ReflexiCoder: Teaching Large Language Models to Self-Reflect on Generated Code and Self-Correct It via Reinforcement Learning
Paper
• 2603.05863 • Published
• 3
Urro
urroxyz
AI & ML interests
i like research on empowering small LMs to do better 😮
i DISLIKE video & image generation (esp. ai "art") 🤢
Recent Activity
updated
a model about 2 hours ago
urroxyz/edit-qwen2.5-3b-poc liked
a dataset about 3 hours ago
allenai/WildChat-4.8M updated
a collection
about 3 hours ago
HUMAN-WRITTEN & LEGALLY-SOURCED* Organizations
upvoted 20 papers about 11 hours ago
Decoupling Reasoning and Confidence: Resurrecting Calibration in Reinforcement Learning from Verifiable Rewards
Paper
• 2603.09117 • Published
• 5
The Reasoning Trap -- Logical Reasoning as a Mechanistic Pathway to Situational Awareness
Paper
• 2603.09200 • Published
• 5
Towards a Neural Debugger for Python
Paper
• 2603.09951 • Published
• 4
Test-Driven AI Agent Definition (TDAD): Compiling Tool-Using Agents from Behavioral Specifications
Paper
• 2603.08806 • Published
• 6
Do What I Say: A Spoken Prompt Dataset for Instruction-Following
Paper
• 2603.09881 • Published
• 7
Are Audio-Language Models Listening? Audio-Specialist Heads for Adaptive Audio Steering
Paper
• 2603.06854 • Published
• 11
Reading, Not Thinking: Understanding and Bridging the Modality Gap When Text Becomes Pixels in Multimodal LLMs
Paper
• 2603.09095 • Published
• 23
Stepping VLMs onto the Court: Benchmarking Spatial Intelligence in Sports
Paper
• 2603.09896 • Published
• 24
Omni-Diffusion: Unified Multimodal Understanding and Generation with Masked Discrete Diffusion
Paper
• 2603.06577 • Published
• 43
MM-Zero: Self-Evolving Multi-Model Vision Language Models From Zero Data
Paper
• 2603.09206 • Published
• 41
Thinking to Recall: How Reasoning Unlocks Parametric Knowledge in LLMs
Paper
• 2603.09906 • Published
• 55
CLIPO: Contrastive Learning in Policy Optimization Generalizes RLVR
Paper
• 2603.10101 • Published
• 3
Lost in Backpropagation: The LM Head is a Gradient Bottleneck
Paper
• 2603.10145 • Published
• 3
UniCom: Unified Multimodal Modeling via Compressed Continuous Semantic Representations
Paper
• 2603.10702 • Published
• 3
Causal Concept Graphs in LLM Latent Space for Stepwise Reasoning
Paper
• 2603.10377 • Published
• 3
Bootstrapping Exploration with Group-Level Natural Language Feedback in Reinforcement Learning
Paper
• 2603.04597 • Published
• 5
RbtAct: Rebuttal as Supervision for Actionable Review Feedback Generation
Paper
• 2603.09723 • Published
• 6
Prism-Δ: Differential Subspace Steering for Prompt Highlighting in Large Language Models
Paper
• 2603.10705 • Published
• 10
RetroAgent: From Solving to Evolving via Retrospective Dual Intrinsic Feedback
Paper
• 2603.08561 • Published
• 10