Knowledge catalogue
arXiv:2604.26848v1 Announce Type: new Abstract: Robotic manipulation critically requires reasoning about future spatial-temporal interactions, yet existing VLA policies and world-model-enhanced polici
arXiv:2601.06160v2 Announce Type: replace Abstract: Large Language Models (LLMs) often suffer from ''Reasoning Collapse'' on challenging mathematical reasoning tasks, where stochastic sampling produce
arXiv:2505.22910v2 Announce Type: replace Abstract: When a student fails an exam, do we tend to blame their effort or the test's difficulty? Attribution, defined as how reasons are assigned to event o
arXiv:2510.04214v3 Announce Type: replace Abstract: We deploy large language models (LLMs) as business development (BD) agents for persuasive price negotiation in online travel agencies (OTAs). The ag
arXiv:2604.26361v1 Announce Type: cross Abstract: Globalization of graphic designs such as those used in marketing materials and magazines is increasingly important for communication to broad audience
arXiv:2604.26347v1 Announce Type: cross Abstract: Objective metrics for emotional expressiveness are vital for speech generation, particularly in expressive synthesis and voice conversion requiring em
Zig has one of the most stringent anti-LLM policies of any major open source project: No LLMs for issues. No LLMs for pull requests. No LLMs for comments on the bug tracker, including translation. Eng
arXiv:2604.26370v1 Announce Type: new Abstract: Vision-language models have shown strong performance, but they often generalize poorly to specialized domains. While semi-supervised vision-language lea
arXiv:2604.26597v1 Announce Type: cross Abstract: Timely and reliable multilingual communication is critical during natural and human-induced disasters, but developing effective solutions for crisis c
arXiv:2604.26360v1 Announce Type: cross Abstract: Reinforcement learning (RL) systems typically optimize scalar reward functions that assume precise and reliable evaluation of outcomes. However, real-
arXiv:2602.03412v2 Announce Type: replace Abstract: As large language model agents tackle increasingly complex long-horizon tasks, effective post-training becomes critical. Prior work faces fundamenta
arXiv:2509.09870v2 Announce Type: replace-cross Abstract: Large language models (LLMs) enable conversational agents (CAs) to express distinctive personalities, raising new questions about how such des
arXiv:2604.26218v1 Announce Type: new Abstract: Brain encoding models not only serve to decipher how visual stimuli are transformed into neural responses, but also represent a critical step toward vis
arXiv:2505.20032v3 Announce Type: replace Abstract: Tactile sensing provides local essential information that is complementary to visual perception, such as texture, compliance, and force. Despite rec
arXiv:2604.26844v1 Announce Type: new Abstract: Many of the thousands of attested languages share common configurations of features, creating a spectrum from typologically very rare (e.g., object-verb
arXiv:2510.17548v2 Announce Type: replace Abstract: Language models are often evaluated with scalar metrics like accuracy, but such measures fail to capture how models internally represent ambiguity,
// When to Retrieve During Reasoning // Pay attention to this one, AI devs. (bookmark it) Most RAG systems retrieve once, before the model starts reasoning. Large reasoning models like o1 and R1 don't
This post likely discusses accountability in AI systems, featuring commentary or a cartoon from Marketoonist (a popular cartoonist who creates comics about business and technology). Gary Marcus, an AI
wow. incredible. A Chinese court has ruled it illegal to replace human workers with AI purely for the sake of cost-cutting. The court decided that companies hold a social responsibility to treat worke
Zuck is zucking up Meta Mark Zuckerberg lacks the cloud-computing business to truly justify Meta's AI spending, @DaveLeeBBG says (via @opinion) https://www.bloomberg.com/opinion/articles/2026-04-30/me
arXiv:2505.13766v5 Announce Type: replace-cross Abstract: Software Quality Assurance (SQA) is critical for delivering reliable, secure, and efficient software products. The Software Quality Assurance
arXiv:2503.09655v2 Announce Type: replace-cross Abstract: Traditional Long Short-Term Memory (LSTM) networks are effective for handling sequential data but have limitations such as gradient vanishing
arXiv:2604.25427v1 Announce Type: new Abstract: While large-scale video diffusion models have demonstrated impressive capabilities in generating high-resolution and semantically rich content, a signif
agents are going and are already changing every industry & vertical, awesome blog from the @MadrigalPharma team on using Deep Agents, Skills, & LangSmith at the frontier of biopharma it’s an awesome t
AI-Residual Economies (Data → Income) Users begin to expect compensation for their contribution to AI systems, not just free usage. These platforms track, attribute, and pay micro-royalties when user
arXiv:2604.25323v1 Announce Type: new Abstract: Recent advances in open-vocabulary mobile manipulation have brought robots into real domestic environments. In such settings, reliable long-horizon exec
arXiv:2604.25072v1 Announce Type: new Abstract: Unified Multimodal Models (uMMs) aim to support both visual understanding and visual generation within a shared representation. However, existing evalua
arXiv:2509.09708v3 Announce Type: replace Abstract: Refusal on harmful prompts is a key safety behaviour in instruction-tuned large language models (LLMs), yet the internal causes of this behaviour re
arXiv:2604.25903v1 Announce Type: cross Abstract: The accelerating adoption of Large Language Models (LLMs) in software engineering (SE) has brought with it a silent crisis: unsustainable computationa
arXiv:2510.09382v2 Announce Type: replace Abstract: Curriculum learning (CL) structures training from simple to complex samples, facilitating progressive learning. However, existing CL approaches for
- Comey indicted for tweeting a number. - Trump FCC threatens ABC's broadcast license. - Trump defacing more govt institutions with his name and picture. - Trump's kids cashing in on huge govt contrac
arXiv:2604.24957v1 Announce Type: new Abstract: Scaling test-time compute has emerged as a powerful mechanism for enhancing Large Language Model (LLM) performance. However, standard post-training para
arXiv:2604.25891v1 Announce Type: new Abstract: Finetuning a language model can lead to emergent misalignment (EM) [Betley et al., 2025b]. Models trained on a narrow distribution of misaligned behavio
arXiv:2604.25676v1 Announce Type: new Abstract: Multilingual retrieval-augmented generation (mRAG) is often implemented within a fixed retrieval space, typically via query or document translation or m
Crazy how many people expect some company or country to achieve a “insurmountable lead” in AI, when in reality no company seems to hold a lead of more that a few weeks or at most a few months before s
arXiv:2604.25182v1 Announce Type: new Abstract: A multilingual collection may contain useful knowledge in other languages to supplement and correct the facts in the original language for Retrieval-Aug
arXiv:2604.25716v1 Announce Type: new Abstract: Safety mechanisms for large language models (LLMs) remain predominantly English-centric, creating systematic vulnerabilities in multilingual deployment.
Damning 🚨 Altman texts Musk: 'we offered you equity when we established the capped profit. you didn't want it at the time.' (Altman drafted this with Shivon Zilis, then sent it to Musk that night.) Op
arXiv:2506.05199v3 Announce Type: replace Abstract: A core task in embodied intelligence is ego-centric 3D visual grounding. Existing methods typically adopt two-stage, heterogeneous pipelines that pa
arXiv:2604.25259v1 Announce Type: new Abstract: Traffic signal control (TSC) plays a central role in reducing congestion and maintaining urban mobility. This dissertation introduces DGLight, a critic-
arXiv:2604.25050v1 Announce Type: new Abstract: Unlike chatbots, physical AI must act while the world keeps evolving. Therefore, the inter-chunk pause of synchronous executors are fatal for dynamic ta
Generative models are often deployed to make decisions on behalf of users, such as vision-language models (VLMs) identifying which person in a room is a doctor to help visually impaired individuals. Y
Gary Marcus discusses on CNN the legal merits of Elon Musk's lawsuit, arguing that despite questionable motivations behind the case, there may be legitimate legal grounds supporting it. The post refer
As enterprises push agentic AI out of the proof-of-concept phase and into production, AI runtime security — the ability to enforce policy at the exact moment an agent acts — is proving to be the bedro
arXiv:2604.25136v1 Announce Type: new Abstract: We propose Frictive Policy Optimization (FPO), a framework for learning language model policies that regulate not only what to say, but when and how to
This is a complimentary response to an article by Gary Marcus, praising his accuracy and work quality. The tweet does not provide specific details about the article's content, only that it was well-re
arXiv:2604.25907v1 Announce Type: new Abstract: Adapting reasoning models to new tasks during post-training with only output-level supervision stalls under reinforcement learning from verifiable rewar
arXiv:2603.01070v2 Announce Type: replace Abstract: Solving complex geometric problems inherently requires interleaved reasoning: a tight alternation between constructing diagrams and performing logic
arXiv:2504.17364v4 Announce Type: replace Abstract: Implicit Neural Representations (INRs) have revolutionized signal processing and computer vision by modeling signals as continuous, differentiable f
👇 I was there for this, sitting right next to Altman. Realizing a few months later he lied about it (by omission) was what turned me against him. We had sworn to tell the whole truth and nothing but t
arXiv:2604.24893v1 Announce Type: new Abstract: In episodic memory with natural language queries (EM-NLQ), a user may ask a question (e.g., 'Where did I place the mug?') that requires searching a long
La industria de las IA vive exclusivamente de nuestra creencias y supuesto de que podría hacer lo que no hace. Sheer insanity. Amazon, Google, Microsoft, and Meta collectively are spending more money
arXiv:2604.25691v1 Announce Type: new Abstract: Tendon-Driven Continuum Robots (TDCRs) pose significant modeling and control challenges due to complex nonlinearities, such as frictional hysteresis and
arXiv:2604.24952v1 Announce Type: new Abstract: Human visual preferences are inherently multi-dimensional, encompassing aesthetics, detail fidelity, and semantic alignment. However, existing datasets
arXiv:2604.24921v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models are a promising paradigm for generalist robotic manipulation by grounding high-level semantic instructions into ex
LOL. Just drop the stupid supply chain risk designation, and admit your mistake. SCOOP: The White House is developing guidance that would allow agencies to get around Anthropic's supply chain risk des
arXiv:2604.25806v1 Announce Type: new Abstract: Creating interactive STEM courseware traditionally requires HTML/CSS/JavaScript expertise, leaving barriers for educators. While generative AI can produ
Misleading indeed. 🚨 OpenAI's lawyer William Savitt just attacked Musk on cross-examination: 'you pledged 1 billion, only delivered 38 million.' That's misleading. The $1B was a COLLECTIVE pledge from
arXiv:2411.14721v2 Announce Type: replace Abstract: Molecule discovery is a pivotal research field, impacting everything from medicine to materials. Recently, Large Language Models (LLMs) have been wi
arXiv:2604.25448v1 Announce Type: new Abstract: Navigating AI regulation across jurisdictions is increasingly difficult for policymakers, legal professionals, and researchers. To address this, we pres