Home Knowledge Base Symbolic State

Symbolic State

No mentions found

This entity hasn't been tracked yet, or Iris is still building its knowledge base.

Related Articles from SNS

Learning Visual Spatial Planning from Symbolic State via Modality-Gap-Aware Self-Distillation

Announce Type: replace Abstract: While vision-language models excel at general multimodal understanding, they still struggle with visual spatial planning. We attribute this to a perception-reasoning modality gap: visual planning requires models to infer latent state structures from pixels and then reason over the recovered structure to produce valid actions, whereas symbolic planning directly leverages explicit objects and constraints. This creates dual bottlenecks in visual state recovery...

arXiv CS 1d ago

Learning Visual Spatial Planning from Symbolic State via Modality-Gap-Aware Self-Distillation

Announce Type: new Abstract: While vision-language models excel at general multimodal understanding, they still struggle with visual spatial planning. We attribute this to a perception-reasoning modality gap: visual planning requires models to infer latent state structures from pixels and then reason over the recovered structure to produce valid actions, whereas symbolic planning directly leverages explicit objects and constraints. This creates dual bottlenecks in visual state recovery and...

arXiv CS 5d ago

Signals Are Not States: Neuro-Symbolic Safeguards for Culturally Aware Classroom AI

arXiv:2603.22793v2 Announce Type: replace Abstract: Classroom AI systems increasingly infer high-level educational states such as engagement, confusion, collaboration, participation, and instructional quality from multimodal and linguistic signals. In multicultural and multilingual classrooms, such inferences can translate culturally situated behavior into stereotyped claims: silence may be read as disengagement, gaze aversion as inattention, code-switching as low proficiency, or indirect...

arXiv CS 1d ago

Inverse Manipulation through Symbolic Planning and Residual Operator Learning

arXiv:2606.05248v1 Announce Type: new Abstract: Inverting a robotic task requires more than reversing symbolic state transitions or rewinding motor trajectories. In robot manipulation tasks, symbolic inverse plans often fail to fully restore the effects of forward executions under continuous interaction dynamics.

arXiv CS 5d ago

Simultaneous Model-Based Evolution of Constants and Expression Structure in GP-GOMEA for Symbolic Regression

arXiv:2606.02236v1 Announce Type: new Abstract: Genetic programming (GP) approaches are among the state-of-the-art for symbolic regression, the task of constructing symbolic expressions that fit well with data. To find highly accurate symbolic expressions, both the expression structure and any contained real-valued constants, are important. GP-GOMEA, a modern model-based evolutionary algorithm, is one of the leading algorithms for finding accurate, yet compact expressions.

arXiv CS 8d ago

Passive Learning of Symbolic Automata over Monotonic Algebras

arXiv:2606.06050v1 Announce Type: new Abstract: Symbolic automata extend classical finite-state automata to handle large or infinite alphabets by labeling transitions by predicates coming from a boolean algebra. Many results from automata theory have been lifted to this model, and it has proved its usefulness for example in multiple software verification applications. Here, we tackle the passive learning problem of identification in the limit, i.e. learning a model from a sample without...

arXiv CS 5d ago

Structural Grid Descriptors Predict Within-Task Solver Success on ARC-AGI

arXiv:2606.09026v1 Announce Type: new Abstract: We ask whether structural properties of intermediate grid states predict whether a symbolic ARC-AGI solver will succeed, framed as a test of conditional mutual information I(X;Y|task) > 0. Across 44,800 runs spanning two architecturally distinct solvers (beam search and Stochastic DFS), 400 ARC tasks, 28 configurations per solver, and both training and evaluation splits, hand-crafted grid descriptors measured at 50% trajectory completion...

arXiv CS 1d ago

Australia the 'perfect' target for new Islamist terror network

Australia the 'perfect' target for new 'ghost proxy' Islamist terror network, experts warn Mon 1 Jun 2026 at 4:44am In short: Experts are warning that an emerging terror network, which has already claimed responsibility for multiple attacks, needs to be taken seriously by foreign governments. Harakat Ashab al-Yamin al-Islamia (HAYI) first emerged online in March and is targeting Jewish people, symbols and buildings. Authorities in the United States have arrested and charged a man they allege...

ABC Australia 10d ago

GP-GOMEA with GPU-Based Fitness Evaluations: Design and Performance Analysis

Announce Type: new Abstract: GP-GOMEA is a state-of-the-art evolutionary algorithm for symbolic regression, known for discovering small and interpretable models. However, its computational cost remains substantial, limiting its applicability to larger datasets and more complex target expressions. In contrast, the rise of modern subsymbolic approaches, particularly deep learning, has been driven largely by the massive parallelism offered by GPUs.

arXiv CS 9d ago

Turkmenistan's 'heavenly' Akhal-Teke horses celebrated in annual beauty pageants

Turkmenistan's 'heavenly' Akhal-Teke horses celebrated in annual beauty pageants The Central Asian country of Turkmenistan is immensely proud of its horses. The ancient and endangered Akhal-Teke species has become a symbol of great national pride in a deeply isolated state where power is firmly concentrated, and are considered so beautiful that beauty pageants are held for them annually. The species and the culture surrounding them has even been listed on UNESCO's Intangible Cultural...

France 24 5d ago