AI-generated summaries

Today's ML research,
without the noise.

Daily summaries of the latest machine learning papers from arXiv, processed every 8 hours.

48 Papers today
8h Update frequency
7 Days of history
Layer-wise Derivative Controlled Networks Achieve Competitive Accuracy and Gradient Stability Across Data Regimes
Rowan Martnishn
NLP Theory Efficient ML
  • CR networks achieve strong low-data performance and maintain accuracy across various training data volumes.
  • Layer-wise derivative control enhances gradient stability, reducing the impact of noise and distribution shifts.
  • The gradient tail ratio serves as a reliable, label-free diagnostic for generalization capability.
  • CR outperforms traditional models and BERT baselines in low-resource settings, demonstrating its efficiency.
Read more
Blurry Window Attention
Axel Laborieux, Christos Sourmpis, Juan Gabriel Kostelec, Qinghai Guo
NLP Large Language Models Efficient ML
  • BLA achieves 8Γ— better state efficiency than Sliding Window Attention (SWA).
  • It effectively combines the retrieval capabilities of SWA with the long-range dependencies of SSMs and linear attention models.
  • BLA's implementation utilizes Dirichlet kernels for reconstructing KV history, enhancing performance in recall-intensive tasks.
  • The method is competitive with popular linear attention models, showing promise for applications requiring long context processing.
Read more
Semantic Cache Distillation: Efficient State Transfer via Reuse and Selective Patching
Qianli Ma, Zhiqing Tang, Hanshuai Cui, Zhi Yao, Weijia Jia
Large Language Models Efficient ML NLP
  • SCD replaces raw KV transmission with compact semantic codes to reduce communication overhead.
  • The framework integrates REUSE for bandwidth efficiency and PATCH for semantic alignment.
  • SCD achieves significant speedup in TTFT while maintaining high generation quality.
  • The proposed methods are particularly effective in bandwidth-constrained environments.
Read more
Encoding the Euler Characteristic Transform
Nello Blaser, Odin Hoff Gardaa, Lars M. Salbu, Elena Xinyi Wang, Bastian Rieck
Computer Vision Graph Learning Theory
  • Introduction of a continuous encoding for the Euler Characteristic Transform (ECT) that avoids discretization.
  • The new encoding records net Euler characteristic changes attributed to vertices, enhancing accuracy and efficiency.
  • Empirical evaluation across six classification benchmarks shows improved performance with the continuous encoding.
  • The representation architecture is less important than the encoding method itself.
Read more
Between Amnesia and Chaos: A Memory Stability Expressivity Trilemma for Trainable Dissipative Oscillator Networks
Caleb Munigety
Theory Time Series Optimization
  • Introduces a trilemma of memory horizon, gradient stability, and dynamical expressivity in dissipative oscillator networks.
  • Demonstrates that damping controls the balance between memory retention and gradient stability.
  • Presents empirical evidence showing learned substrates outperform frozen ones at short memory horizons.
  • Confirms theoretical predictions regarding the critical horizon and damping effects on training.
Read more
Representation-Aware Advantage Estimation: Your Reward Model Provides More Than A Scalar Output
Guozheng Li, Xiyan Fu, Yiwen Guo
Reinforcement Learning Large Language Models Graph Learning
  • Scalar rewards from reward models often fail to capture fine-grained preference differences.
  • Graph-based Advantage Estimation (GraphAE) utilizes RM hidden states to improve advantage estimation.
  • GraphAE constructs a similarity graph to incorporate contextual information from responses.
  • Empirical results show significant performance improvements across various benchmarks.
Read more
Teacher-Free Self-Training Amplifies but Does Not Compound: A Pass@$K$ Crossover on a Free-Verifier Domain
Igor Lima Strozzi
Large Language Models Theory NLP
  • Critic-guided selection significantly outperforms verifier-filtered methods in specific task scenarios.
  • Self-training leads to amplification of capabilities without accelerating learning, indicating a non-compounding effect.
  • The study identifies a pass@K crossover where the base model eventually outperforms the trained model at larger budgets.
  • The findings challenge the validity of the '0% to climb = emergence' test in compositional domains.
Read more
Escaping the KL Agreement Trap in On-Policy Distillation
Haoran Xin, Anhao Zhao, Ying Sun, Jin Li, Xiaoyu Shen, Hui Xiong
NLP Large Language Models Efficient ML
  • Identification of low-KL agreement traps in on-policy distillation, where persistent agreement indicates weak supervision.
  • Development of KAT, an adaptive online termination rule that enhances training efficiency by removing uninformative suffixes.
  • Empirical validation showing KAT improves average accuracy and pass rates while significantly reducing rollout lengths.
Read more
Adaptive Loss Balancing for Noise-Robust GRPO in Generative Recommendation
Kewei Xu, Junbo Qi, Yanyan Zou, Pengfei Zhang, Xingzhi Yao, Shengjie Li
Reinforcement Learning Generative Models Optimization
  • AdaGRPO selectively applies reward signals based on sample difficulty and reward model reliability.
  • The framework mitigates the risks associated with exposure bias in reward models.
  • AdaGRPO outperforms traditional fixed NLL–GRPO mixtures in terms of retrieval and validity.
  • The approach leads to statistically significant improvements in click-through rates and dwell time in production settings.
Read more
A Geometric Measure of Linear Separability for Neural Representations
Yi Wei, Xuan Qi, Furao Shen
Theory Interpretability
  • Introduces the directional linear separability measure (LSM) for assessing one-sided affine separability.
  • LSM provides a geometric interpretation of class-wise representation arrangements, distinguishing it from traditional accuracy metrics.
  • Establishes a relationship between LSM and optimal affine classification accuracy, emphasizing their complementary roles.
  • Proposes a method for estimating LSM in high-dimensional spaces, enhancing its practical applicability.
Read more
Causal Agent Replay: Counterfactual Attribution for LLM-Agent Failures
Jaineet Shah
Large Language Models Interpretability Theory
  • CAR provides a causal framework for understanding failures in LLM agents by modeling agent runs as structural causal models.
  • The framework includes a novel intervention algebra and a point-of-commitment rule to accurately attribute failures.
  • Validation against synthetic models shows CAR's effectiveness in identifying pivotal steps and interactions in agent failures.
  • CAR incorporates confidence intervals in its outcome distributions, enhancing the reliability of causal attributions.
Read more
UPLOTS: A Unified Pretrained Language Model for Constrained Time-series Generation
Du Yin, Hao Xue, Jinliang Deng, Yang Yang, Shuang Ao, Arian Prabowo, Flora Salim
Time Series Generative Models Large Language Models
  • UPLOTS provides a unified approach to time-series generation, eliminating the need for task-specific models.
  • The framework employs prompt-guided generation, allowing for flexible control over generated patterns.
  • Dynamic multi-dataset loss re-weighting enhances model training efficiency and generalization.
  • UPLOTS demonstrates superior performance in data augmentation and constraint-combination tasks.
Read more
Minibatch Selection via Partition Matroid Constrained Gradient Matching
Prayas Agrawal, Prateek Chanda, Ishita Khatri, Ganesh Ramakrishnan, Bamdev Mishra, Pratik Jawanpuria
Large Language Models Optimization Efficient ML
  • PartitionSel maximizes a validation-guided gradient-matching utility under partition-matroid constraints for minibatch selection.
  • The method reduces redundancy in sample selection across heterogeneous domains, improving training compatibility.
  • PartitionSel is shown to be weakly submodular and can be efficiently implemented with provable approximation guarantees.
  • Empirical results indicate significant performance improvements over existing minibatch selection methods.
Read more
Strained Coherence: A Pre-Failure Signal in Coding Agent Execution Trajectories
Marut Pandya, Kasey Zhang, Baiqing Lyu
NLP Large Language Models Interpretability
  • Introduces the concept of 'strained coherence' as a critical failure mode in coding agents.
  • Develops a detection mechanism that flags trajectories where agents acknowledge conflicts but do not resolve them.
  • Demonstrates a significant predictive gap in failure rates between flagged and unflagged trajectories.
  • Provides a robust evaluation across multiple model families and conditions.
Read more
Temporal Context Conditioning for Seasonality-Aware Precipitation Nowcasting of High-Intensity Rainfall
Gijs van Nieuwkoop, Siamak Mehrkanoon
Time Series
  • Introduction of TA-SmaAt-UNet model with temporal conditioning for improved precipitation nowcasting.
  • Temporal context enhances predictions for high-intensity rainfall and seasonal variability.
  • Layer conductance analysis shows effective utilization of temporal conditioning layers.
  • Demonstrates the potential of lightweight temporal context in deep learning models.
Read more
Unsupervised Style Representation Learning for AI-Text Detection via Paraphrase Inversion
Rafael Rivera Soto, Barry Chen, Nicholas Andrews
NLP Large Language Models
  • Introduces an unsupervised method for style representation learning without requiring authorship labels.
  • Utilizes a paraphrase inversion task to separate style from content effectively.
  • Demonstrates strong performance in both few-shot and zero-shot detection settings.
  • Achieves competitive results in related tasks like authorship verification and style discrimination.
Read more
Safe-RULE: Safe Reinforcement UnLEarning
Shixiong Jiang, Taozheng Zhu, Fanxin Kong
Reinforcement Learning Robotics Theory
  • Introduction of Safe-RULE, a framework for safe reinforcement unlearning.
  • Addresses vulnerabilities of offline Safe RL to data poisoning attacks.
  • Allows unlearning of poisoned data without full retraining.
  • Balances task performance and safety during the unlearning process.
Read more
Bittensor Agent Arenas as a Trajectory Primitive: Distilling a Shopping Agent from ShoppingBench Subnet Traces
Shardul Bansal, Seth Schilbe, Jarrod Barnes
Reinforcement Learning Large Language Models NLP
  • Introduction of an incentive-aligned agent arena for generating high-quality training trajectories.
  • Demonstration of significant performance improvements in a shopping agent through post-training on a curated corpus.
  • Development of a structural-quality filter to enhance trajectory selection for training.
  • Identification of the need for per-trajectory supervision in training effective agentic models.
Read more
Drawing with Strangers: Population Scaling Drives Zero-Shot Mutual Intelligibility in Emergent Sketching
Jooyeon Kim
Multimodal Theory
  • Introduction of zero-shot mutual intelligibility (ZMI) as a new measure of communication success between disjoint agent populations.
  • Empirical evidence shows that population scaling improves ZMI through emergent sketching, with linear training costs.
  • Increased in-group diversity and decreased cross-group variation contribute to the emergence of universal communication protocols.
  • Perceptual grounding plays a crucial role in enhancing ZMI by anchoring communication to visual features.
Read more
Transformer Based Model for Spatiotemporal Feature Learning in EEG Emotion Recognition
Xinglong Cui, Dian Gu
Time Series
  • Introduction of EEG-TransNet for enhanced EEG emotion recognition.
  • Utilization of Local Self-Attention Block for improved regional feature learning.
  • Implementation of Fuzzy-Attention Synchronous Transformer (FAST) to handle noisy EEG data.
  • Demonstrated superior performance on multiple EEG datasets.
Read more
Bandits for Efficient Experimentation: Adapting to Control Group, Preferences, and Context Drifts
Udvas Das, Waris Radji, Debabrota Basu, Odalric-Ambrym Maillard
Reinforcement Learning Optimization Theory
  • Dri-MED algorithm effectively manages non-stationary heteroskedastic noise in multi-armed bandit settings.
  • The algorithm ensures that recommendations exceed a baseline strategy's performance at each decision step.
  • Instance-dependent regret scales as ˜O(ΞΊΛœβˆ†dΒ²(log(T))), indicating efficient performance under constraints.
  • Numerical results show significant improvement over conservative baselines that ignore context drifts.
Read more
From Observation to Intervention: A Causal Audit of Expert Importance in Mixture-of-Experts Models
Leonard Engmann, Christian Medeiros Adriano, Holger Giese
Interpretability
  • Observational metrics do not reliably predict causal expert importance in MoE models.
  • No significant correlation was found between routing statistics and expert importance across multiple architectures.
  • Existing pruning methods succeed due to redundancy in early layers rather than accurate identification of dispensable experts.
  • A significant effect was only observed in one model at a specific layer, highlighting the limitations of generalizing findings.
Read more
Have I Solved This Before? Retrieving Similar Segmentation Problems for Evolutionary Learning
Andreas Margraf, Henning Cui, JΓΆrg HΓ€hner
Computer Vision Efficient ML Optimization
  • Proposes a shift from traditional algorithm design to a focus on problem analysis in monitoring systems.
  • Introduces a method for retrieving and reusing filter pipelines to enhance efficiency in segmentation tasks.
  • Analyzes the cross-domain transferability of filter pipelines for different segmentation problems.
  • Demonstrates that simpler models can effectively manage complexity while ensuring reliability.
Read more
Learning Entropy and Spatial Adaptation Dynamics of Multilayer Perceptrons for Structural Point Extraction
Jan Glaser, Ivo Bukovsky, Marcel Jirina
Computer Vision Interpretability Robotics
  • Introduces Learning Entropy as a measure of spatial adaptation dynamics in MLPs.
  • Develops Spatial Learning Entropy Maps (SLEM) to identify critical image regions for learning.
  • Provides a new perspective on feature extraction that focuses on learning impact rather than local image properties.
  • Demonstrates the potential of LE in enhancing explainability and interpretability of neural networks.
Read more
Enabling KV Caching of Shared Prefix for Diffusion Language Models
Younghun Go, Jaehoon Han, Changyong Shin, Chuk Yoo, Gyeongsik Yang
NLP Large Language Models Efficient ML
  • BICACHE is the first KV caching technique specifically designed for shared prefixes in DLMs.
  • Shared prefix KVs can be reused in shallow layers, significantly improving efficiency.
  • The method achieves a throughput increase of 36.3% to 98.3% while maintaining model accuracy.
  • Dynamic identification of safe layer depths for KV reuse is a key innovation.
Read more
Beyond Explaining Predictions: Logic-Based Explanations for Confidence in Machine Learning Models
VinΓ­cius Peixoto Chagas, Carlos Henrique LeitΓ£o Cavalcante, Thiago Alves Rocha
Interpretability
  • Introduces Minimum Confidence Threshold (MCT) for abductive explanations.
  • Proposes confidence-aware abductive explanations that ensure both correctness and user-defined confidence levels.
  • Demonstrates significant improvements in confidence guarantees over traditional abductive explanations.
  • Methodology is applicable to various machine learning models that provide confidence scores.
Read more
UNIQ: Conformal Calibration for Adaptive Conservatism in Offline Reinforcement Learning
Aditya Upadhyay
Reinforcement Learning
  • UNIQ adapts conservatism in offline RL using conformally calibrated uncertainty.
  • The method employs a multi-expectile value ensemble to enhance uncertainty estimation.
  • UNIQ outperforms IQL on specific tasks while maintaining low computational costs.
  • The approach allows for state-adaptive expectile adjustments, improving efficiency.
Read more
FailureScope: Cross-Regime Behavioral Diagnosis of Language Model Weaknesses
Nicholas Saban
NLP Large Language Models Interpretability
  • FAILURESCOPE provides a unified methodology for diagnosing language model weaknesses across different evaluation regimes.
  • The clustering approach yields stable, interpretable failure taxonomies, significantly improving diagnostic efficiency.
  • Unique failure patterns are identified in multi-turn dialogues that are not observable in single-turn analyses.
  • The methodology exposes a critical meta-failure mode in adversarial evaluations, highlighting discrepancies between model performance and evaluation metrics.
Read more
C$^3$ache: Accelerating World Action Models with Cross Inference Chunk Cache
Weisen Zhao, Lam Nguyen, Zhicong Lu, Yuzhang Shang
Robotics Efficient ML
  • C3ache exploits cross-chunk redundancy in WAMs to enhance inference efficiency.
  • The method caches residuals from denoising steps and reuses them across inference chunks.
  • C3ache achieves up to a 2.5Γ— speedup in inference time with negligible degradation in performance.
  • The approach is training-free and can be integrated with existing caching methods.
Read more
Forward-Only Convolutional Neural Networks with Learnable Channel-Class Assignment
Mohammadnavid Ghader, Saeed Reza Kheradpisheh, Bahar Farahani, Mahmood Fazlali
Computer Vision Theory Efficient ML
  • Introduction of a learnable channel-class assignment mechanism for adaptive specialization in CNNs.
  • Implementation of entropy and orthogonality regularization to enhance learning performance.
  • Development of a loss-aware layer contribution strategy for improved intermediate-layer prediction weighting.
  • Demonstration of state-of-the-art performance on CIFAR-10, CIFAR-100, and Tiny-ImageNet datasets.
Read more
Mechanistic Analysis of Alignment Algorithms in Language Models
Aarush Sinha, Ishan Garg, Veeraraju Elluru, Arth Singh, Kushal Garg
NLP Large Language Models Interpretability
  • The paper evaluates six alignment algorithms, revealing distinct internal representation changes rather than uniform effects.
  • KTO and GRPO enhance linear separability, while DPO and ORPO degrade it through different geometric transformations.
  • The study highlights the architecture-dependent variability of alignment effects, necessitating context-specific evaluations.
  • The findings advocate for a mechanistic understanding of alignment to predict unintended side effects in language models.
Read more
Dropout-GRPO: Variational Stochasticity for Continuous Latent Reasoning
Wooil Jung
Reinforcement Learning Large Language Models Optimization
  • Introduces dropout-GRPO to address the lack of stochasticity in continuous latent reasoning models.
  • Proves theoretical properties of the proposed method, including unbiasedness and variance reduction.
  • Empirical results show a significant performance improvement on the GSM8K benchmark.
  • Provides implementation refinements and a reference code for practical application.
Read more
VFUSE: Virulent Feature Understanding with Sparse autoEncoders
Michael Yu, Matthew L. Olson
Generative Models Interpretability
  • Introduction of VFUSE, a mechanistic interpretability approach using Sparse Autoencoders.
  • Demonstrated improved detection of hazardous protein designs using SAE latent space.
  • Identification of monosemantic features linked to hazardous designs with high AUROC scores.
  • First feature-level virulence audit of a protein design model.
Read more
Reformulate LLM Reinforcement Learning for Efficient Training under Black-box Discrepancy
Jiashun Liu, Runze Liu, Xu Wan, Jing Liang, Hongyao Tang, Ling Pan
Reinforcement Learning Large Language Models Optimization
  • Introduces the Discrepancy-Constrained Markov Decision Process (DCMDP) to address train-inference discrepancies in RL for LLMs.
  • Identifies a discrepancy tolerance region that allows for efficient learning without aggressive penalties.
  • Employs a Lagrangian relaxation mechanism to dynamically adjust the balance between performance improvement and discrepancy control.
  • Demonstrates significant performance improvements in large models through the proposed framework.
Read more
Beyond Accuracy: Interpreting Topic Representation in Suicide Ideation Detection Models
Hamideh Ghanadian, Isar Nejadgholi, Hussein Al Osman
NLP Interpretability
  • The study emphasizes the need for interpretability in suicide ideation detection models beyond mere accuracy metrics.
  • Topic-aware data augmentation improves the clarity and distinctness of psychological risk factors in model representations.
  • The use of overcomplete sparse autoencoders allows for a mechanistic analysis of how psychological concepts are encoded in models.
  • The introduction of a geometric separability framework provides a quantitative measure of representational clarity.
Read more
RKSC: Reasoning-Aware KV Cache Sharing and Confident Early Exit for Multi-Step LLM Inference
Anirudh Sekar
Large Language Models Efficient ML NLP
  • RKSC eliminates redundancies in multi-branch LLM reasoning pipelines.
  • ASKS enables efficient KV cache sharing based on hidden-state similarity.
  • CGEE provides dual-level exit mechanisms to reduce verification overhead.
  • The framework achieves a mean speedup of 3.008Γ— over traditional methods.
Read more
Autonomous Aerial Manipulation via Contextual Contrastive Meta Reinforcement Learning
Lixuan Jin, Bingxuan Lan, Xinyi Bao, Xiangyuan Xie, Chunjie Zhang, Zheng Chen, Tianshuo Liu, Ruijie Tian, Jinyu Ru, Gang Wang, Lei Yuan, Yang Yu
Reinforcement Learning Robotics
  • Aco2 enables fully autonomous aerial manipulation of diverse payloads using a lightweight hook.
  • The contextual observation encoder allows for online adaptation to varying flight dynamics.
  • A contrastive objective improves generalization across different payloads without manual calibration.
  • The framework is trained in simulation and successfully transferred to real-world applications.
Read more
The Confidence Trap: Calibration Attacks for Graph Neural Networks
Cuong Dang, Jiahao Zhang, Hieu Ta Quang, Dung Le, Lu Cheng, Suhang Wang
Graph Learning
  • Introduces a Unified Graph Calibration Attack (UGCA) framework for analyzing GNN calibration robustness.
  • Addresses unique challenges in calibration attacks on graph structures, including discrete optimization and edge sensitivity.
  • Establishes theoretical links between model accuracy, dataset complexity, and calibration vulnerability.
  • Demonstrates that UGCA increases Expected Calibration Error while preserving classification accuracy.
Read more
Conformal Prediction for Neural Operators: Distribution-Free Uncertainty Quantification in Physics Simulation
Michael Chin
Theory
  • First application of split conformal prediction to neural operators for physics simulations.
  • Provides distribution-free prediction intervals with finite-sample coverage guarantees.
  • Introduces adaptive-width intervals using Monte Carlo Dropout uncertainty estimates.
  • Develops an uncertainty decomposition framework to differentiate between epistemic and aleatoric uncertainties.
Read more
Instrumented data for causal scientific machine learning
Daniel N. Wilke
Theory Generative Models Optimization
  • Instrumented data provides a mechanistic model for each datum, addressing the limitations of observational and synthetic data.
  • The approach supports causal interventions through Pearl's do-operator, enhancing the interpretability of machine learning models.
  • Instrumented data can improve validation and auditing processes across various scientific disciplines.
  • The methodology is operationally feasible, demonstrated through multi-agent systems that autonomously generate detailed reports from sensor data.
Read more
Convergence of Monte Carlo Optimistic Policy Iteration: Beyond Uniform State-Action Updates
Octave Oliviers, Glenn Vinnicombe
Reinforcement Learning Theory Optimization
  • Proves convergence of MC-O-PI under relaxed conditions for state-action updates.
  • Demonstrates that uniform updates over actions within states are sufficient for convergence.
  • Introduces new proof techniques that do not rely on classical commutativity arguments.
  • Highlights practical implications for implementing MC-O-PI in large or unknown state spaces.
Read more
Embedding Hybrid Systems into Continuous Latent Vector Fields
Sangli Teng, Hang Liu, Koushil Sreenath
Theory Optimization Robotics
  • Proves that n-dimensional hybrid systems can be embedded into m-dimensional spaces with continuous vector fields when m > 2n.
  • Introduces a latent Neural ODE framework that leverages consistency loss for improved recovery of hybrid system dynamics.
  • Demonstrates superior performance over existing methods in learning hybrid systems from time series data.
  • Addresses the differentiability challenges in hybrid systems, making them amenable to optimization techniques.
Read more
Evaluating the Representation Space of Diffusion Models via Self-Supervised Principles
Xiao Li, Yixuan Jia, Zekai Zhang, Xiang Li, Lianghe Shi, Jinxin Zhou, Zhihui Zhu, Liyue Shen, Qing Qu
Generative Models Computer Vision Theory
  • Introduces the Invariant Contamination Ratio (ICR) as a metric for evaluating diffusion models.
  • Finds that representation invariance peaks at intermediate noise levels, enhancing classification performance.
  • Demonstrates that ICR can predict the onset of memorization during training in data-limited scenarios.
  • Establishes a connection between representation learning and generative modeling in diffusion models.
Read more
GENERIC-FNO: Embedding Energy Conservation and Entropy Production into Fourier Neural Operators
Jason Sulskis, Sathya Ravi
Theory
  • First neural operator to fully embed GENERIC structure in function space.
  • Exact enforcement of degeneracy conditions ensures thermodynamic consistency.
  • Demonstrates zero-shot performance across a 4Γ— super-resolution range.
  • Introduces a gauge-invariant diagnostic for assessing reversible vs. dissipative dynamics.
Read more
Thresholded Local Hyper-Flow Diffusion
Meher Chaitanya, Sebastian Dalleiger, Luana Ruiz
Graph Learning Optimization Theory
  • Introduction of TL-HFD, a locality-focused first-order method for hypergraph clustering.
  • Proven exactness of local updates and finite-time dual suboptimality.
  • Development of an activated-volume bound for controlling volume promotion.
  • Empirical results demonstrate improved performance over traditional HFD, especially in noisy scenarios.
Read more
Rotate2Think: Geometric Priming via Orthogonal Rotation to Improve Language Model Reasoning
Aditya Sharma, Christopher J. Pal, Amal Zouaq
NLP Large Language Models Multimodal
  • Introduction of Rotate2Think, a training-free method for improving language model reasoning.
  • Geometric characterization of reasoning representations shows distinct regions for input and thinking embeddings.
  • High fidelity in mapping between input and thinking embeddings via orthogonal rotation.
  • Significant accuracy improvements across multiple benchmarks and model families.
Read more
Efficiently Learning Drifting Halfspaces with Massart Noise
Mingchen Ma, Guyang Cao, Jelena Diakonikolas, Ilias Diakonikolas
Theory Efficient ML
  • Introduces efficient learning algorithms for drifting halfspaces under Massart noise.
  • Achieves improved error rates in the realizable setting compared to prior work.
  • Establishes a lower bound on algorithm performance, indicating a tradeoff between information and computation.
  • Demonstrates the applicability of the proposed methods to real-world scenarios with distribution drift.
Read more
Trajectory Geometry of Transformer Representations Across Layers
Vishal Pandey, Gopal Singh
NLP Large Language Models Interpretability
  • Introduces a trajectory-geometric framework for understanding transformer representations.
  • Identifies significant trajectory convergence for semantically related prompts in deeper layers.
  • Demonstrates that reasoning tasks lead to greater trajectory curvature than lexical tasks.
  • Shows measurable bifurcation for ambiguous tokens, indicating a clear disambiguation signature.
Read more