Knowledge catalogue
arXiv:2609.38256v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used to answer questions about politically contentious issues, yet evaluations typically treat a model's s
I've run the benchmark on a RTX 3090, 1024 tokens in / 256 out, concurrency 1–32. If the model fits on vRAM (Gemma-4-26B-A4B, byte-identical GGUF on both engines): llama.cpp has 2.2–3.2× the throughpu
arXiv:2609.39566v1 Announce Type: new Abstract: Foundation models can serve as clinical agents through tool-use harnesses. However, conventional medical benchmarks assess reasoning over preselected ev
arXiv:2609.38312v1 Announce Type: cross Abstract: The Platonic Representation Hypothesis predicts that sufficiently scaled foundation models converge on a shared representation of the world. As each n
arXiv:2609.40071v1 Announce Type: cross Abstract: Digital twins increasingly support downstream analytical tasks that depend on time-series data, motivating interest in time-series foundation models (
arXiv:2506.21734v4 Announce Type: replace Abstract: Reasoning, the process of devising and executing complex goal-oriented action sequences, remains a critical challenge in AI. Current large language
arXiv:2607.15870v2 Announce Type: replace Abstract: Human label variation in natural language inference is increasingly treated as signal rather than noise, but how much of it formal semantic structur
arXiv:2609.40127v1 Announce Type: cross Abstract: Modern transformers pair impressive capabilities with substantial memory and compute demands. Low-rank weight factorization reduces both while keeping
arXiv:2609.40219v1 Announce Type: cross Abstract: World Action Models (WAMs) couple visual dynamics prediction with action generation, yet they do not explicitly support the reuse of action experience
arXiv:2609.38743v1 Announce Type: new Abstract: LLM agents rely on retrieval tools to access external knowledge, yet visual agentic search remains severely bottlenecked by standard single-step retriev
arXiv:2609.39957v1 Announce Type: cross Abstract: Coding agents solve repository-level tasks through sequences of actions, where a single erroneous action can misdirect subsequent decisions and increa
arXiv:2609.39882v1 Announce Type: new Abstract: Pre-training equips large language models (LLMs) with a broad repertoire of behavioral patterns associated with roles, styles, values, and goals. Post-t
arXiv:2609.40222v1 Announce Type: new Abstract: When a camera revisits a previously observed region, a video world model should reproduce what was there before. This requires both remembering past obs
arXiv:2609.39870v1 Announce Type: new Abstract: World-action models (WAMs) augment robot policies with action-conditioned environment dynamics, yet existing approaches largely rely on future observati
arXiv:2609.38543v1 Announce Type: new Abstract: Constantly evolving real-world knowledge necessitates models to be updated continuously. Especially in medicine, as clinical evidence changes over time,
arXiv:2609.39765v1 Announce Type: new Abstract: Agent memory faces heterogeneous access needs: a single-hop question may require one piece of evidence, whereas a multi-hop question must combine eviden
arXiv:2609.38587v1 Announce Type: new Abstract: Electroencephalography (EEG) is recorded continuously over hours, with relevant dynamics spanning timescales from milliseconds to hours. Most EEG founda
arXiv:2609.38691v1 Announce Type: new Abstract: Streaming video generators allow users to dynamically modulate video synthesis via mid-stream prompt switching. Existing streaming methods can respond t
arXiv:2609.39490v1 Announce Type: cross Abstract: Recent advances have enabled unified omni-modal models in understanding audio, vision, and language. However, existing benchmarks, training data, and
arXiv:2609.39150v1 Announce Type: new Abstract: Omni-modal large language models deployed in real-world environments encounter external noise that can interfere with their perception and understanding
arXiv:2609.39884v1 Announce Type: cross Abstract: Role prompting elicits specialized behavior from large language models through an expert identity, offering a lightweight way to guide reasoning on de
arXiv:2609.39903v1 Announce Type: new Abstract: Scientific software presents a demanding test for computer-using agents based on visual language models (VLMs): completing a research workflow requires
arXiv:2609.38782v1 Announce Type: new Abstract: Conversational agents increasingly interact with children, yet evidence on how their design shapes children's susceptibility to persuasion comes almost
arXiv:2609.38857v1 Announce Type: new Abstract: Retrieving objects from dense clutter requires rearrangement during which the manipulator can occlude objects while moving them. Repeated arm withdrawal
arXiv:2609.38926v1 Announce Type: cross Abstract: Long-term precipitation nowcasting requires modeling radar-echo evolution while preserving localized high-intensity structures. Recent radar-specific
arXiv:2609.38795v1 Announce Type: new Abstract: Block drafters for speculative decoding are commonly trained on corpora written by external models, where a single off-policy token invalidates supervis
arXiv:2609.39518v1 Announce Type: new Abstract: Effective human-AI collaboration requires partners to establish references through interaction, which becomes fragile when descriptions are ambiguous, s
arXiv:2609.39149v1 Announce Type: new Abstract: Textual skills enable large language model (LLM) based agents to accumulate reusable procedural knowledge without updating model parameters. Yet existin
arXiv:2609.39451v1 Announce Type: new Abstract: Progressive autoregressive image codecs provide an appealing paradigm for generative compression by quantizing continuous latents into discrete tokens,
arXiv:2503.19081v2 Announce Type: replace Abstract: Scientific foundation models (SciFMs) aim to learn generalizable representations of physical systems governed by partial differential equations (PDE
arXiv:2609.38526v1 Announce Type: cross Abstract: Scaling laws for optimization against reward models in AI alignment have pinned down how performance depends on optimization effort---measured by a KL
arXiv:2609.39384v1 Announce Type: new Abstract: Long-horizon surgical assistance requires humanoid robots to coordinate with evolving human activities while maintaining safety across planning and exec
arXiv:2609.39685v1 Announce Type: cross Abstract: Long-horizon robot manipulation reuses skills across many task compositions, but improving these compositions with additional end-to-end demonstration
arXiv:2609.38491v1 Announce Type: new Abstract: Clinical research in psychiatry increasingly relies on large scale collection of spoken language data to identify acoustic and linguistic biomarkers. Ye
arXiv:2609.40198v1 Announce Type: cross Abstract: Speech-to-speech systems must solve tasks whose requirements emerge across conversational turns. We introduce SpeechConversationBench (SCB), a focused
arXiv:2609.39082v1 Announce Type: new Abstract: As new evidence arrives, a sequence model must update what it remembers and how memory influences predictions. While Transformers incur computation and
arXiv:2603.02561v2 Announce Type: replace-cross Abstract: Attention mechanism remains the defining operator in Transformers since it provides expressive global credit assignment, yet its quadratic cos
arXiv:2609.39570v1 Announce Type: new Abstract: Trajectory planning is a core component of autonomous driving systems, where real-time performance and solution quality directly affect safety and relia
arXiv:2609.38984v1 Announce Type: cross Abstract: World-action models (WAMs) leverage pretrained video models to improve generalization in robot control by jointly predicting future visual states and
arXiv:2609.38636v1 Announce Type: new Abstract: We introduce Scene Text Editing with Preserved Style (STEPS), a novel diffusion model architecture for quality text replacement in images. Scene Text Ed
arXiv:2609.39034v1 Announce Type: cross Abstract: Designing expressive sequence layers with efficient inference remains a central challenge in modern machine learning. Standard softmax attention achie
arXiv:2609.38389v1 Announce Type: cross Abstract: Large language models (LLMs) remain vulnerable to adversarial attacks that circumvent safety alignment to elicit harmful outputs. It remains unclear h
arXiv:2609.39578v1 Announce Type: new Abstract: Agent harnesses often improve language models with human-designed workflows, but as models grow more capable, unreliable guidance can increasingly const
arXiv:2603.21144v2 Announce Type: replace-cross Abstract: This paper proposes a new formulation of functional Gaussian Process regression on manifolds, based on an Empirical Bayes approach, in the spa
To clarify: this was satire. I wasn’t fired from OpenAI. The underlying issue is serious: how do we independently verify AI-generated code, and who is accountable when mistakes reach production? This
vLLM's tensor parallel requires that several of the model architecture numbers be evenly divisible by the number of GPUs selected for tensor parallel. This usually means that you can only use a number
arXiv:2609.39157v1 Announce Type: new Abstract: Video object removal presents a uniquely difficult editing challenge. Because a removal prompt specifies only what to erase rather than what to generate
arXiv:2609.39086v1 Announce Type: cross Abstract: Runtime error healing lets a crashed program continue by generating code that repairs its live runtime state. Recent work shows that LLMs can generate
arXiv:2609.38802v1 Announce Type: cross Abstract: Uncontrolled repetition can prolong autoregressive generation in large language models (LLMs) and enable resource consumption attacks. Prior analyses
arXiv:2609.38721v1 Announce Type: new Abstract: Modern multimodal models bring generation and understanding into a single unified system, which enables them to provide and learn from their own feedbac
arXiv:2609.39701v1 Announce Type: new Abstract: Value steering should change an LLM's normative priorities while preserving the scenario, facts, and task constraints underlying its answer. Conventiona
arXiv:2609.38270v1 Announce Type: cross Abstract: Advancing beyond traditional static scoring models, LLM-powered agentic recommender systems (LLM-ARS) instantiate users and items as autonomous agents
arXiv:2609.39374v1 Announce Type: cross Abstract: Synthetic time series are increasingly used for data augmentation, privacy-preserving data sharing, and downstream model development, yet faithfully r
arXiv:2609.38494v1 Announce Type: cross Abstract: Robotic manipulation integrates vision, touch, and language, whose importance shifts across stages: vision guides reaching, while touch, through its e
arXiv:2609.39142v1 Announce Type: new Abstract: Can structured text replace vision for diagram reasoning? A wrong answer after textualization can arise because the representation omits information the
arXiv:2609.39483v1 Announce Type: new Abstract: Ownership establishes rights over the use, control, and transfer of objects. Understanding these relations is essential for AI systems to interact appro
arXiv:2609.39325v1 Announce Type: new Abstract: The ability of Large Language Model (LLM) agents to complete daily and professional work is receiving increasing attention. Training such agents require
arXiv:2609.37783v1 Announce Type: cross Abstract: Photographic evidence is becoming increasingly vulnerable to forms of alteration and fabrication that existing legal and technical workflows are not w
arXiv:2609.38142v1 Announce Type: new Abstract: A small trainable advisor can steer a frozen language-model executor using natural-language advice. In addition to learning from task rewards, the advis
arXiv:2609.37229v1 Announce Type: new Abstract: Human motion defines an action, while a camera trajectory determines how it is presented. Camera generation for a given human motion and joint human-cam