6 citations · 12 across the 18 of their papers we have counts for
19 papers
Towards a full-stack functionalist theory of consciousness: Identifying its functional profile
Sushrut Thorat, Paras Chopra
If consciousness is functional, a basic question is what awareness of a content actually changes in how a system operates on it. We ask, for a particular content X and mental or bo…
Towards Nexus-Score: Metadata Gaps Limit Scholarly AI Attribution
Aadi Narayana Varma Dantuluri, Sushrut Thorat, Paras Chopra
Artificial intelligence systems increasingly mediate how science is found and credited. We asked whether missing metadata prevents AI systems from crediting work. As a boundary tes…
Frontier Coding Agents Use Metaprogramming to Adapt to Unfamiliar Programming Languages
Aman Sharma, Sushrut Thorat, Paras Chopra
LLM-based coding agents are usually evaluated in familiar software settings: mainstream languages, common libraries, and public repositories. These benchmarks remain important, but…
Represented Is Not Computed: A Causal Test of Candidate Algorithmic Intermediates in a Transformer
Ishita Darade, Sushrut Thorat
Structured prompts require integrating components according to task-relevant relations. How a network implements this integration is often hard to judge in language or vision, wher…
The illusory simplicity of the feedforward pass: evidence for the dynamical nature of stimulus encoding along the primate ventral stream
Daniel Anthes, Sushrut Thorat, Anna Mitola +3
In studying primate vision, a large body of work focuses on the first feedforward sweep. During this initial time window, information is thought to pass through ventral stream regi…
Path Integration and Object-Location Binding Emerge in an Action-Conditioned Predictive Sequence Network
Linda Ariel Ventura, Victoria Bosch, Tim C Kietzmann +1
Adaptive cognition requires structured internal models of objects and their relations. Predictive neural networks are often proposed to learn such world models, but how these are i…
Predicting upcoming visual features during eye movements yields scene representations aligned with human visual cortex
Sushrut Thorat, Adrien Doerig, Alexander Kroner +2
Natural scenes are complex arrangements of objects, surfaces, and backgrounds. For the brain's visual system to effectively operate, it needs to extract not only what objects are p…
Brain-language fusion enables interactive neural readout and in-silico experimentation
Victoria Bosch, Daniel Anthes, Adrien Doerig +3
Large language models (LLMs) have revolutionized human-machine interaction, and have been extended by embedding diverse modalities such as images into a shared language space. Yet,…
Adopting a human developmental visual diet yields robust, shape-based AI vision
Zejin Lu, Sushrut Thorat, Radoslaw M Cichy +1
Despite years of research and the dramatic scaling of artificial intelligence (AI) systems, a striking misalignment between artificial and human vision persists. Contrary to humans…
Models of attractor dynamics in the brain
Tala Fakhoury, Elia Turner, Sushrut Thorat +1
Attractor dynamics are a fundamental computational motif in neural circuits, supporting diverse cognitive functions through stable, self-sustaining patterns of neural activity. In…
Sparks of cognitive flexibility: self-guided context inference for flexible stimulus-response mapping by attentional routing
Rowan P. Sommers, Sushrut Thorat, Daniel Anthes +1
Flexible cognition demands discovering hidden rules to quickly adapt stimulus-response mappings. Standard neural networks struggle in such tasks requiring rapid, context-driven rem…
Computational characterization of the role of an attention schema in controlling visuospatial attention
Lotta Piefke, Adrien Doerig, Tim Kietzmann +1
How does the brain control attention? The Attention Schema Theory suggests that the brain explicitly models its state of attention, termed an attention schema, for its control. How…
Diagnosing Catastrophe: Large parts of accuracy loss in continual learning can be accounted for by readout misalignment
Daniel Anthes, Sushrut Thorat, Peter König +1
Unlike primates, training artificial neural networks on changing data distributions leads to a rapid decrease in performance on old tasks. This phenomenon is commonly referred to a…
Keep Moving: identifying task-relevant subspaces to maximise plasticity for newly learned tasks
Daniel Anthes, Sushrut Thorat, Peter König +1
Continual learning algorithms strive to acquire new knowledge while preserving prior information. Often, these algorithms emphasise stability and restrict network updates upon lear…
Characterising representation dynamics in recurrent neural networks for object recognition
Sushrut Thorat, Adrien Doerig, Tim C. Kietzmann
Recurrent neural networks (RNNs) have yielded promising results for both recognizing objects in challenging conditions and modeling aspects of primate vision. However, the represen…
Category-orthogonal object features guide information processing in recurrent neural networks trained for object categorization
Sushrut Thorat, Giacomo Aldegheri, Tim C. Kietzmann
Recurrent neural networks (RNNs) have been shown to perform better than feedforward architectures in visual object categorization tasks, especially in challenging conditions such a…
Modulation of early visual processing alleviates capacity limits in solving multiple tasks
Sushrut Thorat, Giacomo Aldegheri, Marcel A. J. van Gerven +1
In daily life situations, we have to perform multiple tasks given a visual stimulus, which requires task-relevant information to be transmitted through our visual system. When it i…
The functional role of cue-driven feature-based feedback in object recognition
Sushrut Thorat, Marcel van Gerven, Marius Peelen
Visual object recognition is not a trivial task, especially when the objects are degraded or surrounded by clutter or presented briefly. External cues (such as verbal cues or visua…
Implementing a Reverse Dictionary, based on word definitions, using a Node-Graph Architecture
Sushrut Thorat, Varad Choudhari
In this paper, we outline an approach to build graph-based reverse dictionaries using word definitions. A reverse dictionary takes a phrase as an input and outputs a list of words…