Source author record

Nicholas Asher

Explore this author’s publications, collaborators and research topics. This catalog record has not been claimed by its author.

ResearcherUnclaimed source record

Artificial Intelligence Computation and Language Computer Science and Game Theory Computer Vision Logic in Computer Science Machine Learning

Catalog footprint

Research overview

5works

6topics

4close collaborators

Actions

Is this your work?

Open graph Browse papers

preprint2026arXiv

Minimal Clips, Maximum Salience: Long Video Summarization via Key Moment Extraction

Vision-Language Models (VLMs) are able to process increasingly longer videos. Yet, important visual information is easily lost throughout the entire context and missed by VLMs. Also, it is important to design tools that enable cost-effective analysis of lengthy video content. In this paper, we propose a clip selection method that targets key video moments to be included in a multimodal summary. We divide the video into short clips and generate compact visual descriptions of each using a lightweight video captioning model. These are then passed to a large language model (LLM), which selects the K clips containing the most relevant visual information for a multimodal summary. We evaluate our approach on reference clips for the task, automatically derived from full human-annotated screenplays and summaries in the MovieSum dataset. We further show that these reference clips (less than 6% of the movie) are sufficient to build a complete multimodal summary of the movies in MovieSum. Using our clip selection method, we achieve a summarization performance close to that of these reference clips while capturing substantially more relevant video information than random clip selection. Importantly, we maintain low computational cost by relying on a lightweight captioning model.

preprint2026arXiv

TAPIOCA: Why Task- Aware Pruning Improves OOD model Capability

Recent work has promoted task-aware layer pruning as a way to improve model performance on particular tasks, as shown by TALE. In this paper, we investigate when such improvements occur and why. We show first that, across controlled polynomial regression tasks and large language models, such pruning yields no benefit on in-distribution (ID) data but consistently improves out-of-distribution (OOD) accuracy. We further show empirically that OOD inputs induce layerwise norm and pairwise-distance profiles that deviate from the corresponding ID profiles. This leads to a geometric explanation of task-aware pruning: each task induces a task-adapted geometry, characterized empirically by the representation profiles observed on ID inputs. OOD inputs can introduce a distorted version of the task-adapted geometry. Task-aware pruning identifies layers that create or amplify this distortion; by removing them, it shifts OOD representational norms and pairwise distances toward those observed on the adapted distribution. This realigns OOD inputs with the model's task-adapted geometry and improves performance. We provide causal evidence through controlled distribution shifts and residual-scaling interventions, and demonstrate consistent behavior across model scales.

preprint2023arXiv

Transport-based Counterfactual Models

Counterfactual frameworks have grown popular in machine learning for both explaining algorithmic decisions but also defining individual notions of fairness, more intuitive than typical group fairness conditions. However, state-of-the-art models to compute counterfactuals are either unrealistic or unfeasible. In particular, while Pearl's causal inference provides appealing rules to calculate counterfactuals, it relies on a model that is unknown and hard to discover in practice. We address the problem of designing realistic and feasible counterfactuals in the absence of a causal model. We define transport-based counterfactual models as collections of joint probability distributions between observable distributions, and show their connection to causal counterfactuals. More specifically, we argue that optimal-transport theory defines relevant transport-based counterfactual models, as they are numerically feasible, statistically-faithful, and can coincide under some assumptions with causal counterfactual models. Finally, these models make counterfactual approaches to fairness feasible, and we illustrate their practicality and efficiency on fair learning. With this paper, we aim at laying out the theoretical foundations for a new, implementable approach to counterfactual thinking.

preprint2013arXiv

Infinite games with uncertain moves

We study infinite two-player games where one of the players is unsure about the set of moves available to the other player. In particular, the set of moves of the other player is a strict superset of what she assumes it to be. We explore what happens to sets in various levels of the Borel hierarchy under such a situation. We show that the sets at every alternate level of the hierarchy jump to the next higher level.

preprint2010arXiv

Testing SDRT's Right Frontier

The Right Frontier Constraint (RFC), as a constraint on the attachment of new constituents to an existing discourse structure, has important implications for the interpretation of anaphoric elements in discourse and for Machine Learning (ML) approaches to learning discourse structures. In this paper we provide strong empirical support for SDRT's version of RFC. The analysis of about 100 doubly annotated documents by five different naive annotators shows that SDRT's RFC is respected about 95% of the time. The qualitative analysis of presumed violations that we have performed shows that they are either click-errors or structural misconceptions.

Inspect adjacent papers, topics, institutions and collaborators without losing the researcher page.

Building this map preview

BZPEER is loading the nearby papers, people, topics and institutions for this page.