Knowledge catalogue
arXiv:2605.30154v1 Announce Type: new Abstract: Correctness-based Reinforcement Learning with Verifiable Rewards (RLVR) trains language models from binary feedback on sampled outputs, but the objectiv
arXiv:2605.30049v1 Announce Type: new Abstract: Diffusion Transformers have become a powerful backbone for text-to-image generation, but their layered and cross-modal generation process makes safety c
arXiv:2603.00454v2 Announce Type: replace-cross Abstract: Generative Flow Networks (GFlowNets) enable fine-tuning large language models to approximate reward-proportional posteriors, but they remain p
arXiv:2605.29156v1 Announce Type: cross Abstract: Pointwise reward modeling offers critical signals for LLM post-training, yet struggles with absolute scoring in subjective, non-verifiable settings. R
arXiv:2605.29310v1 Announce Type: new Abstract: Stepwise model routing improves the efficiency of Large Reasoning Models (LRMs) by assigning each reasoning step to a suitable model. Recent methods for
arXiv:2605.29146v1 Announce Type: cross Abstract: Medication recommendation predicts medications for patient visits, but existing methods still face two key challenges. At the model level, traditional
arXiv:2605.30166v1 Announce Type: cross Abstract: LLM-driven social bots can generate fluent, human-like text, reducing the discriminative advantage of content-based detection alone. However, coordina
arXiv:2605.30251v1 Announce Type: cross Abstract: Large language models (LLMs) often solve a task when all instructions are given in a single prompt, but fail when the same information is revealed gra
arXiv:2602.13238v2 Announce Type: replace-cross Abstract: Stacked intelligent metasurfaces (SIMs) have recently emerged as a powerful wave-domain technology that enables multi-stage manipulation of el
arXiv:2605.28863v1 Announce Type: cross Abstract: Imperfect-information multiplayer games test whether agents can act under hidden information, sparse rewards, and non-stationary opponents. We study t
arXiv:2605.30116v1 Announce Type: new Abstract: Distribution Matching Distillation (DMD) is a widely used paradigm for accelerating inference in few-step video diffusion models. However, DMD-style vid
Gary Marcus criticizes Apple's email filtering system for incorrectly routing Mark Cuban's message to spam, highlighting a failure in Apple's spam detection algorithm. The post reflects concerns about
arXiv:2605.29236v1 Announce Type: new Abstract: Alarm fatigue in intensive care units (ICUs) is a well documented patient safety crisis. Clinical monitors generate 350 or more alarms per patient per d
arXiv:2605.30289v1 Announce Type: new Abstract: Numeric tabular datasets are the dominant data format in scientific practice, yet large language models lack native mechanisms for representing numeric
This post by cognitive scientist Gary Marcus appears to comment humorously on political or ideological conformity, suggesting that people and leaders flip their positions based on party alignment rath
arXiv:2605.30036v1 Announce Type: new Abstract: Large Language Models (LLMs) demonstrate a remarkable capacity to adopt different personas and roles; however, it remains unclear whether they can manif
arXiv:2601.03134v2 Announce Type: replace Abstract: As LLMs gain persuasive capabilities through extended dialogues, they create new opportunities for studying adversarial conversational behavior in e
arXiv:2512.10388v2 Announce Type: replace-cross Abstract: Conventional Sequential Recommender Systems (SRS) typically assign unique hash IDs (HID) to construct item embeddings, which mainly capture co
arXiv:2605.29123v1 Announce Type: new Abstract: Masked diffusion language models (MDMs) uniquely support any-order generation, with confidence-based decoding currently serving as the de facto standard
arXiv:2605.29082v1 Announce Type: new Abstract: AI agents are increasingly expected to operate as digital employees: accessing enterprise data, making decisions, and taking actions autonomously. But a
arXiv:2605.29645v1 Announce Type: cross Abstract: We study contextual bandits in the stochastic i.i.d. setting, where a learner observes contexts drawn from an unknown distribution, selects actions fr
arXiv:2605.29032v1 Announce Type: new Abstract: Model-based reinforcement learning (MBRL) agents typically learn world models by minimizing predictive loss. However, powerful RL optimizers inevitably
arXiv:2605.29652v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly being used to generate health text from structured records such as wearable time series, biomarkers, vital
this is on track to be this year’s “what did Ilya see?” rumor that people love that has nothing to do with reality. Im calling BS on this story. 1. That would be 100,000 employees spending 5k/mo each
Today I learned that @Grimezsz has more courage in her pinky than Roon does in his entire cowardly body. Roon made excuses; Grimes defended her views calmly and respectfully, like grownups should. Ope
Tokenmaxxing is so done. TOKENS OR HUMANS? The new corporate trade off as AI costs balloon 'This is the first time ever that I can remember that technology costs the same as people' - @jainarvind 'Com
arXiv:2605.29930v1 Announce Type: new Abstract: Mutual misunderstanding in contemporary society does not arise merely because people hold different opinions or values. Even under the same observations
arXiv:2605.29141v1 Announce Type: cross Abstract: Traditional recommender systems (RecSys) primarily infer user preferences from implicit signals (such as clicks, watches, and purchases), often neglec
arXiv:2605.29430v1 Announce Type: new Abstract: Automatic speech recognition (ASR) is a core component of human--computer interaction and an increasingly important front-end for LLM-based assistants a
arXiv:2605.29941v1 Announce Type: cross Abstract: Critical networking workflows require high-fidelity packet captures (PCAPs) for testing, security analysis, and protocol validation, not just statisti
arXiv:2605.29380v1 Announce Type: cross Abstract: Mainstream strategies for finetuning pretrained multimodal models often degrade out-of-distribution (OOD) robustness, a phenomenon known as catastroph
arXiv:2605.29894v1 Announce Type: new Abstract: Recent progress in computer vision has produced a wide range of powerful specialized models for detection, segmentation, counting, and other visual task
arXiv:2605.30220v1 Announce Type: new Abstract: We introduce TriSearch, a reinforcement learning framework for optimizing objectives over triangulations of a polytope via bistellar flips. The key idea
arXiv:2605.05964v2 Announce Type: replace Abstract: Quantifying uncertainty in neural network predictions is essential for high-stakes domains such as autonomous driving, healthcare, and manufacturing
arXiv:2605.29715v1 Announce Type: new Abstract: Emotional support plays an important role in dialogue systems, and its success depends on adapting to a user's evolving and implicit needs across multi-
arXiv:2605.29471v1 Announce Type: new Abstract: Collaborative driving systems leverage vehicle-to-everything (V2X) communication for multi-agent collaborative perception to enhance driving safety, yet
arXiv:2602.08567v2 Announce Type: replace-cross Abstract: Multi-agent large language model (LLM) systems increasingly consist of agents that observe and respond to one another's outputs. While value a
arXiv:2605.30117v1 Announce Type: new Abstract: Understanding how Vision-Language-Action (VLA) models transform multimodal knowledge into embodied control remains an open challenge. We present VLA-Tra
Was this priced into the $965 billion valuation? This looks like the beginning of the end for OpenAI and Anthropic. The Chinese AI wave did not just cut prices. It destroyed the entire funding logic b
arXiv:2605.29267v1 Announce Type: new Abstract: Foundation models are increasingly trained on synthetic data generated by prior model iterations rather than exclusively on real data. This self-consumi
arXiv:2605.29126v1 Announce Type: cross Abstract: A linear probe can decode a representation almost perfectly and yet be completely irrelevant to how the model uses it. On calendar-date duration reaso
arXiv:2605.30111v1 Announce Type: cross Abstract: Point cloud segmentation is a fundamental task in 3D scene understanding. Its progress is constrained by the high cost and time required for dense 3D
yes, absolutely, many companies are experimenting. but also: most of those experiments are failing to yield significant RoI. (weird for an economist to not even ask or address that question.) Looks li
you break it, you buy it peter thiel has broken the united states, and now he is abandoning it Peter Thiel has temporarily relocated his family to Argentina, enrolled his children in school there, and
1. Agreed that OpenAI is in deep trouble; that’s why I have long suggested that it might be the WeWork of AI but 2. Anthropic is not out of the woods; their best quarter was exactly when tokenmaxxing
arXiv:2509.15848v2 Announce Type: replace Abstract: Industrial monitoring systems, especially when deployed in Industry 4.0 environments, are experiencing a shift in paradigm from traditional rule-bas
arXiv:2605.27461v1 Announce Type: new Abstract: Vision-Language-Action (VLA) policies have shown promising manipulation capabilities, yet their practical impact is often limited by the reliability dem
arXiv:2605.27744v1 Announce Type: new Abstract: Multi-agent LLM systems have become the dominant production workload, but the serving stack was not built for them. The agent framework above knows agen
arXiv:2602.16837v2 Announce Type: replace Abstract: Transformer models systematically favor certain token positions, yet the architectural origins of this position bias remain poorly understood. This
arXiv:2605.28664v1 Announce Type: cross Abstract: Safety detection models require examples of HHH (Helpful, Harmless, Honest)-violating outputs for robust generalization, however such examples are sca
arXiv:2410.04498v2 Announce Type: replace Abstract: In sparse reward scenarios of reinforcement learning (RL), the memory mechanism provides promising shortcuts to policy optimization by reflecting on
arXiv:2605.28396v1 Announce Type: cross Abstract: On-policy distillation (OPD) transfers reasoning behavior by training a student on teacher feedback along student-generated trajectories, but standard
arXiv:2605.28810v1 Announce Type: new Abstract: Functional music applications, from consumer focus and sleep aids to clinical interventions, share a distinctive recommendation problem: success is defi
arXiv:2605.27466v1 Announce Type: cross Abstract: Multi-agent systems built on large language models (LLMs) require many coordination choices that are difficult to fix a priori: which skill protocol t
arXiv:2605.28774v1 Announce Type: new Abstract: Vision-language models with extended reasoning succeed on complex problems, but many real-world problems require external tools that internal reasoning
arXiv:2605.27621v1 Announce Type: cross Abstract: As multi-agent systems (MAS) become increasingly complex, identifying the contributions of individual agents is critical for system optimization. Howe
AI systems may soon help run economies, infrastructure, and military operations. But these systems are not reliably loyal or secure. An adversary can make an AI work against its own operator. In our n
arXiv:2605.28255v1 Announce Type: new Abstract: AI systems are fallible, and humans can make mistakes in deciding whether to trust AI over their own judgment. Thus, improving human-AI collaboration re
Gary Marcus raises a philosophical question about whether calculators, despite their computational capabilities, might possess consciousness. The post likely explores the disconnect between functional
Almost everyone is building agent harness systems the wrong way. The default move: pick LangChain or LangGraph or the OpenAI Agents SDK, accept the loop, the tools, the memory, the orchestration, the