TextReg mitigates prompt distributional overfitting via regularized text-space optimization, reporting up to +16.5% OOD accuracy gains over prior methods on reasoning benchmarks.
hub Canonical reference
Language models are few-shot learners.Advances in neural information processing systems, 33:1877–1901
Canonical reference. 82% of citing Pith papers cite this work as background.
35
Pith papers citing it
Background
82% of classified citations
hub tools
citation-role summary
background 9
method 1
other 1
citation-polarity summary
representative citing papers
TabQL is a reinforcement learning framework that substitutes a tabular foundation model with in-context capabilities for the parametric Q-network in DQN, with a warm-up phase and theoretical analysis claiming improved sample efficiency.
Local neural operators on 3x3x3 patches, composed via Schwarz iteration, solve large-scale nonlinear elasticity on arbitrary geometries without domain-specific retraining.
DreamAvoid uses a Dream Trigger, Action Proposer, and Dream Evaluator trained on success/failure/boundary data to let VLA policies avoid critical-phase failures via test-time future dreaming.
A knowledge-first approach to LLM-driven automatic heuristic design in combinatorial optimization yields better discovery efficiency, transfer, and generalization than code-centric baselines by formalizing a distortion-compression trade-off.
In a controlled synthetic setting, transformers implement in-distribution task inference via convex combinations of task vectors and out-of-distribution inference via nearly orthogonal extrapolative representations.
TimeSeriesExamAgent combines templates and LLM agents to generate scalable time series reasoning benchmarks, demonstrating that current LLMs have limited performance on both abstract and domain-specific tasks.
This work delivers the first measurements of performance-energy trade-offs across four multi-request LLM workflow patterns on A100 GPUs using vLLM and Parrot.
A distributional alignment metric d_NTP and a linear regression method LTV for task vectors that improves accuracy by 9.2% over baselines on classification and regression tasks across multiple LLMs.
Introduces the ICT framework and an RL pipeline to train language agent reflectors that distill experience into reusable prompts, outperforming baselines on held-out tasks in ALFWorld and MiniHack.
Attention-state memory externalizes long prefixes into a lightweight lookup table of precomputed attention states, yielding higher accuracy than standard in-context learning at fixed memory budgets and lower latency than full attention.
Nonlinear Bipolar Compensation with Bipolar Logarithmic Transformation reduces outlier effects in post-training quantization by performing compensation in a compressed transformed space.
Conditional Attribute Transformers jointly estimate next-token probabilities and conditional attribute values for autoregressive sequence models, enabling credit assignment, counterfactuals, and steerable generation in one pass.
An audit of 152 papers reveals that geospatial foundation models lack standardized evaluations, training controls, and weight releases, so no one knows the state of the art.
AB-Sparse adaptively allocates per-head block sizes for sparse attention, adds lossless centroid quantization and custom variable-block GPU kernels, and reports up to 5.43% accuracy gain over fixed-block baselines with no throughput loss.
SOMA estimates a local response manifold from early turns and adapts a small surrogate model via divergence-maximizing prompts and localized LoRA fine-tuning for efficient multi-turn serving.
MoLF routes updates between full fine-tuning and LoRA at the optimizer level to match or exceed the better of the two static methods on SQL, medical QA, and counterfactual tasks while an efficient variant outperforms prior adaptive LoRA by up to 20%.
GazeMind encodes gaze data for LLM reasoning to deliver interpretable, personalized cognitive load predictions that generalize across tasks without fine-tuning and outperform baselines by over 20% on a new 152-person dataset.
ViewSAM achieves state-of-the-art weakly supervised performance on cross-view referring multi-object tracking by refining SAM tracklets via affinity-guided re-prompting and modeling view-induced variations as learnable conditions on SAM2.
Dynamic parameterization of standard layers can replace explicit attention for linear-time global visual modeling.
LMM-Searcher uses file-based visual UIDs and a fetch tool plus 12K synthesized trajectories to fine-tune a multimodal agent that scales to 100-turn horizons and reaches SOTA among open-source models on MM-BrowseComp and MMSearch-Plus.
Small transformers learn to forecast unseen dynamical systems in-context by using delay embeddings to recover the manifold and forecasting its invariant sets via a transfer-operator strategy.
Generative video models exhibit emergent zero-shot capabilities across perception, manipulation, and basic reasoning tasks.
LoRA-Mixer routes modular LoRA experts into attention projection matrices with an adaptive Routing Specialization Loss to improve multi-task performance while using fewer trainable parameters than prior LoRA-MoE methods.
citing papers explorer
-
TextReg: Mitigating Prompt Distributional Overfitting via Regularized Text-Space Optimization
TextReg mitigates prompt distributional overfitting via regularized text-space optimization, reporting up to +16.5% OOD accuracy gains over prior methods on reasoning benchmarks.
-
TabQL: In-Context Q-Learning with Tabular Foundation Models
TabQL is a reinforcement learning framework that substitutes a tabular foundation model with in-context capabilities for the parametric Q-network in DQN, with a warm-up phase and theoretical analysis claiming improved sample efficiency.
-
Neural-Schwarz Tiling for Geometry-Universal PDE Solving at Scale
Local neural operators on 3x3x3 patches, composed via Schwarz iteration, solve large-scale nonlinear elasticity on arbitrary geometries without domain-specific retraining.
-
DreamAvoid: Critical-Phase Test-Time Dreaming to Avoid Failures in VLA Policies
DreamAvoid uses a Dream Trigger, Action Proposer, and Dream Evaluator trained on success/failure/boundary data to let VLA policies avoid critical-phase failures via test-time future dreaming.
-
Back to the Beginning of Heuristic Design: Bridging Code and Knowledge with LLMs
A knowledge-first approach to LLM-driven automatic heuristic design in combinatorial optimization yields better discovery efficiency, transfer, and generalization than code-centric baselines by formalizing a distortion-compression trade-off.
-
Task Vector Geometry Underlies Dual Modes of Task Inference in Transformers
In a controlled synthetic setting, transformers implement in-distribution task inference via convex combinations of task vectors and out-of-distribution inference via nearly orthogonal extrapolative representations.
-
TimeSeriesExamAgent: Creating Time Series Reasoning Benchmarks at Scale
TimeSeriesExamAgent combines templates and LLM agents to generate scalable time series reasoning benchmarks, demonstrating that current LLMs have limited performance on both abstract and domain-specific tasks.
-
Characterizing Performance-Energy Trade-offs of Large Language Models in Multi-Request Workflows
This work delivers the first measurements of performance-energy trade-offs across four multi-request LLM workflow patterns on A100 GPUs using vLLM and Parrot.
-
Distributional Alignment as a Criterion for Designing Task Vectors in In-Context Learning
A distributional alignment metric d_NTP and a linear regression method LTV for task vectors that improves accuracy by 9.2% over baselines on classification and regression tasks across multiple LLMs.
-
Training Language Agents to Learn from Experience
Introduces the ICT framework and an RL pipeline to train language agent reflectors that distill experience into reusable prompts, outperforming baselines on held-out tasks in ALFWorld and MiniHack.
-
Context Memorization for Efficient Long Context Generation
Attention-state memory externalizes long prefixes into a lightweight lookup table of precomputed attention states, yielding higher accuracy than standard in-context learning at fixed memory budgets and lower latency than full attention.
-
Nonlinear Bipolar Compensation: Handling Outliers in Post-Training Quantization
Nonlinear Bipolar Compensation with Bipolar Logarithmic Transformation reduces outlier effects in post-training quantization by performing compensation in a compressed transformed space.
-
Conditional Attribute Estimation with Autoregressive Sequence Models
Conditional Attribute Transformers jointly estimate next-token probabilities and conditional attribute values for autoregressive sequence models, enabling credit assignment, counterfactuals, and steerable generation in one pass.
-
No One Knows the State of the Art in Geospatial Foundation Models
An audit of 152 papers reveals that geospatial foundation models lack standardized evaluations, training controls, and weight releases, so no one knows the state of the art.
-
AB-Sparse: Sparse Attention with Adaptive Block Size for Accurate and Efficient Long-Context Inference
AB-Sparse adaptively allocates per-head block sizes for sparse attention, adds lossless centroid quantization and custom variable-block GPU kernels, and reports up to 5.43% accuracy gain over fixed-block baselines with no throughput loss.
-
SOMA: Efficient Multi-turn LLM Serving via Small Language Model
SOMA estimates a local response manifold from early turns and adapts a small surrogate model via divergence-maximizing prompts and localized LoRA fine-tuning for efficient multi-turn serving.
-
Beyond LoRA vs. Full Fine-Tuning: Gradient-Guided Optimizer Routing for LLM Adaptation
MoLF routes updates between full fine-tuning and LoRA at the optimizer level to match or exceed the better of the two static methods on SQL, medical QA, and counterfactual tasks while an efficient variant outperforms prior adaptive LoRA by up to 20%.
-
GazeMind: A Gaze-Guided LLM Agent for Personalized Cognitive Load Assessment
GazeMind encodes gaze data for LLM reasoning to deliver interpretable, personalized cognitive load predictions that generalize across tasks without fine-tuning and outperform baselines by over 20% on a new 152-person dataset.
-
ViewSAM: Learning View-aware Cross-modal Semantics for Weakly Supervised Cross-view Referring Multi-Object Tracking
ViewSAM achieves state-of-the-art weakly supervised performance on cross-view referring multi-object tracking by refining SAM tracklets via affinity-guided re-prompting and modeling view-induced variations as learnable conditions on SAM2.
-
Linear-Time Global Visual Modeling without Explicit Attention
Dynamic parameterization of standard layers can replace explicit attention for linear-time global visual modeling.
-
Towards Long-horizon Agentic Multimodal Search
LMM-Searcher uses file-based visual UIDs and a fetch tool plus 12K synthesized trajectories to fine-tune a multimodal agent that scales to 100-turn horizons and reaches SOTA among open-source models on MM-BrowseComp and MMSearch-Plus.
-
Transformers for dynamical systems learn transfer operators in-context
Small transformers learn to forecast unseen dynamical systems in-context by using delay embeddings to recover the manifold and forecasting its invariant sets via a transfer-operator strategy.
-
Video models are zero-shot learners and reasoners
Generative video models exhibit emergent zero-shot capabilities across perception, manipulation, and basic reasoning tasks.
-
LoRA-Mixer: Coordinate Modular LoRA Experts Through Serial Attention Routing
LoRA-Mixer routes modular LoRA experts into attention projection matrices with an adaptive Routing Specialization Loss to improve multi-task performance while using fewer trainable parameters than prior LoRA-MoE methods.
-
Superposition Yields Robust Neural Scaling
Strong superposition causes neural loss to scale as the inverse of model dimension due to geometric feature overlaps, explaining scaling laws for broad frequency distributions.
-
Siamese Foundation Models for Crystal Structure Prediction
DAO pretrains Siamese diffusion-based models on stable/unstable crystal data to achieve 100% experimental match on Cr6Os2 and 2000x speedup over DFT on real superconductors.
-
Prune, Update and Trim: Robust Structured Pruning for Large Language Models
Putri is a structured pruning technique for LLMs that compensates for pruning errors via weight updates and sequential processing while pruning at the attention-head level to reach state-of-the-art results at extreme sparsity.
-
Unveiling Memorization-Generalization Coexistence: A Case Study on Arithmetic Tasks with Label Noise
Experiments on modular arithmetic with heavy label noise show that over-parameterized networks form a distributed internal generalization structure that can be extracted via frequency methods to achieve high accuracy despite 80% noise.
-
CoT-Guard: Small Models for Strong Monitoring
CoT-Guard is a 4B model using SFT and RL that achieves 75% G-mean^2 on hidden objective detection under prompt and code manipulation attacks, outperforming several larger models.
-
A Composite Activation Function for Learning Stable Binary Representations
HTAF is a sigmoid-tanh composite that approximates the Heaviside function to allow stable gradient training of binary activation networks, yielding ICBMs with stable discretization and competitive performance on image tasks.
-
Trustworthy Agent Network: Trust in Agent Networks Must Be Baked In, Not Bolted On
Argues that trustworthiness in Agent-to-Agent networks requires a new conceptual framework with four design pillars baked in from the beginning, as retrofitting existing single-agent methods is insufficient.
-
Responsible Agentic AI Requires Explicit Provenance
Explicit provenance across the full agentic AI lifecycle is the necessary condition for making responsibility computable and actionable.
-
Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems
This survey frames foundation agents using brain-inspired modular architectures and reviews challenges in evolution, collaboration, and safety.
- SSDAU: Structured Semantic Data Augmentation for Joint Entity and Relation Extraction
- Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer