Knowledge catalogue
arXiv:2605.29317v1 Announce Type: new Abstract: Parameter-efficient fine-tuning(PEFT) has largely focused on LoRA and its accuracy-oriented variants, leaving the original goal of reducing trainable pa
arXiv:2605.29001v1 Announce Type: cross Abstract: A paraphrase-quality audit of MathCheck (ICLR 2025) detected 4 semantically incorrect paraphrases in 129 groups (3.1%); removing them drops GPT-4o fro
arXiv:2605.29587v1 Announce Type: cross Abstract: In transcriptomics, gene-set-aware factorization methods such as the Pathway Level Information Extractor (PLIER) are most effective when trained on la
arXiv:2507.21429v3 Announce Type: replace-cross Abstract: We study local linear convergence of gradient descent for finite-width feedforward networks under the squared empirical loss. Prior work shows
arXiv:2605.29768v1 Announce Type: new Abstract: Existing traffic forecasting benchmarks assume a fixed sensor set, but real road-sensor networks grow continuously as the road network changes year by y
arXiv:2605.28965v1 Announce Type: new Abstract: Linking free-text phenotype descriptions to ontology terms, typically referred to as phenotype annotation, is essential for the cross-study integration
arXiv:2605.30045v1 Announce Type: new Abstract: Video object removal frequently struggles to simultaneously eliminate target objects and their associated physical effects (e.g., smoke, reflections, li
arXiv:2605.29107v1 Announce Type: cross Abstract: Large language models (LLMs) increasingly rank products, documents, and recommendations for user queries, which makes manipulating these rankings a gr
arXiv:2605.30022v1 Announce Type: cross Abstract: Positional encoding (PE) underpins how permutation-invariant Transformers represent sequence order, yet how positional information is processed and st
arXiv:2602.01058v2 Announce Type: replace-cross Abstract: Post-training of reasoning LLMs is a holistic process that typically consists of an offline SFT stage followed by an online reinforcement lear
arXiv:2605.28848v1 Announce Type: cross Abstract: Deployed language models are evaluated in a non-stationary environment: model versions, retrieval layers, safety systems, and real-world inputs all ch
arXiv:2605.30341v1 Announce Type: cross Abstract: Studying scalable methods for visual generative modeling requires large, accessible, and stable datasets. We introduce GPIC, a Giant Permissive Image
I cannot verify this claim as it references a future date (the URL timestamp appears invalid) and describes a model version (GPT-5.5 Pro) that doesn't exist in current public releases. The post appear
arXiv:2605.29494v1 Announce Type: new Abstract: Deep neural network training involves both forward propagation (from features through logits to loss) and backward propagation (from loss through gradie
arXiv:2605.30322v1 Announce Type: cross Abstract: We introduce Gram, an automated alignment auditing framework to assess the propensity of AI agents to engage in sabotage. We evaluate Gemini models ac
arXiv:2605.29668v1 Announce Type: new Abstract: LLM agents acting in structured environments fail in operational rather than conversational ways, and reliability depends on procedural knowledge of the
arXiv:2508.05614v2 Announce Type: replace-cross Abstract: LLM agents achieve 85-96% success on tasks where instructions fully specify the action, but drop to 29-53% when action feasibility depends on
arXiv:2605.28882v1 Announce Type: cross Abstract: With the rapid advancement of large language models, evaluating human-likeness in open-ended conversation has become increasingly important. However,
arXiv:2605.29218v1 Announce Type: new Abstract: Web agents, which couple language models with browsing and tool-use capabilities, show promise as open web assistants. Yet progress is increasingly limi
arXiv:2605.29532v1 Announce Type: cross Abstract: Exploratory GUI testing is a particularly demanding setting for MLLM agents: without predefined test scripts, an agent must autonomously navigate an a
arXiv:2605.28910v1 Announce Type: cross Abstract: Large language models (LLMs) have shown promise on summarization tasks, but they often produce hallucinations, which are unsupported or incorrect stat
arXiv:2605.29055v1 Announce Type: new Abstract: Hallucination remains a major reliability barrier for production LLM systems, particularly in multi-agent pipelines where unsupported claims can propaga
Reece Rogers / Wired: Hands-on with Gemini Spark beta rolling out to AI Ultra subs: planned a birthday party from emails and calendar, but called a live-in boyfriend a “close friend” — Google's new AI
Hear the architects of Gemini reflect on their journey to continue pushing the frontier of AI, on this episode of Release Notes. @JeffDean, @koraykv, @OriolVinyalsML, and @NoamShazeer sit down on came
arXiv:2605.30058v1 Announce Type: new Abstract: While LLM agents have demonstrated remarkable task-oriented abilities such as planning, reasoning, and action, few works have treated them as complete h
Here's an extended edit of the quote that includes a following fragment where Andrew Macdonald called the trade 'harder to justify' - full, unedited transcript is here: https://gist.github.com/simonw/
arXiv:2605.29782v1 Announce Type: cross Abstract: Reinforcement learning (RL) refines large language models (LLMs) by directly optimizing model behavior through reward signals. While accurate state va
Braintrust leverages OpenAI's Codex model to automatically convert customer requests and natural language specifications into functional code, streamlining the software development process. This appli
arXiv:2605.29442v1 Announce Type: cross Abstract: AI coding agents increasingly act directly within software environments, yet existing analyses of their failures rely on benchmark trajectories that m
arXiv:2602.02103v2 Announce Type: replace-cross Abstract: Chain-of-thought (CoT) reasoning has become a central mechanism for eliciting multi-step reasoning in Large Language Models (LLMs). Yet recent
arXiv:2605.30260v1 Announce Type: cross Abstract: Large Language Models (LLMs) must continuously learn and update knowledge to remain effective in dynamic real-world environments. While Low-Rank Adapt
How lucky are you to have been born when and where you are? Had Opus 4.8 in Claude Code whip up a new visualization of all humans who ever lived. In addition to being neat, it is an interesting test o
arXiv:2605.30096v1 Announce Type: cross Abstract: Large language models (LLMs) can autonomously conduct multi-stage cyber attacks, but the consistency of their offensive behavior under repeated trials
I GOT THE DOMAIN! I FINALLY GOT IT!!!!!!!!!!1 🥳🎉 Paint.NET is now at https://paint.net! Well, it will be just as soon as I push all the buttons to migrate content and set up redirects from getpaint.
- I still get nonstop questions about use cases, even though I think thinking about things in the use case framework is the wrong way of thinking about it - Enterprises are starting to see actual busi
arXiv:2605.30179v1 Announce Type: cross Abstract: Parameter-efficient adaptation has made LLMs practical for domain prediction, but standard LoRA still relies on a static low-rank update and does not
I’m going to let you in on a secret. I made a mistake once.* In August 2024.* It’s true. I actually got something wrong. I predicted that there would be a collapse of the AI bubble (which in my judgem
Simon Willison expresses skepticism about reports claiming Uber overspent on AI and was disappointed with the results, indicating he investigated the story and found issues with its accuracy or framin
arXiv:2605.29983v1 Announce Type: cross Abstract: The adversarial robustness of attributions is a fundamental requirement for reliable explainability in deep learning, yet existing approaches typicall
arXiv:2603.00377v2 Announce Type: replace Abstract: Full Waveform Inversion (FWI) is a highly nonlinear and ill-posed problem that aims to recover subsurface velocity maps from surface-recorded seismi
In conversation with OpenAI’s @markchen90, Terence reflects on a future where AI reduces the cognitive friction of research, helps preserve the paths behind discovery, and expands what mathematicians
arXiv:2605.29270v1 Announce Type: new Abstract: The era of the Internet of Agents (IoA) is taking shape: LLM agents are expected to fulfill user goals by orchestrating fast-growing populations of Mode
arXiv:2605.29223v1 Announce Type: new Abstract: The parameter counts of the most widely used large language models (LLMs) are often withheld by their developers, leaving model size -- a primary refere
arXiv:2605.29473v1 Announce Type: cross Abstract: Language models are increasingly being deployed for conversational support in informal caregiving contexts, where interactions often extend beyond inf
arXiv:2511.22884v2 Announce Type: replace Abstract: Data analysis has become an indispensable part of scientific research. To discover the latent knowledge and insights hidden within massive datasets,
Interesting that the GPT-5 Pro series models have consistently been the best models for single-shot attempts at the hardest problems since last summer. There has been no real competition in all that t
arXiv:2605.29889v1 Announce Type: cross Abstract: Patient-voiced clinical-triage benchmarks report high under-triage rates for consumer LLMs for constrained multiple-choice output, yet the same cases
arXiv:2505.21627v4 Announce Type: replace-cross Abstract: State-of-the-art large language models require specialized hardware and substantial energy to operate. As a consequence, cloud-based services
Jeremy Howard expresses positive views on GPT-5.5, stating he has recently switched to using it as his primary model and finds it nearly comparable to Anthropic's Opus 4.6 and 4.7 while offering signi
NVIDIA has released a corrected version of DeepSeek-V4-Pro-NVFP4, a quantized model variant optimized for NVIDIA hardware using NV-FP4 (NVIDIA's 4-bit floating-point format). The model is available on
arXiv:2605.29523v1 Announce Type: new Abstract: Large Language Models (LLMs) have advanced financial automation through Retrieval-Augmented Generation (RAG), yet hallucinations remain a critical barri
arXiv:2605.29524v1 Announce Type: cross Abstract: Relay and reseller APIs increasingly intermediate access to large language models (LLMs), but users have no direct way to verify that a claimed endpoi
arXiv:2605.29371v1 Announce Type: cross Abstract: We study the subclass of potential mean-field games in which the running interaction cost and the terminal target cost are both expressed through repr
arXiv:2605.29684v1 Announce Type: new Abstract: The scaling limit where both the size of the training set P and the width N of a deep neural network grow at the same rate, the so-called proportional-w
arXiv:2605.29075v1 Announce Type: new Abstract: LLMs encode both general capabilities and domain-specific knowledge in a single set of parameters. We ask whether this capacity can be reorganized: keep
arXiv:2605.29459v1 Announce Type: new Abstract: Large language models route every input through a learned embedding table of shape |V| x d_model, consuming hundreds of millions to billions of trainabl
arXiv:2605.29009v1 Announce Type: cross Abstract: Post-training large language models with reinforcement learning is bottlenecked by the reward signal. Existing approaches require either ground-truth
arXiv:2605.29928v1 Announce Type: cross Abstract: As AI-generated and AI-assisted content floods online spaces, source labels attached to such content can distort human reasoning judgments, with downs
arXiv:2605.28854v1 Announce Type: new Abstract: Large language models (LLMs) exhibit remarkable flexibility: they can adapt to novel tasks from in-context examples without any parameter updates, a cap
arXiv:2605.30018v1 Announce Type: new Abstract: Large language models (LLMs) frequently achieve impressive scores on standardized benchmarks, yet accuracy alone offers a limited view of their capabili