Papers

Field

Top tools here

Open problems in Graph learning

Quantization error propagation in recurrent states1 paper raises it · 1 addresses it
Low-precision recurrent states in linear attention degrade accuracy due to error accumulation over time and across dimensions.
- STEPQuant: When and Where Errors Matter in Delta-Rule Recurrent State Quantizationraises · addresses
Train-rollout discrepancy in low-precision RL1 paper raises it · 1 addresses it
Quantizing training and rollout paths independently in RL leads to mismatched behavior and reduced performance.
- TRACE: Rollout-Guided Quantization-Aware Training for FP4 Reinforcement Learning of MoE Language Modelsraises · addresses
Distribution shift in decoding-aware pruning1 paper raises it · 1 addresses it
Pruning guided by natural sequences fails to account for self-generated token distributions during decoding, hurting performance.
- SparseDecoding: Decoding-Aware Pruning for Accurate and Efficient LLM Inferenceraises · addresses
Lack of benchmarks for graph decision-making in System One models1 paper raises it · 1 addresses it
Existing benchmarks do not diagnose the unique challenges of graph-based decision tasks for non-language models.
- GraphDecisionBench: Benchmarking System One Models on Graph Tasksraises · addresses
Non-compositional sparse autoencoder features1 paper raises it · 1 addresses it
Sparse autoencoder features often exhibit higher-order interactions, limiting interpretability and control.
- Behavioral Compositionality of Sparse Autoencoder Representationsraises · addresses

Named by an AI from these papers' abstracts.

Open problems

Recently funded

Topics in this field

gradient descent · learning rate · neural networks221 papers35 this week
graph learning · graph neural · graph neural networks263 papers30 this week
neural networks · neural network · arnold networks149 papers29 this week
memory efficient · optimizers · low rank adaptation157 papers24 this week
bit quantization · quantization aware training · quantization aware152 papers18 this week
linear attention · softmax attention · transformer attention106 papers10 this week

Topics in this field

Active contributors · 90 days

Pietro LiòLocaLeJEPA: Maximum Entropy Representations under Geometric Priors8
Dan AlistarhWhat Matters for NVFP4 Training? A Comparative Study of Low-Precision Pretraining Recipes6
Rong-Hua LiToward Omni Multimodal Graph Foundation Model: A Topology-Driven Binding Approach6
Xunkai LiToward Omni Multimodal Graph Foundation Model: A Topology-Driven Binding Approach6
Rebekka BurkholzAC/DC on a Budget - Alternating Sparse Phases5
Haggai MaronGraph Metanetworks for Transformer Based Language Models5

Active contributors

Activity · 12 weeks

Activity

Recent papers

All papers in Research

arXiv cs.LGOct 11
Revisited Support Vector Machines: A Unified Joint Optimization Framework with Nyström Approximation for Scalable Adaptive Learning
Nassou Gongon Benjamin, Noulapeu Ngaffo, Patrick Njionou Sadjang
The theoretical elegance of Support Vector Machines (SVMs), grounded in statistical learning theory, establishes them as a reference for robust classification. However, in the era of Big Data, classical SVMs face two major bottlenecks: the prohibitive cubic complexity $\mathcal{O}(N^3)$ of training and the rigidity of static kernels. Traditional methodologies treat kernel selection as a discrete, "brute-force" GridSearch problem, effectively decoupling the learning of data representation from the optimization of the decision boundary. This paper proposes a paradigm shift with a so-called "Revisited SVM", a unified framework that recasts the learning process as a continuous %bi-level joint optimization problem. We derive a novel objective function $J(α, θ)$ that allows for the simultaneous optimization of dual Lagrange multipliers and kernel hyper-parameters. To solve this challenging non-convex problem efficiently, we introduce a hybrid Block Coordinate Ascent (BCA) algorithm, tightly integrated with Nyström-based low-rank approximation, which drastically reduces computational complexity to $\mathcal{O}(Nm)$. Extensive experiments conducted across four heterogeneous domains…
PDF arXiv
arXiv cs.LGOct 11
Riemannian Graph Tokenizer for Structural Knowledge Transfer
Qimin Zhou, Haibo Liu, Yujie Wang, Li Sun, Chuan Shi
Foundation models are at the forefront of artificial intelligence. A tokenizer, converting the raw input into discrete representations that the model can understand, plays an important role to the success of foundation models. Unlike the text tokenizer that is well studied in large language models, graph tokenizer is still at its early stage, facing the challenges of tackling the non-Euclidean structures and capturing the structural semantics. How to design a graph tokenizer for structural knowledge transfer? To this end, we propose a Riemannian Graph Tokenizer (RGT) that bridges the structural knowledge and quantized representations to support cross-domain structural knowledge transfer. The connection is established by Riemannian geometry. Specifically, we first define the geometric vocabulary (trees, cycles and sequences), which captures fundamental structural patterns and reflects the intrinsic geometry of graph. Second, we construct a Riemannian quantizer with Riemannian Straight-Through Estimator to tokenise graph structures across multiple domains into discrete tokens. To ensure consistency and transferability across diverse geometric spaces, RGT further incorporates a…
PDF arXiv
arXiv cs.LGOct 11
GA-SVD: Generation-aware Singular Value Decomposition for LLM Compression
Shengkun Tang, Cong Zeng, Zongfang Liu, Dan Alistarh, Zhiqiang Shen
Large language models (LLMs) demonstrate strong generalization across a broad range of reasoning and generation tasks, but their large parameter counts impose substantial memory and computation costs, hindering deployment in practical resource-constrained settings. One-shot low-rank compression is a promising solution since it reduces model size and inference cost effectively. However, existing SVD-based methods primarily target multiple-choice benchmarks and often fail to preserve performance on generation tasks. Moreover, their rank allocation strategies are typically heuristic. We propose GA-SVD, a generation-aware low-rank compression framework for LLMs. First, we introduce Generation-Aware Weight Whitening (GAWW), which leverages gradients from on-policy knowledge distillation to construct whitening transformations aligned with generative behavior. Second, we develop an evolutionary global rank allocation method that searches for effective layer-wise rank allocation under a given global compression ratio. Across extensive experiments on Mistral-7B, Qwen3 series, and Llama-3.3 models, evaluated on both multiple-choice and generative benchmarks, GA-SVD consistently outperforms…
PDF arXiv
arXiv cs.LGOct 11
WUSPruner: Second-Moment-Optimal Transforms for Structured Pruning
Shengkun Tang, Dan Alistarh, Zhiqiang Shen
Structured pruning is typically formulated as identifying which model dimensions to remove, often within the model's original representation. However, the effect of coordinate deletion fundamentally depends on the basis in which pruning is performed. This raises a more fundamental question: how should the basis be chosen specifically for coordinate deletion? We introduce WUSPruner, a transform-based framework for structured pruning of large language models. We formulate basis selection as a local linear reconstruction problem that directly minimizes the reconstruction loss induced by pruning. Inspired by the second-moment transformation in WUSH, we consider a WUS transform constructed jointly from activation and weight statistics. We show that under positive-definite second moments, WUS transform minimizes the local reconstruction loss over all invertible changes of basis. In the resulting basis, the activation and weight second moments are simultaneously diagonalized and balanced, causing the deletion error to decompose into independent spectral contributions and yielding a principled criterion for coordinate selection. Guided by this result, we develop a scalable pruning method…
PDF arXiv
arXiv cs.LGOct 11
Approximation in Contrastive Representation Learning
Yuanfan Li, Zihan Zhang, Yiming Ying, Ding-Xuan Zhou
Contrastive representation learning (CRL) is a fundamental paradigm for learning transferable representations. Recent work identifies its population target as the pointwise mutual information (PMI) $\log\frac{p(x,y)}{p_X(x)p_Y(y)}$ between two modalities $X,Y$, where $p$ is the joint density function and $p_X,p_Y$ are the marginals. However, it remains unclear why standard inner-product scores $f(x)^\top g(y)$ can effectively approximate a generally nonseparable population target PMI. In this paper, we address this question from the aspect of approximation for CRL. By linking PMI to a compact operator, we show that $D$-dimensional inner-product models perform rank-$D$ spectral approximation, with error controlled by the spectral tail. We then study neural network realizations: in general settings, we show that deep neural network scoring functions are universally consistent, and the approximation error rates depend on the smoothness of the PMI function; under structured low-rank data models we obtain improved rates attained by moderate-width encoders. Finally, we establish a fast calibration rate from contrastive excess risk to downstream retrieval error under a density-ratio…
PDF arXiv
arXiv cs.LGOct 11
E8 Lattice Key Quantization for Low-Bit KV-Cache Compression
Sasho Nedelkoski, Alexander Acker, Soeren Becker, Dominik Scheinert, Odej Kao
Compressing the key-value (KV) cache is essential for serving long-context large language models (LLMs) under memory constraints. While current scalar quantization methods achieve significant compression, they typically face a quality-fidelity trade-off, either suffering from performance instability at 2-bit precision or necessitating 3-bit keys to maintain model quality. In this work, we demonstrate that a uniform low-bit k2v2 configuration (2-bit keys and 2-bit values) can preserve near-baseline quality by using vector quantization (VQ) based on the $E_8$ lattice for KV keys. We show that structured VQ exploits correlations across adjacent dimensions to achieve signal-to-quantization-noise ratios (SQNR) higher than those of independent scalar quantization at the same key payload rate. To ensure practical utility, we adapt a table-based asymmetric scoring algorithm that avoids explicit codebook dequantization during attention computation and preserves decode-throughput parity with scalar baselines. Across five LLM families, our $E_8$ k2v2 approach yields \textasciitilde$6\times$ KV compression, roughly 20\% smaller than scalar k3v2 (3-bit keys and 2-bit values), while retaining…
PDF arXiv

Papers

Topics in this field

gradient descent · learning rate · neural networks221 papers35 this week
graph learning · graph neural · graph neural networks263 papers30 this week
neural networks · neural network · arnold networks149 papers29 this week
memory efficient · optimizers · low rank adaptation157 papers24 this week
bit quantization · quantization aware training · quantization aware152 papers18 this week
linear attention · softmax attention · transformer attention106 papers10 this week

Active contributors · 90 days

Pietro LiòLocaLeJEPA: Maximum Entropy Representations under Geometric Priors8
Dan AlistarhWhat Matters for NVFP4 Training? A Comparative Study of Low-Precision Pretraining Recipes6
Rong-Hua LiToward Omni Multimodal Graph Foundation Model: A Topology-Driven Binding Approach6
Xunkai LiToward Omni Multimodal Graph Foundation Model: A Topology-Driven Binding Approach6
Rebekka BurkholzAC/DC on a Budget - Alternating Sparse Phases5
Haggai MaronGraph Metanetworks for Transformer Based Language Models5

Activity · 12 weeks

Fields · AI · updated 11m ago

Graph learning

Found by the topic model: graph learning, gradient descent, bit quantization.

146papers this week−35.4% vs last week

All papers · 1k With code · 11

Newest Most relevant

999 papers this month

Open problems in Graph learning

Quantization error propagation in recurrent states1 paper raises it · 1 addresses it
Low-precision recurrent states in linear attention degrade accuracy due to error accumulation over time and across dimensions.
- STEPQuant: When and Where Errors Matter in Delta-Rule Recurrent State Quantizationraises · addresses
Train-rollout discrepancy in low-precision RL1 paper raises it · 1 addresses it
Quantizing training and rollout paths independently in RL leads to mismatched behavior and reduced performance.
- TRACE: Rollout-Guided Quantization-Aware Training for FP4 Reinforcement Learning of MoE Language Modelsraises · addresses
Distribution shift in decoding-aware pruning1 paper raises it · 1 addresses it
Pruning guided by natural sequences fails to account for self-generated token distributions during decoding, hurting performance.
- SparseDecoding: Decoding-Aware Pruning for Accurate and Efficient LLM Inferenceraises · addresses
Lack of benchmarks for graph decision-making in System One models1 paper raises it · 1 addresses it
Existing benchmarks do not diagnose the unique challenges of graph-based decision tasks for non-language models.
- GraphDecisionBench: Benchmarking System One Models on Graph Tasksraises · addresses
Non-compositional sparse autoencoder features1 paper raises it · 1 addresses it
Sparse autoencoder features often exhibit higher-order interactions, limiting interpretability and control.
- Behavioral Compositionality of Sparse Autoencoder Representationsraises · addresses

Named by an AI from these papers' abstracts.

Recent papers

All papers in Research

arXiv cs.LGOct 11
Revisited Support Vector Machines: A Unified Joint Optimization Framework with Nyström Approximation for Scalable Adaptive Learning
Nassou Gongon Benjamin, Noulapeu Ngaffo, Patrick Njionou Sadjang
The theoretical elegance of Support Vector Machines (SVMs), grounded in statistical learning theory, establishes them as a reference for robust classification. However, in the era of Big Data, classical SVMs face two major bottlenecks: the prohibitive cubic complexity $\mathcal{O}(N^3)$ of training and the rigidity of static kernels. Traditional methodologies treat kernel selection as a discrete, "brute-force" GridSearch problem, effectively decoupling the learning of data representation from the optimization of the decision boundary. This paper proposes a paradigm shift with a so-called "Revisited SVM", a unified framework that recasts the learning process as a continuous %bi-level joint optimization problem. We derive a novel objective function $J(α, θ)$ that allows for the simultaneous optimization of dual Lagrange multipliers and kernel hyper-parameters. To solve this challenging non-convex problem efficiently, we introduce a hybrid Block Coordinate Ascent (BCA) algorithm, tightly integrated with Nyström-based low-rank approximation, which drastically reduces computational complexity to $\mathcal{O}(Nm)$. Extensive experiments conducted across four heterogeneous domains…
PDF arXiv
arXiv cs.LGOct 11
Riemannian Graph Tokenizer for Structural Knowledge Transfer
Qimin Zhou, Haibo Liu, Yujie Wang, Li Sun, Chuan Shi
Foundation models are at the forefront of artificial intelligence. A tokenizer, converting the raw input into discrete representations that the model can understand, plays an important role to the success of foundation models. Unlike the text tokenizer that is well studied in large language models, graph tokenizer is still at its early stage, facing the challenges of tackling the non-Euclidean structures and capturing the structural semantics. How to design a graph tokenizer for structural knowledge transfer? To this end, we propose a Riemannian Graph Tokenizer (RGT) that bridges the structural knowledge and quantized representations to support cross-domain structural knowledge transfer. The connection is established by Riemannian geometry. Specifically, we first define the geometric vocabulary (trees, cycles and sequences), which captures fundamental structural patterns and reflects the intrinsic geometry of graph. Second, we construct a Riemannian quantizer with Riemannian Straight-Through Estimator to tokenise graph structures across multiple domains into discrete tokens. To ensure consistency and transferability across diverse geometric spaces, RGT further incorporates a…
PDF arXiv
arXiv cs.LGOct 11
GA-SVD: Generation-aware Singular Value Decomposition for LLM Compression
Shengkun Tang, Cong Zeng, Zongfang Liu, Dan Alistarh, Zhiqiang Shen
Large language models (LLMs) demonstrate strong generalization across a broad range of reasoning and generation tasks, but their large parameter counts impose substantial memory and computation costs, hindering deployment in practical resource-constrained settings. One-shot low-rank compression is a promising solution since it reduces model size and inference cost effectively. However, existing SVD-based methods primarily target multiple-choice benchmarks and often fail to preserve performance on generation tasks. Moreover, their rank allocation strategies are typically heuristic. We propose GA-SVD, a generation-aware low-rank compression framework for LLMs. First, we introduce Generation-Aware Weight Whitening (GAWW), which leverages gradients from on-policy knowledge distillation to construct whitening transformations aligned with generative behavior. Second, we develop an evolutionary global rank allocation method that searches for effective layer-wise rank allocation under a given global compression ratio. Across extensive experiments on Mistral-7B, Qwen3 series, and Llama-3.3 models, evaluated on both multiple-choice and generative benchmarks, GA-SVD consistently outperforms…
PDF arXiv
arXiv cs.LGOct 11
WUSPruner: Second-Moment-Optimal Transforms for Structured Pruning
Shengkun Tang, Dan Alistarh, Zhiqiang Shen
Structured pruning is typically formulated as identifying which model dimensions to remove, often within the model's original representation. However, the effect of coordinate deletion fundamentally depends on the basis in which pruning is performed. This raises a more fundamental question: how should the basis be chosen specifically for coordinate deletion? We introduce WUSPruner, a transform-based framework for structured pruning of large language models. We formulate basis selection as a local linear reconstruction problem that directly minimizes the reconstruction loss induced by pruning. Inspired by the second-moment transformation in WUSH, we consider a WUS transform constructed jointly from activation and weight statistics. We show that under positive-definite second moments, WUS transform minimizes the local reconstruction loss over all invertible changes of basis. In the resulting basis, the activation and weight second moments are simultaneously diagonalized and balanced, causing the deletion error to decompose into independent spectral contributions and yielding a principled criterion for coordinate selection. Guided by this result, we develop a scalable pruning method…
PDF arXiv
arXiv cs.LGOct 11
Approximation in Contrastive Representation Learning
Yuanfan Li, Zihan Zhang, Yiming Ying, Ding-Xuan Zhou
Contrastive representation learning (CRL) is a fundamental paradigm for learning transferable representations. Recent work identifies its population target as the pointwise mutual information (PMI) $\log\frac{p(x,y)}{p_X(x)p_Y(y)}$ between two modalities $X,Y$, where $p$ is the joint density function and $p_X,p_Y$ are the marginals. However, it remains unclear why standard inner-product scores $f(x)^\top g(y)$ can effectively approximate a generally nonseparable population target PMI. In this paper, we address this question from the aspect of approximation for CRL. By linking PMI to a compact operator, we show that $D$-dimensional inner-product models perform rank-$D$ spectral approximation, with error controlled by the spectral tail. We then study neural network realizations: in general settings, we show that deep neural network scoring functions are universally consistent, and the approximation error rates depend on the smoothness of the PMI function; under structured low-rank data models we obtain improved rates attained by moderate-width encoders. Finally, we establish a fast calibration rate from contrastive excess risk to downstream retrieval error under a density-ratio…
PDF arXiv
arXiv cs.LGOct 11
E8 Lattice Key Quantization for Low-Bit KV-Cache Compression
Sasho Nedelkoski, Alexander Acker, Soeren Becker, Dominik Scheinert, Odej Kao
Compressing the key-value (KV) cache is essential for serving long-context large language models (LLMs) under memory constraints. While current scalar quantization methods achieve significant compression, they typically face a quality-fidelity trade-off, either suffering from performance instability at 2-bit precision or necessitating 3-bit keys to maintain model quality. In this work, we demonstrate that a uniform low-bit k2v2 configuration (2-bit keys and 2-bit values) can preserve near-baseline quality by using vector quantization (VQ) based on the $E_8$ lattice for KV keys. We show that structured VQ exploits correlations across adjacent dimensions to achieve signal-to-quantization-noise ratios (SQNR) higher than those of independent scalar quantization at the same key payload rate. To ensure practical utility, we adapt a table-based asymmetric scoring algorithm that avoids explicit codebook dequantization during attention computation and preserves decode-throughput parity with scalar baselines. Across five LLM families, our $E_8$ k2v2 approach yields \textasciitilde$6\times$ KV compression, roughly 20\% smaller than scalar k3v2 (3-bit keys and 2-bit values), while retaining…
PDF arXiv