Knowledge catalogue
arXiv:2606.00267v1 Announce Type: cross Abstract: Video world models (WMs) have shown promise for policy evaluation and improvement by imagining realistic future observations conditioned on ego-robot
arXiv:2606.00999v1 Announce Type: new Abstract: Large-scale vision foundation models have driven substantial gains on dense prediction tasks such as semantic segmentation, but their size makes deploym
arXiv:2606.00851v1 Announce Type: cross Abstract: Empathetic spoken dialogue systems must infer a user's emotional state to respond appropriately, yet everyday speech often carries weak, neutral, or a
arXiv:2509.24696v2 Announce Type: replace-cross Abstract: Personalizing large language models (LLMs) to individual user preferences is a critical step beyond generating generically helpful responses.
arXiv:2606.01868v1 Announce Type: new Abstract: Reinforcement Learning (RL) has long served as a model for goal-directed animal behavior in neuroscience. Modern deep RL has shown remarkable success ac
Thanks everyone for reading! Longer version some additional points on crowd psychology and links to a pair of great new podcasts with the legendary investors @realsteveeisman and @gnoble79 and converg
arXiv:2606.00674v1 Announce Type: cross Abstract: Large Language Models (LLMs) aligned via outcome-based Reinforcement Learning (RL) frequently exhibit a critical failure mode: they achieve high perfo
The persistent and possibly industry-funded campaign to discredit me begins with a fundamental misunderstanding of my work. It’s worth taking the time to understand the issues, if you want to understa
The persistent campaign to discredit me begins with a fundamental misunderstanding of my work. It is worth taking the time to understand the issues, if you want to understand a lot of what is driving
Public opinion has shifted dramatically against data centers over a nine-month period, with a 49-point swing in unfavorable sentiment, reflecting growing political concern about these facilities. This
arXiv:2606.00344v1 Announce Type: new Abstract: Neural collapse is a structural property of the last-hidden-layer activations in neural network classification models, when trained beyond a zero classi
arXiv:2510.10943v2 Announce Type: replace-cross Abstract: Bias in large language models (LLMs) remains a persistent challenge, often leading to stereotyping and unfair treatment across social groups.
Things are so chaotic in AI right now that @axios had to specify *which* AI backlash they were referring to! Anthropic faces AI spending backlash before IPO https://www.axios.com/2026/06/02/anthropic-
arXiv:2606.00966v1 Announce Type: new Abstract: Vision-Language Action (VLA) models continue to face challenges such as slow inference speed and difficulty performing fine-grained motion adjustments,
🚨 Today is a milestone in US AI policy, and an unbelievable moment for me, personally. 🚨 Here’s what I told @senjohnkennedy was the most important policy to implement, at the US Senate in May 2023, an
arXiv:2606.02518v1 Announce Type: new Abstract: Fine-grained image classification (FGIC) has broad applications and has attracted significant research attention. In this paper, we explore a novel para
arXiv:2602.07883v3 Announce Type: replace Abstract: LLM-powered agentic systems excel at complex long-horizon tasks, but remain constrained by static configurations fixed before execution. Such rigidi
arXiv:2606.00596v1 Announce Type: new Abstract: Large language models have rapidly evolved in multilingual competence and reasoning capacity, enabling their integration into Social Sciences and Humani
arXiv:2606.02313v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models offer a promising end-to-end paradigm for unmanned aerial vehicles (UAVs) to accomplish complex tasks specified by f
arXiv:2606.00959v1 Announce Type: new Abstract: Understanding modality interaction in multimodal large language models (MLLMs) is central to reliable deployment. We introduce Partial Information Decom
arXiv:2606.01380v1 Announce Type: new Abstract: In this work, we introduce a novel training-free inversion (TFinv) framework for one-step diffusion models,addressing key challenges in real image inver
arXiv:2606.01238v1 Announce Type: cross Abstract: While diffusion-based policies have impressive performance and expressivity, their long offline training slows down the data collection and policy dep
arXiv:2510.03494v2 Announce Type: replace Abstract: We study finite-horizon offline reinforcement learning (RL) with function approximation for both policy evaluation and policy optimization. Prior wo
arXiv:2606.01755v1 Announce Type: new Abstract: Personalized large language models adapt responses to users' preferences and social attributes, but can introduce substantial universal truth inconsiste
arXiv:2606.02350v1 Announce Type: new Abstract: Reconstructing humans and their surrounding environments in a globally consistent 4D space is essential for comprehensive perception. However, prior wor
arXiv:2606.01249v1 Announce Type: cross Abstract: On-Policy Distillation (OPD) is a fundamental technique for efficient post-training of large language models (LLMs), with broad applications in agent
arXiv:2606.01322v1 Announce Type: cross Abstract: Safety evaluation of Large Language Models (LLMs) remains heavily English-centric, leaving Low-Resource Languages (LRLs), particularly African ones, c
arXiv:2606.01615v1 Announce Type: new Abstract: Video-language models are pivotal for tasks such as moment retrieval and highlight detection, yet they often struggle to capture the dynamic, non-linear
arXiv:2606.00170v1 Announce Type: cross Abstract: In recent years, emotion recognition based on physiological signals such as electroencephalogram (EEG) has gained considerable attention, as internal
arXiv:2606.02153v1 Announce Type: new Abstract: Methods using inertial measurement units (IMUs) provide a wearable alternative to camera-based motion capture. To mitigate drift from inertial signals,
Gary Marcus observes the unusual linguistic phenomenon of rarely contemplating the plural form of the word 'backlash,' highlighting how certain words are infrequently used in plural despite being gram
arXiv:2603.10282v2 Announce Type: replace Abstract: In recent years, Behavior Cloning (BC) has become one of the most prevalent methods for learning manipulation from human demonstrations. Despite the
arXiv:2606.00037v1 Announce Type: cross Abstract: Machine learning models embedded in deployed AI systems are routinely updated to maintain correct functioning over time. Yet such updates can generate
arXiv:2606.00508v1 Announce Type: cross Abstract: This study introduces an intriguing phenomenon in Video LLMs: rather than merely translating frames into textual embeddings, Video LLMs establish a co
arXiv:2506.13702v4 Announce Type: replace-cross Abstract: Single-trajectory preference optimization methods learn from datasets of ((prompt, response, reward)) tuples, offering a practical alternative
arXiv:2506.22666v3 Announce Type: replace-cross Abstract: The rise of API-only access to state-of-the-art LLMs highlights the need for effective black-box jailbreak methods to identify model vulnerabi
arXiv:2501.12178v2 Announce Type: replace Abstract: Medical imaging studies often rely on a single sample per subject, assuming it is representative of their physiological traits. However, variations
arXiv:2601.03309v2 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) models, which integrate pretrained large Vision-Language Models (VLM) into their policy backbone, are gaining sig
arXiv:2606.00689v1 Announce Type: new Abstract: Multimodal MRI provides complementary information for neuroimaging analysis, where different imaging modalities capture distinct anatomical, tissue, and
arXiv:2606.00424v1 Announce Type: new Abstract: As large language models become stronger, weak supervisors may fail to provide reliable labels, preferences, or final judgments for complex outputs, lim
arXiv:2601.21718v2 Announce Type: replace-cross Abstract: Behavior cloning (BC) is a practical offline imitation learning method, but it often fails when expert demonstrations are limited. Recent work
arXiv:2606.01671v1 Announce Type: new Abstract: In the contemporary epoch of multilingual education, learning idioms provides a fascinating gateway towards creativity, cultural values, historical cont
arXiv:2511.05613v2 Announce Type: replace-cross Abstract: Foundation models are increasingly central to high-stakes AI systems, and governance frameworks now depend on evaluations to assess their risk
Why things will eventually fall apart: 1. Everybody, even Google, seems to be treating AI as if it were some kind of winner take all competition like web search was, in which Google taking over 95% 2.
arXiv:2606.00113v1 Announce Type: new Abstract: Robotic manipulation depends on the ability to anticipate how actions reshape objects, contacts, and scene geometry before execution. Learned world mode
arXiv:2606.02027v1 Announce Type: cross Abstract: Robot learning must produce policies that generalize to new combinations of constraints, teammates, and environments. To achieve this, we must structu
arXiv:2602.03896v2 Announce Type: replace-cross Abstract: Poisson-distributed latent variable models are widely used in computational neuroscience, but differentiating through discrete stochastic samp
arXiv:2605.30843v1 Announce Type: new Abstract: In the forward reinforcement-learning problem, the reward is fixed and known; the learner is asked to find a good policy or value function. Here we turn
arXiv:2605.31021v1 Announce Type: new Abstract: Current alignment paradigms for generative artificial intelligence rely predominantly on monolithic benchmarking frameworks that reduce the plurality of
arXiv:2605.30452v1 Announce Type: cross Abstract: Many machine learning problems involve multiple inherent trade-offs that are best addressed by gradient-based multi-objective optimization (MOO) algor
arXiv:2605.30625v1 Announce Type: cross Abstract: Inferring continuous probability paths from sparse snapshots is a fundamental challenge in domains like single-cell biology, where high-fidelity data
arXiv:2605.30406v1 Announce Type: cross Abstract: Recent research demonstrating AI systems exhibiting deception and shutdown resistance suggests that AI loss of control (LOC) is an urgent policy conce
arXiv:2605.31034v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) and group-based policy optimization methods such as GRPO update a stochastic policy by sampling
arXiv:2605.30742v1 Announce Type: new Abstract: This paper addresses the task of temporal sentence grounding (TSG). Although many respectable works have made decent achievements in this important topi
arXiv:2605.31490v1 Announce Type: new Abstract: On-policy distillation (OPD) provides dense teacher feedback along rollouts generated by the student and has emerged as a promising post-training paradi
arXiv:2605.31153v1 Announce Type: new Abstract: Given the surge of harmful AI-generated imagery online, reliably distinguishing authentic images from generated ones has become an urgent research topic
arXiv:2602.10117v5 Announce Type: replace-cross Abstract: Large Language Models (LLMs) often provide chain-of-thought (CoT) reasoning traces that appear plausible, but may hide internal biases. We cal
arXiv:2605.30972v1 Announce Type: new Abstract: Accurate 3D medical image segmentation requires both long-range volumetric context and fine boundary preservation. CNN-based methods have limited global
arXiv:2510.11683v3 Announce Type: replace-cross Abstract: A key challenge in applying reinforcement learning (RL) to diffusion large language models (dLLMs) is the intractability of their likelihood f
arXiv:2411.13865v4 Announce Type: replace-cross Abstract: Modern recommender systems often create information cocoons, restricting users' exposure to diverse content. The central challenge is to balan