Large Language Models

I am not an "anti" like this guy, but still an interesting video of person interacting with chat 4o

(Posting Here because removed by Chatgpt Complaints moderators because the model here is 4o, and refuse to believe there were any safety ...

We built a way for two people's AI context to talk to each other (without sharing their conversations)

We've been thinking about how we use AI in our relationships. Big part of it is about other people. Talking about them, figuring out what...

No flattery please, Claude: I’m British | Brief letters

[2603.02709] Sensory-Aware Sequential Recommendation via Review-Distilled Representations

Abstract page for arXiv paper 2603.02709: Sensory-Aware Sequential Recommendation via Review-Distilled Representations

[2603.02376] CUCo: An Agentic Framework for Compute and Communication Co-design

Abstract page for arXiv paper 2603.02376: CUCo: An Agentic Framework for Compute and Communication Co-design

[2603.02676] ITLC at SemEval-2026 Task 11: Normalization and Deterministic Parsing for Formal Reasoning in LLMs

Abstract page for arXiv paper 2603.02676: ITLC at SemEval-2026 Task 11: Normalization and Deterministic Parsing for Formal Reasoning in LLMs

[2603.02655] Real-Time Generation of Game Video Commentary with Multimodal LLMs: Pause-Aware Decoding Approaches

Abstract page for arXiv paper 2603.02655: Real-Time Generation of Game Video Commentary with Multimodal LLMs: Pause-Aware Decoding Approa...

[2603.02597] GPUTOK: GPU Accelerated Byte Level BPE Tokenization

Abstract page for arXiv paper 2603.02597: GPUTOK: GPU Accelerated Byte Level BPE Tokenization

[2603.02578] How Controllable Are Large Language Models? A Unified Evaluation across Behavioral Granularities

Abstract page for arXiv paper 2603.02578: How Controllable Are Large Language Models? A Unified Evaluation across Behavioral Granularities

[2603.02248] HELIOS: Harmonizing Early Fusion, Late Fusion, and LLM Reasoning for Multi-Granular Table-Text Retrieval

Abstract page for arXiv paper 2603.02248: HELIOS: Harmonizing Early Fusion, Late Fusion, and LLM Reasoning for Multi-Granular Table-Text ...

[2603.02557] CAPT: Confusion-Aware Prompt Tuning for Reducing Vision-Language Misalignment

Abstract page for arXiv paper 2603.02557: CAPT: Confusion-Aware Prompt Tuning for Reducing Vision-Language Misalignment

[2603.02556] Through the Lens of Contrast: Self-Improving Visual Reasoning in VLMs

Abstract page for arXiv paper 2603.02556: Through the Lens of Contrast: Self-Improving Visual Reasoning in VLMs

[2603.02547] CoDAR: Continuous Diffusion Language Models are More Powerful Than You Think

Abstract page for arXiv paper 2603.02547: CoDAR: Continuous Diffusion Language Models are More Powerful Than You Think

[2603.02512] Human-Certified Module Repositories for the AI Age

Abstract page for arXiv paper 2603.02512: Human-Certified Module Repositories for the AI Age

[2603.03206] Understanding and Mitigating Dataset Corruption in LLM Steering

Abstract page for arXiv paper 2603.03206: Understanding and Mitigating Dataset Corruption in LLM Steering

[2603.02420] Slurry-as-a-Service: A Modest Proposal on Scalable Pluralistic Alignment for Nutrient Optimization

Abstract page for arXiv paper 2603.02420: Slurry-as-a-Service: A Modest Proposal on Scalable Pluralistic Alignment for Nutrient Optimization

[2603.03155] Information Routing in Atomistic Foundation Models: How Equivariance Creates Linearly Disentangled Representations

Abstract page for arXiv paper 2603.03155: Information Routing in Atomistic Foundation Models: How Equivariance Creates Linearly Disentang...

[2603.02297] ZeroDayBench: Evaluating LLM Agents on Unseen Zero-Day Vulnerabilities for Cyberdefense

Abstract page for arXiv paper 2603.02297: ZeroDayBench: Evaluating LLM Agents on Unseen Zero-Day Vulnerabilities for Cyberdefense

[2603.02345] RIVA: Leveraging LLM Agents for Reliable Configuration Drift Detection

Abstract page for arXiv paper 2603.02345: RIVA: Leveraging LLM Agents for Reliable Configuration Drift Detection

[2603.03031] Step-Level Sparse Autoencoder for Reasoning Process Interpretation

Abstract page for arXiv paper 2603.03031: Step-Level Sparse Autoencoder for Reasoning Process Interpretation

[2603.02277] Quantifying Frontier LLM Capabilities for Container Sandbox Escape

Abstract page for arXiv paper 2603.02277: Quantifying Frontier LLM Capabilities for Container Sandbox Escape

[2603.03000] Why Does RLAIF Work At All?

Abstract page for arXiv paper 2603.03000: Why Does RLAIF Work At All?

[2603.02266] When Scaling Fails: Mitigating Audio Perception Decay of LALMs via Multi-Step Perception-Aware Reasoning

Abstract page for arXiv paper 2603.02266: When Scaling Fails: Mitigating Audio Perception Decay of LALMs via Multi-Step Perception-Aware ...