Knowledge catalogue
arXiv:2605.07021v1 Announce Type: new Abstract: Reasoning in Large Language Models (LLMs) poses a challenge for oversight as many misaligned behaviors do not surface until reasoning concludes. To addr
arXiv:2601.15050v4 Announce Type: replace Abstract: Current evaluation methods for Retrieval Augmented Generation (RAG) suffer from extit{factual myopia}: they relentlessly emphasize factual accuracy
arXiv:2605.07306v1 Announce Type: cross Abstract: Biological laboratory automation can reduce repetitive manual work and improve reproducibility, but reliable embodied execution in wet-lab environment
arXiv:2605.06981v1 Announce Type: cross Abstract: Personalized systems rely on user representations to connect behavioral history with downstream recommendation applications. Existing methods typicall
This article discusses AWS infrastructure, tools, and services designed to support the training and deployment of large foundation models, enabling machine learning practitioners to leverage AWS's com
arXiv:2605.07335v1 Announce Type: new Abstract: Virtual Cell Modeling (VCM) requires models that not only predict perturbation responses, but also support targeted revision when predictions fail. Curr
arXiv:2605.07782v1 Announce Type: new Abstract: LLMs can generate hardware descriptions from natural language specifications, but the resulting Verilog often contains width mismatches, combinational l
arXiv:2605.07162v1 Announce Type: new Abstract: Personalized LLMs can significantly enhance user experiences by tailoring responses to preferences such as helpfulness, conciseness, and humor. However,
arXiv:2605.07040v1 Announce Type: cross Abstract: Large language models (LLMs) are widely used for tutoring, feedback generation, and content creation, but their broad pretraining makes them hard to c
arXiv:2605.07764v1 Announce Type: new Abstract: Natural-language interfaces can make swarm robotics more accessible to non-expert operators, but they must translate ambiguous user intent into executab
arXiv:2510.07926v2 Announce Type: replace Abstract: Despite demonstrating remarkable performance across a wide range of tasks, large language models (LLMs) have also been found to frequently produce o
arXiv:2603.02274v2 Announce Type: replace-cross Abstract: Precision oncology is currently limited by the small-N, large-P paradox, where high-dimensional genomic data is abundant but pharmacological r
arXiv:2605.07024v1 Announce Type: new Abstract: Large Language Models for code generation frequently produce hallucinations in Fill-in-the-Middle (FIM) tasks -- plausible but incorrect completions suc
arXiv:2605.07011v1 Announce Type: new Abstract: Motivational-interviewing-based health coaching is an effective approach for improving mental health and promoting healthy behavior change. However, the
arXiv:2605.07675v1 Announce Type: new Abstract: We introduce FactoryBench, a benchmark for evaluating time-series models and LLMs on machine understanding over industrial robotic telemetry. Q&A pairs
arXiv:2605.07208v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly used to brainstorm and evaluate research ideas, yet assessing such judgments is fundamentally difficult be
arXiv:2504.11837v2 Announce Type: replace-cross Abstract: Emotional support conversation (ESC) aims to alleviate the emotional distress of individuals through effective conversations. Although large l
arXiv:2605.06920v1 Announce Type: cross Abstract: We propose incentive-aligned mechanisms for in-context credit assignment: the task of assigning credit for AI-generated content (e.g. code, news artic
arXiv:2605.07613v1 Announce Type: new Abstract: Conversational news recommendation requires grounding each suggestion in a rapidly evolving article corpus while addressing implicit user intents that l
arXiv:2510.01569v3 Announce Type: replace Abstract: We present InvThink, a training and prompting framework that requires the model to enumerate, analyze, and constrain potential failures before gener
arXiv:2605.07847v1 Announce Type: new Abstract: As user simulators are increasingly used for interactive training and evaluation of AI assistants, it is essential that they represent the diverse behav
arXiv:2605.06903v1 Announce Type: cross Abstract: Large language models are now embedded in everyday writing workflows, making reliable AI-generated text detection important for academic integrity, co
arXiv:2605.06895v1 Announce Type: new Abstract: How can we make models robust to even imperfect human feedback? In reinforcement learning from human feedback (RLHF), human preferences over model outpu
arXiv:2605.07140v1 Announce Type: cross Abstract: Skeleton-based human activity recognition has achieved strong empirical performance, yet most existing models remain black boxes and difficult to inte
arXiv:2605.07572v1 Announce Type: new Abstract: When applying Bayesian optimization (BO) to scientific workflow, a major yet often overlooked source of uncertainty is the task itself -- namely, what t
arXiv:2603.04678v2 Announce Type: replace-cross Abstract: Large language models are known to often exhibit inconsistent knowledge. This is particularly problematic in multilingual scenarios, where mod
arXiv:2511.22316v2 Announce Type: replace Abstract: Large Language Models (LLMs) quantization facilitates deploying LLMs in resource-limited settings, but existing methods that combine incompatible gr
arXiv:2512.14018v2 Announce Type: replace-cross Abstract: Large language models (LLMs) have achieved remarkable progress in automatic code generation, yet their ability to produce high-performance cod
arXiv:2509.26272v3 Announce Type: replace Abstract: The rapid rise of synthetic media has made deepfake detection a critical challenge for online safety and trust. Progress remains constrained by the
Your AI coding agent, the one you use to write code, needs to reduce your maintenance costs. Not by a little bit, either. You write code twice as quick now? Better hope you’ve halved your maintenance
arXiv:2605.06483v2 Announce Type: replace Abstract: Signal Temporal Logic (STL) is an expressive formal language for specifying spatio-temporal requirements over real-valued, real-time signals. It has
arXiv:2605.07164v1 Announce Type: new Abstract: Self-evolving agents improve by accumulating and reusing experience from past interactions. Existing work has largely focused on how experience is const
arXiv:2605.07022v1 Announce Type: new Abstract: Manually curated biomedical repositories -- spanning bioactivity, genomics, and chemistry -- are expensive to maintain, lag behind primary literature, a
arXiv:2605.06822v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed for autonomous financial trading, a domain requiring continuous adaptation to noisy, non-stationa
arXiv:2605.07093v1 Announce Type: cross Abstract: The Translation Tax is often treated as a scalar: translated benchmarks are assumed to inflate scores by preserving English-source cues. We audit this
arXiv:2512.03454v4 Announce Type: replace-cross Abstract: Interpreting natural-language commands to localize target objects is critical for autonomous driving (AD). Existing visual grounding (VG) meth
arXiv:2605.07158v1 Announce Type: cross Abstract: Vector search and retrieval-augmented generation (RAG) rest on the assumption that cosine similarity between text embeddings reflects conceptual relat
arXiv:2605.07172v1 Announce Type: new Abstract: Alignment of large language models (LLMs) via SFT and RLHF/DPO typically ignores the global geometry of the representation space, relying instead on loc
arXiv:2605.07986v1 Announce Type: cross Abstract: AI measurement science has a wide variety of methodologies and measurements for comparing AI systems, resulting in what often appear to be 'apples-to-
arXiv:2605.08054v1 Announce Type: new Abstract: Generating human motion that satisfies customized zero-shot goal functions, enabling applications such as controllable character animation and behavior
arXiv:2509.11777v2 Announce Type: replace Abstract: Customer feedback in industrial forums offers rich but underexplored insights into real-world product experience. Yet systematic analysis remains ch
arXiv:2605.07481v1 Announce Type: cross Abstract: In this paper, we investigate the recent state-of-the-art schemes for watermarking large language models (LLMs) outputs. These techniques are claimed
arXiv:2506.21582v5 Announce Type: replace-cross Abstract: Text analytics has traditionally required specialized knowledge in Natural Language Processing (NLP) or text analysis, which presents a barrie
arXiv:2605.05848v2 Announce Type: replace-cross Abstract: Video large multimodal models increasingly face a scalability bottleneck: long videos produce excessively long visual-token sequences, which s
arXiv:2605.06708v1 Announce Type: cross Abstract: Visual text compression (VTC) promises efficient long-context processing by rendering text into an image and re-encoding it with a vision-language mod
arXiv:2605.06761v1 Announce Type: new Abstract: The web is complex, open-ended, and constantly changing, making it challenging to scale training data for visual web agents. Existing data collection at
arXiv:2605.07533v1 Announce Type: new Abstract: Large Language Models (LLMs) have recently demonstrated strong performance in machine translation (MT). However, most prior work focuses on improving or
arXiv:2605.06992v1 Announce Type: new Abstract: AI agents are increasingly deployed in multi-task settings, where the task to perform is specified at test time, and the agent must generalize to unseen
arXiv:2605.07579v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) for Large Reasoning Models hinges on baseline estimation for variance reduction, but existing ap
> shipped the agent > opened the dashboard > latency: fine > error rate: fine > users: unhappy > checked the responses > technically correct > wrong tool called 3 steps earlier > no trace to follow >
Mark: 1/ First milestone: the Physical Turing Test. You literally can’t tell if a human or robot is doing the task. 2/ Next: Physical API. A fleet of robots, configured like software via APIs & CLI. 3
concluding my 'taking deep agents to production' series with arguably the most important component: observability. when you deploy a deep agent with LangSmith, you automatically get traces for every r
I promise this will be the best 20 min you spend today! Robotics: Endgame, the sequel to my last year's Sequoia AI Ascent talk, 'Physical Turing Test'. I laid out the roadmap for solving Physical AGI
Jim is always a crowd favorite at AI Ascent. His ability to simplify the latest research into a clear 'what and why it matters' while adding humor along the way is unmatched. If you're interested in p
Our crowd favorite from last year’s AI Ascent is back for round 2… this time: Robotics The Endgame ♟️ thank you for dazzling us @DrJimFan ! You can see the forest from the trees and are quite the ente
v0.30.0-rc7 is a release candidate version of Ollama, a platform for running large language models. This pre-release build was recently pushed to Docker repositories and represents testing iterations
arXiv:2605.03117v1 Announce Type: cross Abstract: Repository-level fault localization (FL) and automated program repair (APR) require an agent to identify the relevant code units across files, follow
arXiv:2602.19041v2 Announce Type: replace Abstract: A recurring challenge in preference fine-tuning (PFT) is handling extit{intransitive} (i.e., cyclic) preferences. Intransitive preferences often ste
Behind the Scenes Hardening Firefox with Claude Mythos Preview Fascinating, in-depth details on how Mozilla used their access to the Claude Mythos preview to locate and then fix hundreds of vulnerabil
arXiv:2605.04400v1 Announce Type: cross Abstract: While Separate Source-Channel Coding (SSCC) retains the practical benefits of modular system design, its effectiveness in noisy text transmission is f