Newest and Lowest Rated Papers

Abstract Objective To quantify the time lag between biomedical articles and the studies they describe as “recent,” a term widely used to imply timeliness despite rarely reflecting the actual age of the cited evidence. Design Retrospective analysis of suspiciously timeless citations based on a structured PubMed search of 20 predefined “recent” expressions. Sample 1000 English language, full text biomedical articles in which a “recent” expression is directly linked to a citation. Main outcome measure Time lag in years between citing articles and their referenced “recent” studies. Results The age of the cited “recent” studies varied widely. The citation lag ranged from 0 to 37 years (mean 5.53 years, median 4 years, interquartile range 2-7). The most frequent lag was one year (n=159, 15.9%), and 177 references (17.7%) were at least 10 years old. Citation patterns varied across medical specialties: critical care, infectious diseases, genetics, immunology, and radiology showed shorter median lags (around two years), while nephrology, veterinary medicine, and dentistry displayed substantially longer lags (ranging from 8.5 to 14 years). Among expressions, “recent approach,” “recent discovery,” and “recent study” were linked to older references, whereas “recent publication” and “recent article” had much fresher citations. The citation lag was similar across world regions and gradually decreased over time, with the most recent publications showing the shortest lags. Journals with high impact factors (≥12) cited more up-to-date work. Conclusions This playful analysis suggests that “recent” is applied with striking elasticity across biomedical literature. While some authors cite genuinely recent work, others stretch the definition to decades. Readers and reviewers should take “recent” claims with a grain of chronological salt.

No ratings yet

View paper →

PreviousPage 357 of 506Next

Closing the Train-Test Gap in World Models for Gradient-Based Planning

Arjun Parthasarathy, Nimit Kalra, Rohun Agrawal, Yann LeCun, Oumayma Bounou, Pavel Izmailov, Micah Goldblum

arXiv·2025

World models paired with model predictive control (MPC) can be trained offline on large-scale datasets of expert trajectories and enable generalization to a wide range of planning tasks at inference time. Compared to traditional MPC procedures, which rely on slow search algorithms or on iteratively solving optimization problems exactly, gradient-based planning offers a computationally efficient alternative. However, the performance of gradient-based planning has thus far lagged behind that of other approaches. In this paper, we propose improved methods for training world models that enable efficient gradient-based planning. We begin with the observation that although a world model is trained on a next-state prediction objective, it is used at test-time to instead estimate a sequence of actions. The goal of our work is to close this train-test gap. To that end, we propose train-time data synthesis techniques that enable significantly improved gradient-based planning with existing world models. At test time, our approach outperforms or matches the classical gradient-free cross-entropy method (CEM) across a variety of object manipulation and navigation tasks in 10% of the time budget.

No ratings yet

View paper →

SPIN: Simultaneous Perception, Interaction and Navigation

Shagun Uppal, Ananye Agarwal, Haoyu Xiong, Kenneth Shaw, Deepak Pathak

arXiv·2024

While there has been remarkable progress recently in the fields of manipulation and locomotion, mobile manipulation remains a long-standing challenge. Compared to locomotion or static manipulation, a mobile system must make a diverse range of long-horizon tasks feasible in unstructured and dynamic environments. While the applications are broad and interesting, there are a plethora of challenges in developing these systems such as coordination between the base and arm, reliance on onboard perception for perceiving and interacting with the environment, and most importantly, simultaneously integrating all these parts together. Prior works approach the problem using disentangled modular skills for mobility and manipulation that are trivially tied together. This causes several limitations such as compounding errors, delays in decision-making, and no whole-body coordination. In this work, we present a reactive mobile manipulation framework that uses an active visual system to consciously perceive and react to its environment. Similar to how humans leverage whole-body and hand-eye coordination, we develop a mobile manipulator that exploits its ability to move and see, more specifically -- to move in order to see and to see in order to move. This allows it to not only move around and interact with its environment but also, choose "when" to perceive "what" using an active visual system. We observe that such an agent learns to navigate around complex cluttered scenarios while displaying agile whole-body coordination using only ego-vision without needing to create environment maps. Results visualizations and videos at https://spin-robot.github.io/

No ratings yet

View paper →

Eliezer's Unteachable Methods of Sanity

Eliezer Yudkowsky

LessWrong·2025

"How are you coping with the end of the world?" journalists sometimes ask me, and the true answer is something they have no hope of understanding and I have no hope of explaining in 30 seconds, so I usually answer something like, "By having a great distaste for drama, and remembering that it's not about me." The journalists don't understand that either, but at least I haven't wasted much time along the way. Actual LessWrong readers also sometimes ask me how I deal emotionally with the end of the world. I suspect a more precise answer may not help. But Raymond Arnold thinks I should say it, so I will say it. I say again, I don't actually think my answer is going to help. Wisely did Ozy write, "Other People Might Just Not Have Your Problems." Also I don't have a bunch of other people's problems, and other people can't make internal function calls that I've practiced to the point of hardly noticing them. I don't expect that my methods of sanity will be reproducible by nearly anyone. I feel pessimistic that they will help to hear about. Raymond Arnold asked me to speak them anyways, so I will. ---------------------------------------- Stay genre-savvy / be an intelligent character. The first and oldest reason I stay sane is that I am an author, and above tropes. Going mad in the face of the oncoming end of the world is a trope. I consciously see those culturally transmitted patterns that inhabit thought processes aka tropes, both in fiction, and in the narratives tha...

No ratings yet

View paper →

pre-code lesbian cinema, a list of films by mich, Letterboxd

mich

letterboxd.com·2024

A list of 23 films compiled on Letterboxd, including Wings (1927), Children of Divorce (1927), The Docks of New York (1928), Our Dancing Daughters (1928) and The Wild Party (1929). About this list: disclaimer: this is likely not a complete list, but rather a list to kickstart your journey into pre-code lesbian cinema! note that by “pre-code lesbian” most of these films will include some reference whether overtly or covertly to lesbianism. since the films are from the early 1900s, this list may also include films where: • the women are “queer” in the eyes of modern audiences • they contain homoerotic subtext • the women could be interpreted as a lesbian today, but did not clearly portray one then under film/social constraints enjoy! (films are listed in chronological order)

No ratings yet

View paper →

Posterior Behavioral Cloning: Pretraining BC Policies for Efficient RL Finetuning

Andrew Wagenmaker, Perry Dong, Raymond Tsao, Chelsea Finn, Sergey Levine

arXiv·2025

Standard practice across domains from robotics to language is to first pretrain a policy on a large-scale demonstration dataset, and then finetune this policy, typically with reinforcement learning (RL), in order to improve performance on deployment domains. This finetuning step has proved critical in achieving human or super-human performance, yet while much attention has been given to developing more effective finetuning algorithms, little attention has been given to ensuring the pretrained policy is an effective initialization for RL finetuning. In this work we seek to understand how the pretrained policy affects finetuning performance, and how to pretrain policies in order to ensure they are effective initializations for finetuning. We first show theoretically that standard behavioral cloning (BC) -- which trains a policy to directly match the actions played by the demonstrator -- can fail to ensure coverage over the demonstrator's actions, a minimal condition necessary for effective RL finetuning. We then show that if, instead of exactly fitting the observed demonstrations, we train a policy to model the posterior distribution of the demonstrator's behavior given the demonstration dataset, we do obtain a policy that ensures coverage over the demonstrator's actions, enabling more effective finetuning. Furthermore, this policy -- which we refer to as the posterior behavioral cloning (PostBC) policy -- achieves this while ensuring pretrained performance is no worse than that of the BC policy. We then show that PostBC is practically implementable with modern generative models in robotic control domains -- relying only on standard supervised learning -- and leads to significantly improved RL finetuning performance on both realistic robotic control benchmarks and real-world robotic manipulation tasks, as compared to standard behavioral cloning.

No ratings yet

View paper →

From Model Training to Model Raising

Roland Aydin, Christian Cyron, Steve Bachelor, Ashton Anderson, Robert West

arXiv·2025

Current AI training methods align models with human values only after their core capabilities have been established, resulting in models that are easily misaligned and lack deep-rooted value systems. We propose a paradigm shift from "model training" to "model raising", in which alignment is woven into a model's development from the start. We identify several key components for this paradigm, all centered around redesigning the training corpus: reframing training data from a first-person perspective, recontextualizing information as lived experience, simulating social interactions, and scaffolding the ordering of training data. We expect that this redesign of the training corpus will lead to an early commitment to values from the first training token onward, such that knowledge, skills, and values are intrinsically much harder to separate. In an ecosystem in which large language model capabilities start overtaking human capabilities in many tasks, this seems to us like a critical need.

No ratings yet

View paper →

Newest and Lowest Rated Papers

How Christianity Lost James Baldwin -

The Israel Exemption

How recent is recent? Retrospective analysis of suspiciously timeless citations

Closing the Train-Test Gap in World Models for Gradient-Based Planning

SPIN: Simultaneous Perception, Interaction and Navigation

State of Robot Learning, December 2025

Eliezer's Unteachable Methods of Sanity

Navigation World Models

Frontal pseudoalopecia in history: Part 2—Cultural forms

pre-code lesbian cinema, a list of films by mich, Letterboxd

Posterior Behavioral Cloning: Pretraining BC Policies for Efficient RL Finetuning

From Model Training to Model Raising