it precisel
arXiv:2605.21977v1 Announce Type: new Abstract: AI-generated content (AIGC) is rapidly improving, creating an urgent need for detectors that generalize across data sources, deployment pipelines, and v
arXiv:2601.23224v2 Announce Type: replace Abstract: Existing multimodal large language models for long-video understanding predominantly rely on uniform sampling and single-turn inference, limiting th
This post likely shares images or video footage of SpaceX's Starship vehicle captured from a Starlink satellite in orbit, providing a perspective of the spacecraft from space. The content demonstrates
arXiv:2605.22000v1 Announce Type: new Abstract: Three-dimensional (3D) histopathology of unprocessed tissues has the potential to transform disease management by enabling volumetric characterization o
arXiv:2602.13294v3 Announce Type: replace Abstract: Evaluating whether Multimodal Large Language Models (MLLMs) genuinely reason about physical dynamics remains challenging. Most existing benchmarks r
arXiv:2605.22096v1 Announce Type: new Abstract: Capsule endoscopy event detection is challenging because clinically relevant findings are sparse, visually heterogeneous, and evaluated at the event lev
arXiv:2605.21924v1 Announce Type: new Abstract: On-policy knowledge distillation has proven effective for language models, yet its application to vision-language models (VLMs) remains underexplored. W
arXiv:2605.21633v1 Announce Type: cross Abstract: When the blood supply to the brain is obstructed by a clot, oxygen delivery to brain tissues becomes insufficient, leading to cellular necrosis. In he
Streaming vision-language models (VLMs) continuously generate responses given an instruction prompt and an online stream of input frames. This is a core mechanism for real-time visual assistants. Exis
SpaceX's Starship Flight Test 12 was a test flight of the fully integrated Starship launch vehicle, likely involving the Super Heavy booster and Starship upper stage. Elon Musk promoted the live broad
This post expresses optimism about humanity's future prospects, suggesting current times represent an exceptionally positive period for human civilization and development. The incomplete text indicate
DeepSeek has announced a permanent discount for its DeepSeek-V4-Pro model, encouraging developers to build and innovate with the platform. The announcement was made via social media and emphasizes the
We desperately need better ways of evaluating models. Something that shows how helpful they are at working hand-in-hand with humans to help them get stuff done in a cooperative/iterative way. The Clau
We saw our first meaningful jump in the ARC-AGI-3 competition today @tufalabs went from 0.68% > 1.17% My notes: - .68% is the score of the best template (which is why so many people have this score) -
We’re giving away $10,000,000 to founders building agent-first businesses. Autonomous, proactive agents will run tomorrow's companies. We're backing 500 founders building them. The Founding 500. http:
We're hosting an agentic AI meetup in LA on May 28th — 5–7pm at Gulp in Playa Vista. Builders, founders, engineers. Drinks, no fluff. RAG systems, agentic workflows, or just starting out — all welcome
OpenAI solicited community feedback on X regarding content or features they should prioritize in the following week. This post reflects OpenAI's practice of engaging their audience to guide product de
Western civilization is amazing What if the west isn't the villain they told you it was? We’ve spent years accepting accusations about racism, intolerance, and slavery without challenging the bigger h
arXiv:2605.22651v1 Announce Type: new Abstract: CLIP-style contrastive pretraining typically curates web-scale image-text pairs using sample-level filtering signals, often based on pair-level alignmen
arXiv:2602.01334v2 Announce Type: replace Abstract: Vision tool-use reinforcement learning (RL) can equip vision language models with visual operators such as crop-and-zoom and achieves strong perform
Sam Altman posed a question to the public asking what problem they most hope AI will solve in the future, with an implied offer that OpenAI might be able to help address it. The post invites community
arXiv:2605.21807v1 Announce Type: new Abstract: Across medical specialties, clinical practice is anchored in evidence-based guidelines that codify best studied diagnostic and treatment pathways. These
arXiv:2602.05536v2 Announce Type: replace-cross Abstract: Model merging combines multiple fine-tuned models into a single model by adding their weight updates, providing a lightweight alternative to r