2/13/2026
Stable Differentiable Modal Synthesis for Learning Nonlinear Dynamics
Stable Differentiable Modal Synthesis for Learning Nonlinear Dynamics
2/13/2026
Labels or Preferences? Budget-Constrained Learning with Human Judgments over AI-Generated Outputs
Labels or Preferences? Budget-Constrained Learning with Human Judgments over AI-Generated Outputs
2/13/2026
Distributional Computational Graphs: Error Bounds
Distributional Computational Graphs: Error Bounds
2/13/2026
A Feature Extraction Pipeline for Enhancing Lightweight Neural Networks in sEMG-based Joint Torque Estimation
A Feature Extraction Pipeline for Enhancing Lightweight Neural Networks in sEMG-based Joint Torque Estimation
2/13/2026
Empirical Likelihood-Based Fairness Auditing: Distribution-Free Certification and Flagging
Empirical Likelihood-Based Fairness Auditing: Distribution-Free Certification and Flagging
2/13/2026
Are LLM Evaluators Really Narcissists? Sanity Checking Self-Preference Evaluations
Are LLM Evaluators Really Narcissists? Sanity Checking Self-Preference Evaluations
2/13/2026
Alternating Reinforcement Learning for Rubric-Based Reward Modeling in Non-Verifiable LLM Post-Training
Alternating Reinforcement Learning for Rubric-Based Reward Modeling in Non-Verifiable LLM Post-Training
2/13/2026
Humanoid Manipulation Interface: Humanoid Whole-Body Manipulation from Robot-Free Demonstrations
Humanoid Manipulation Interface: Humanoid Whole-Body Manipulation from Robot-Free Demonstrations
2/13/2026
When Evaluation Becomes a Side Channel: Regime Leakage and Structural Mitigations for Alignment Assessment
When Evaluation Becomes a Side Channel: Regime Leakage and Structural Mitigations for Alignment Assessment
2/13/2026
Reinforcement Inference: Leveraging Uncertainty for Self-Correcting Language Model Reasoning
Reinforcement Inference: Leveraging Uncertainty for Self-Correcting Language Model Reasoning
2/13/2026
Efficient reduction of stellar contamination and noise in planetary transmission spectra using neural networks
Efficient reduction of stellar contamination and noise in planetary transmission spectra using neural networks
2/13/2026
End-to-End Semantic ID Generation for Generative Advertisement Recommendation
End-to-End Semantic ID Generation for Generative Advertisement Recommendation
2/13/2026
Spend Search Where It Pays: Value-Guided Structured Sampling and Optimization for Generative Recommendation
Spend Search Where It Pays: Value-Guided Structured Sampling and Optimization for Generative Recommendation
2/13/2026
GeoAgent: Learning to Geolocate Everywhere with Reinforced Geographic Characteristics
GeoAgent: RL-based model for geolocation reasoning using fine-grained geographic characteristics and GeoSeek dataset with annotated chain-of-thought.
2/13/2026
Self-EvolveRec: Self-Evolving Recommender Systems with LLM-based Directional Feedback
LLM-driven framework for automated recommender system design using directional feedback instead of scalar metrics to guide architecture evolution.
2/13/2026
LLM Steering: From Prompting Tricks to Activation Control
Technical exploration of LLM control methods beyond prompting, covering activation-level steering techniques. Advances understanding of model behavior.
2/13/2026
Exercise Selection Algorithms with Equipment Constraints
Exercise recommendation system with equipment constraints and personalization; specialized ML application.
2/13/2026
How Computer Vision Turns Videos into AI-Ready Prompts
Data engineering patterns for aggregating and normalizing fitness data from multiple sources; practical pipeline work.
2/13/2026
A Governance Lens on Drift, Evidence, and Reliance.
Examines model drift through governance perspective, distinguishing behavioral drift from statistical drift in ML systems.
2/13/2026
Why Your Chatbot is the BlackBerry of the 2020s
DAG pipeline management tool. Minimal information; not AI-specific or clearly relevant.
2/13/2026
On Robustness and Chain-of-Thought Consistency of RL-Finetuned VLMs
Analysis of RL fine-tuned VLMs showing vulnerability to textual perturbations and weak visual grounding despite improved visual reasoning benchmarks.
2/13/2026
I Run LLMs on a 768GB IBM POWER8 Server (And It's Faster Than You Think)
Performance optimization of llama.cpp on specialized hardware achieving 8.8x speedup. Relevant for efficient LLM deployment strategies.
2/12/2026
What does RL improve for Visual Reasoning? A Frankenstein-Style Analysis
Frankenstein-style analysis framework isolating specific visual reasoning improvements from RL versus supervised fine-tuning in vision-language models.
2/12/2026
Stroke of Surprise: Progressive Semantic Illusions in Vector Sketching
Novel generative framework for creating vector sketches that transform semantically through progressive stroke addition, addressing dual-constraint optimization challenges.
2/12/2026
T3D: Few-Step Diffusion Language Models via Trajectory Self-Distillation with Direct Discriminative Optimization
T3D proposes trajectory self-distillation framework to enable fast parallel token decoding in diffusion LLMs with fewer refinement steps while maintaining generation quality.
2/12/2026
DeepGen 1.0: A Lightweight Unified Multimodal Model for Advancing Image Generation and Editing
DeepGen 1.0 is a lightweight 5B unified model for image generation and editing using Stacked Channel Bridging, achieving competitive performance to larger models with reduced deployment costs.
2/12/2026
ExStrucTiny: A Benchmark for Schema-Variable Structured Information Extraction from Document Images
ExStrucTiny benchmark evaluates VLM performance on schema-variable structured information extraction from diverse enterprise documents with flexible schemas.
2/12/2026
Sci-CoE: Co-evolving Scientific Reasoning LLMs via Geometric Consensus with Sparse Supervision
Sci-CoE framework enables LLMs to self-improve on scientific reasoning through co-evolution as both solver and verifier with geometric consensus mechanisms.
2/12/2026
dVoting: Fast Voting for dLLMs
dVoting fast voting technique for diffusion LLMs enabling parallel test-time scaling for improved reasoning performance.
2/12/2026
Learning beyond Teacher: Generalized On-Policy Distillation with Reward Extrapolation
Theoretical and empirical analysis of on-policy distillation as dense KL-constrained RL, proposing generalized reward extrapolation.
2/12/2026
P-GenRM: Personalized Generative Reward Model with Test-time User-based Scaling
P-GenRM enables personalized LLM alignment through scenario-specific reward models with test-time user-based scaling, addressing generalization to new users with limited feedback.
2/12/2026
The Pensieve Paradigm: Stateful Language Models Mastering Their Own Context
StateLM foundation model framework giving LLMs agency to manage their own context and memory via database operations.
2/12/2026
GigaBrain-0.5M*: a VLA That Learns From World Model-Based Reinforcement Learning
GigaBrain-0.5M VLA model trained via world model-based reinforcement learning for improved multi-step action prediction.
2/12/2026
DeepSight: An All-in-One LM Safety Toolkit
DeepSight is a unified toolkit for LLM/MLLM safety covering workflow, evaluation, diagnosis, and alignment with integrated explainability and risk scenario grounding capabilities.
2/12/2026
LawThinker: A Deep Research Legal Agent in Dynamic Environments
LawThinker autonomous legal research agent using Explore-Verify-Memorize strategy with intermediate step verification in dynamic environments.
2/12/2026
Composition-RL: Compose Your Verifiable Prompts for Reinforcement Learning of Large Language Models
Composition-RL optimizes RLVR training by composing verifiable prompts to balance hard and easy examples, mitigating ineffective data and enabling better prompt dataset expansion.
2/12/2026
Making AI Coding Agents Production-Aware: Using Hud.io's MCP Server with Cloudflare Workers
Opinion piece on chatbot limitations and technology evolution. Commentary without technical substance or concrete insights.
2/12/2026
Gaia2: Benchmarking LLM Agents on Dynamic and Asynchronous Environments
Gaia2 benchmark for evaluating LLM agents in realistic, asynchronous, dynamic environments with temporal constraints and collaboration.
2/12/2026
TADA! Tuning Audio Diffusion Models through Activation Steering
TADA: activation steering technique for audio diffusion models to control semantic musical concepts through shared attention layers.
2/12/2026
Intelligent AI Delegation
Adaptive framework for intelligent AI agent delegation across decomposed sub-tasks with dynamic adaptation to environmental changes and failure handling.
2/12/2026
Zooming without Zooming: Region-to-Image Distillation for Fine-Grained Multimodal Perception
Region-to-Image Distillation: reduces latency in multimodal LLMs' fine-grained perception by distilling zooming behavior into inference-time efficiency.
2/12/2026
Detecting RLVR Training Data via Structural Convergence of Reasoning
Detection method for identifying RLVR training data contamination via structural convergence signatures in reasoning trajectories, addressing benchmark contamination concerns.
2/12/2026
Light4D: Training-Free Extreme Viewpoint 4D Video Relighting
Light4D: training-free framework for 4D video relighting under extreme viewpoints using diffusion models with temporal consistency.
2/12/2026
MiniCPM-SALA: Hybridizing Sparse and Linear Attention for Efficient Long-Context Modeling
MiniCPM-SALA hybrid sparse-linear attention architecture for efficient long-context LLM processing in 9B parameter model.
2/12/2026
Code2Worlds: Empowering Coding LLMs for 4D World Generation
Code2Worlds: extends coding LLMs to 4D world generation with dynamic physics simulation by addressing multi-scale context and semantic-physical execution gaps.
2/12/2026
Think Longer to Explore Deeper: Learn to Explore In-Context via Length-Incentivized Reinforcement Learning
Framework enabling LLMs to perform in-context exploration through length-incentivized RL, allowing models to generate, verify, and refine multiple reasoning hypotheses within continuous context.
2/12/2026
Adapting Vision-Language Models for E-commerce Understanding at Scale
Large-scale study on adapting general-purpose VLMs to e-commerce attribute understanding while preserving generalizability across multi-image noisy product data.
2/12/2026
DICE: Diffusion Large Language Models Excel at Generating CUDA Kernels
Diffusion language models tailored for CUDA kernel code generation, addressing data scarcity and specialization challenges through parallel token generation approach.
2/12/2026
ThinkRouter: Efficient Reasoning via Routing Thinking between Latent and Discrete Spaces
ThinkRouter framework routing reasoning between latent and discrete spaces to improve efficiency based on model confidence dynamics.
2/12/2026
ScalSelect: Scalable Training-Free Multimodal Data Selection for Efficient Visual Instruction Tuning
ScalSelect training-free data selection method for efficient visual instruction tuning of vision-language models.