💡 AI Reasoning - inarcissuss

PointVG-R: Internalizing Geometric Reasoning in MLLMs for Precise Pointing Localization via Visual Chain of Thought

🧠LLM arXiv·

Beyond Fixed Budgets: Characterizing the Inelasticity and Limitations of Tree-of-Thought Reasoning Strategies

💬LLM Prompting arXiv·

Representation Matters: An Empirical Study of Program Representations for LLM Vulnerability Reasoning

🧠LLM Reasoning arXiv·

TriViewBench: Controlled Complexity Scaling for Multi-View Structural Reasoning in MLLMs

🧠LLM Reasoning arXiv·

Can Reasoning Models Detect Changes to their Chains of Thought?

🌀Hallucination arXiv·

Quantifying Prior Dominance in RAG Systems

🧠LLM Reasoning arXiv·

Local Causal Attribution of Chain-of-Thought Reasoning

🧠LLM Reasoning arXiv·

Riazi-8B: An Urdu Large Language Model for Mathematical Reasoning

🧠LLM Reasoning arXiv·

MammoExpert: Benchmarking Chain-of-Thought Reasoning in Mammography Diagnosis

🧠LLM Reasoning arXiv·

Efficient and Trainable Language Model Test-Time Scaling via Local Branch Routing

🎯RLHF arXiv·

When Does Intrinsic Self-Correction Help? A Task-Sensitive Analysis

🔬AI Research arXiv·

ActiveScope: Actively Seeking and Correcting Perception for MLLMs

💬LLM Prompting arXiv·

VeryTrace: Verifying Reasoning Traces through Compilable Formalism and Structured Verification

🧠LLM Reasoning arXiv·

When Compression Helps and When It Hurts: Condition-Aware Analysis of Chain-of-Thought Distillation

🧠LLM Reasoning arXiv·

To Compare, or Not to Compare: On Methodological Practices in Evaluating Social Bias

🧠LLM arXiv·

When Helpfulness Overrides Causal Caution: Context-Dependent Suppression and Recovery in LLMs

🧠LLM Reasoning arXiv·

ISCSLP 2026 CoT-TTS Challenge: Chain-of-Thought Reasoning for Context-Aware Text-to-Speech

🗣️Large Language Models arXiv·

Quantization Inflates Reasoning: Token Inflation as a Hidden Cost of Low-Bit Reasoning Models

A Verifiable Search Is Not a Learnable Chain-of-Thought

PointVG-R: Internalizing Geometric Reasoning in MLLMs for Precise Pointing Localization via Visual Chain of Thought

Beyond Fixed Budgets: Characterizing the Inelasticity and Limitations of Tree-of-Thought Reasoning Strategies

Representation Matters: An Empirical Study of Program Representations for LLM Vulnerability Reasoning

TriViewBench: Controlled Complexity Scaling for Multi-View Structural Reasoning in MLLMs

Can Reasoning Models Detect Changes to their Chains of Thought?

Quantifying Prior Dominance in RAG Systems

Local Causal Attribution of Chain-of-Thought Reasoning

Riazi-8B: An Urdu Large Language Model for Mathematical Reasoning

MammoExpert: Benchmarking Chain-of-Thought Reasoning in Mammography Diagnosis

Efficient and Trainable Language Model Test-Time Scaling via Local Branch Routing

When Does Intrinsic Self-Correction Help? A Task-Sensitive Analysis

ActiveScope: Actively Seeking and Correcting Perception for MLLMs

VeryTrace: Verifying Reasoning Traces through Compilable Formalism and Structured Verification

When Compression Helps and When It Hurts: Condition-Aware Analysis of Chain-of-Thought Distillation

To Compare, or Not to Compare: On Methodological Practices in Evaluating Social Bias

When Helpfulness Overrides Causal Caution: Context-Dependent Suppression and Recovery in LLMs

ISCSLP 2026 CoT-TTS Challenge: Chain-of-Thought Reasoning for Context-Aware Text-to-Speech

video-SALMONN-R$^3$: Learning to ReWatch, ReAsk, and ReAnswer for Efficient Video Understanding