Category: News

ButterflyQuant: Ultra-low-bit LLM Quantization through Learnable Orthogonal Butterfly Transformscs.AI updates on arXiv.org arXiv:2509.09679v3 Announce Type: replace-cross
Abstract: Large language models require massive memory footprints, severely limiting deployment on consumer hardware. Quantization reduces memory through lower numerical precision, but extreme 2-bit quantization suffers from catastrophic performance loss due to outliers in activations. Rotation-based methods such as QuIP and QuaRot apply orthogonal transforms to eliminate outliers before quantization, using computational invariance: $mathbf{y} = mathbf{Wx} = (mathbf{WQ}^T)(mathbf{Qx})$ for orthogonal $mathbf{Q}$. However, these methods use fixed transforms–Hadamard matrices achieving optimal worst-case coherence $mu = 1/sqrt{n}$–that cannot adapt to specific weight distributions. We identify that different transformer layers exhibit distinct outlier patterns, motivating layer-adaptive rotations rather than one-size-fits-all approaches. In this work, we propose ButterflyQuant, which replaces Hadamard rotations with learnable butterfly transforms parameterized by continuous Givens rotation angles. Unlike Hadamard’s discrete ${+1, -1}$ entries that are non-differentiable and thus prohibit gradient-based learning, butterfly transforms’ continuous parameterization enables smooth optimization while guaranteeing orthogonality by construction. This orthogonal constraint ensures theoretical guarantees in outlier suppression while achieving $O(n log n)$ computational complexity with only $frac{n log n}{2}$ learnable parameters. We further introduce a uniformity regularization on post-transformation activations to promote smoother distributions amenable to quantization. Learning requires only 128 calibration samples and converges in minutes on a single GPU.

 arXiv:2509.09679v3 Announce Type: replace-cross
Abstract: Large language models require massive memory footprints, severely limiting deployment on consumer hardware. Quantization reduces memory through lower numerical precision, but extreme 2-bit quantization suffers from catastrophic performance loss due to outliers in activations. Rotation-based methods such as QuIP and QuaRot apply orthogonal transforms to eliminate outliers before quantization, using computational invariance: $mathbf{y} = mathbf{Wx} = (mathbf{WQ}^T)(mathbf{Qx})$ for orthogonal $mathbf{Q}$. However, these methods use fixed transforms–Hadamard matrices achieving optimal worst-case coherence $mu = 1/sqrt{n}$–that cannot adapt to specific weight distributions. We identify that different transformer layers exhibit distinct outlier patterns, motivating layer-adaptive rotations rather than one-size-fits-all approaches. In this work, we propose ButterflyQuant, which replaces Hadamard rotations with learnable butterfly transforms parameterized by continuous Givens rotation angles. Unlike Hadamard’s discrete ${+1, -1}$ entries that are non-differentiable and thus prohibit gradient-based learning, butterfly transforms’ continuous parameterization enables smooth optimization while guaranteeing orthogonality by construction. This orthogonal constraint ensures theoretical guarantees in outlier suppression while achieving $O(n log n)$ computational complexity with only $frac{n log n}{2}$ learnable parameters. We further introduce a uniformity regularization on post-transformation activations to promote smoother distributions amenable to quantization. Learning requires only 128 calibration samples and converges in minutes on a single GPU. Read More  

ZebraPose: Zebra Detection and Pose Estimation using only Synthetic Datacs.AI updates on arXiv.org arXiv:2408.10831v2 Announce Type: replace-cross
Abstract: Collecting and labeling large real-world wild animal datasets is impractical, costly, error-prone, and labor-intensive. For animal monitoring tasks, as detection, tracking, and pose estimation, out-of-distribution viewpoints (e.g. aerial) are also typically needed but rarely found in publicly available datasets. To solve this, existing approaches synthesize data with simplistic techniques that then necessitate strategies to bridge the synthetic-to-real gap. Therefore, real images, style constraints, complex animal models, or pre-trained networks are often leveraged. In contrast, we generate a fully synthetic dataset using a 3D photorealistic simulator and demonstrate that it can eliminate such needs for detecting and estimating 2D poses of wild zebras. Moreover, existing top-down 2D pose estimation approaches using synthetic data assume reliable detection models. However, these often fail in out-of-distribution scenarios, e.g. those that include wildlife or aerial imagery. Our method overcomes this by enabling the training of both tasks using the same synthetic dataset. Through extensive benchmarks, we show that models trained from scratch exclusively on our synthetic data generalize well to real images. We perform these using multiple real-world and synthetic datasets, pre-trained and randomly initialized backbones, and different image resolutions. Code, results, models, and data can be found athttps://zebrapose.is.tue.mpg.de/.

 arXiv:2408.10831v2 Announce Type: replace-cross
Abstract: Collecting and labeling large real-world wild animal datasets is impractical, costly, error-prone, and labor-intensive. For animal monitoring tasks, as detection, tracking, and pose estimation, out-of-distribution viewpoints (e.g. aerial) are also typically needed but rarely found in publicly available datasets. To solve this, existing approaches synthesize data with simplistic techniques that then necessitate strategies to bridge the synthetic-to-real gap. Therefore, real images, style constraints, complex animal models, or pre-trained networks are often leveraged. In contrast, we generate a fully synthetic dataset using a 3D photorealistic simulator and demonstrate that it can eliminate such needs for detecting and estimating 2D poses of wild zebras. Moreover, existing top-down 2D pose estimation approaches using synthetic data assume reliable detection models. However, these often fail in out-of-distribution scenarios, e.g. those that include wildlife or aerial imagery. Our method overcomes this by enabling the training of both tasks using the same synthetic dataset. Through extensive benchmarks, we show that models trained from scratch exclusively on our synthetic data generalize well to real images. We perform these using multiple real-world and synthetic datasets, pre-trained and randomly initialized backbones, and different image resolutions. Code, results, models, and data can be found athttps://zebrapose.is.tue.mpg.de/. Read More  

Intrinsic Self-Correction in LLMs: Towards Explainable Prompting via Mechanistic Interpretabilitycs.AI updates on arXiv.org arXiv:2505.11924v3 Announce Type: replace-cross
Abstract: Intrinsic self-correction refers to the phenomenon where a language model refines its own outputs purely through prompting, without external feedback or parameter updates. While this approach improves performance across diverse tasks, its mechanism remains unclear. We show that intrinsic self-correction functions by steering hidden representations along interpretable latent directions, as evidenced by both alignment analysis and activation interventions. To achieve this, we analyze intrinsic self-correction via the representation shift induced by prompting. In parallel, we construct interpretable latent directions with contrastive pairs and verify the causal effect of these directions via activation addition. Evaluating six open-source LLMs, our results demonstrate that prompt-induced representation shifts in text detoxification and text toxification consistently align with latent directions constructed from contrastive pairs. In detoxification, the shifts align with the non-toxic direction; in toxification, they align with the toxic direction. These findings suggest that representation steering is the mechanistic driver of intrinsic self-correction. Our analysis highlights that understanding model internals offers a direct route to analyzing the mechanisms of prompt-driven LLM behaviors.

 arXiv:2505.11924v3 Announce Type: replace-cross
Abstract: Intrinsic self-correction refers to the phenomenon where a language model refines its own outputs purely through prompting, without external feedback or parameter updates. While this approach improves performance across diverse tasks, its mechanism remains unclear. We show that intrinsic self-correction functions by steering hidden representations along interpretable latent directions, as evidenced by both alignment analysis and activation interventions. To achieve this, we analyze intrinsic self-correction via the representation shift induced by prompting. In parallel, we construct interpretable latent directions with contrastive pairs and verify the causal effect of these directions via activation addition. Evaluating six open-source LLMs, our results demonstrate that prompt-induced representation shifts in text detoxification and text toxification consistently align with latent directions constructed from contrastive pairs. In detoxification, the shifts align with the non-toxic direction; in toxification, they align with the toxic direction. These findings suggest that representation steering is the mechanistic driver of intrinsic self-correction. Our analysis highlights that understanding model internals offers a direct route to analyzing the mechanisms of prompt-driven LLM behaviors. Read More  

AI Driven Discovery of Bio Ecological Mediation in Cascading Heatwave Riskscs.AI updates on arXiv.org arXiv:2509.25112v2 Announce Type: replace
Abstract: Compound heatwaves increasingly trigger complex cascading failures that propagate through interconnected physical and human systems, yet the fragmentation of disciplinary knowledge hinders the comprehensive mapping of these systemic risk topologies. This study introduces the Heatwave Discovery Agent HeDA as an autonomous scientific synthesis framework designed to bridge cognitive gaps by constructing a high fidelity knowledge graph from 8,111 academic publications. By structuring 70,297 evidence nodes, the system exhibits enhanced inferential fidelity in capturing long tail risk mechanisms and achieves a significant accuracy margin compared to standard foundation models including GPT 5.2 and Claude Sonnet 4.5 in complex reasoning tasks. The resulting topological analysis reveals a critical bio ecological mediation effect where biological systems function as the primary non linear amplifiers of thermal stress that transform physical meteorological hazards into systemic socioeconomic losses. We further identify latent functional couplings between theoretically distinct sectors such as the heat induced synchronization of power grid failures and emergency medical capacity saturation. These findings elucidate the dynamics of compound climate risks and provide an empirical basis for shifting adaptation strategies from static sectoral defense to dynamic cross system resilience.

 arXiv:2509.25112v2 Announce Type: replace
Abstract: Compound heatwaves increasingly trigger complex cascading failures that propagate through interconnected physical and human systems, yet the fragmentation of disciplinary knowledge hinders the comprehensive mapping of these systemic risk topologies. This study introduces the Heatwave Discovery Agent HeDA as an autonomous scientific synthesis framework designed to bridge cognitive gaps by constructing a high fidelity knowledge graph from 8,111 academic publications. By structuring 70,297 evidence nodes, the system exhibits enhanced inferential fidelity in capturing long tail risk mechanisms and achieves a significant accuracy margin compared to standard foundation models including GPT 5.2 and Claude Sonnet 4.5 in complex reasoning tasks. The resulting topological analysis reveals a critical bio ecological mediation effect where biological systems function as the primary non linear amplifiers of thermal stress that transform physical meteorological hazards into systemic socioeconomic losses. We further identify latent functional couplings between theoretically distinct sectors such as the heat induced synchronization of power grid failures and emergency medical capacity saturation. These findings elucidate the dynamics of compound climate risks and provide an empirical basis for shifting adaptation strategies from static sectoral defense to dynamic cross system resilience. Read More  

Progress Constraints for Reinforcement Learning in Behavior Treescs.AI updates on arXiv.org arXiv:2602.06525v2 Announce Type: replace
Abstract: Behavior Trees (BTs) provide a structured and reactive framework for decision-making, commonly used to switch between sub-controllers based on environmental conditions. Reinforcement Learning (RL), on the other hand, can learn near-optimal controllers but sometimes struggles with sparse rewards, safe exploration, and long-horizon credit assignment. Combining BTs with RL has the potential for mutual benefit: a BT design encodes structured domain knowledge that can simplify RL training, while RL enables automatic learning of the controllers within BTs. However, naive integration of BTs and RL can lead to some controllers counteracting other controllers, possibly undoing previously achieved subgoals, thereby degrading the overall performance. To address this, we propose progress constraints, a novel mechanism where feasibility estimators constrain the allowed action set based on theoretical BT convergence results. Empirical evaluations in a 2D proof-of-concept and a high-fidelity warehouse environment demonstrate improved performance, sample efficiency, and constraint satisfaction, compared to prior methods of BT-RL integration.

 arXiv:2602.06525v2 Announce Type: replace
Abstract: Behavior Trees (BTs) provide a structured and reactive framework for decision-making, commonly used to switch between sub-controllers based on environmental conditions. Reinforcement Learning (RL), on the other hand, can learn near-optimal controllers but sometimes struggles with sparse rewards, safe exploration, and long-horizon credit assignment. Combining BTs with RL has the potential for mutual benefit: a BT design encodes structured domain knowledge that can simplify RL training, while RL enables automatic learning of the controllers within BTs. However, naive integration of BTs and RL can lead to some controllers counteracting other controllers, possibly undoing previously achieved subgoals, thereby degrading the overall performance. To address this, we propose progress constraints, a novel mechanism where feasibility estimators constrain the allowed action set based on theoretical BT convergence results. Empirical evaluations in a 2D proof-of-concept and a high-fidelity warehouse environment demonstrate improved performance, sample efficiency, and constraint satisfaction, compared to prior methods of BT-RL integration. Read More  

TABES: Trajectory-Aware Backward-on-Entropy Steering for Masked Diffusion Modelscs.AI updates on arXiv.org arXiv:2602.00250v2 Announce Type: replace-cross
Abstract: Masked Diffusion Models (MDMs) have emerged as a promising non-autoregressive paradigm for generative tasks, offering parallel decoding and bidirectional context utilization. However, current sampling methods rely on simple confidence-based heuristics that ignore the long-term impact of local decisions, leading to trajectory lock-in where early hallucinations cascade into global incoherence. While search-based methods mitigate this, they incur prohibitive computational costs ($O(K)$ forward passes per step). In this work, we propose Backward-on-Entropy (BoE) Steering, a gradient-guided inference framework that approximates infinite-horizon lookahead via a single backward pass. We formally derive the Token Influence Score (TIS) from a first-order expansion of the trajectory cost functional, proving that the gradient of future entropy with respect to input embeddings serves as an optimal control signal for minimizing uncertainty. To ensure scalability, we introduce texttt{ActiveQueryAttention}, a sparse adjoint primitive that exploits the structure of the masking objective to reduce backward pass complexity. BoE achieves a superior Pareto frontier for inference-time scaling compared to existing unmasking methods, demonstrating that gradient-guided steering offers a mathematically principled and efficient path to robust non-autoregressive generation. We will release the code.

 arXiv:2602.00250v2 Announce Type: replace-cross
Abstract: Masked Diffusion Models (MDMs) have emerged as a promising non-autoregressive paradigm for generative tasks, offering parallel decoding and bidirectional context utilization. However, current sampling methods rely on simple confidence-based heuristics that ignore the long-term impact of local decisions, leading to trajectory lock-in where early hallucinations cascade into global incoherence. While search-based methods mitigate this, they incur prohibitive computational costs ($O(K)$ forward passes per step). In this work, we propose Backward-on-Entropy (BoE) Steering, a gradient-guided inference framework that approximates infinite-horizon lookahead via a single backward pass. We formally derive the Token Influence Score (TIS) from a first-order expansion of the trajectory cost functional, proving that the gradient of future entropy with respect to input embeddings serves as an optimal control signal for minimizing uncertainty. To ensure scalability, we introduce texttt{ActiveQueryAttention}, a sparse adjoint primitive that exploits the structure of the masking objective to reduce backward pass complexity. BoE achieves a superior Pareto frontier for inference-time scaling compared to existing unmasking methods, demonstrating that gradient-guided steering offers a mathematically principled and efficient path to robust non-autoregressive generation. We will release the code. Read More  

Learning to Compose for Cross-domain Agentic Workflow Generationcs.AI updates on arXiv.org arXiv:2602.11114v1 Announce Type: cross
Abstract: Automatically generating agentic workflows — executable operator graphs or codes that orchestrate reasoning, verification, and repair — has become a practical way to solve complex tasks beyond what single-pass LLM generation can reliably handle. Yet what constitutes a good workflow depends heavily on the task distribution and the available operators. Under domain shift, current systems typically rely on iterative workflow refinement to discover a feasible workflow from a large workflow space, incurring high iteration costs and yielding unstable, domain-specific behavior. In response, we internalize a decompose-recompose-decide mechanism into an open-source LLM for cross-domain workflow generation. To decompose, we learn a compact set of reusable workflow capabilities across diverse domains. To recompose, we map each input task to a sparse composition over these bases to generate a task-specific workflow in a single pass. To decide, we attribute the success or failure of workflow generation to counterfactual contributions from learned capabilities, thereby capturing which capabilities actually drive success by their marginal effects. Across stringent multi-domain, cross-domain, and unseen-domain evaluations, our 1-pass generator surpasses SOTA refinement baselines that consume 20 iterations, while substantially reducing generation latency and cost.

 arXiv:2602.11114v1 Announce Type: cross
Abstract: Automatically generating agentic workflows — executable operator graphs or codes that orchestrate reasoning, verification, and repair — has become a practical way to solve complex tasks beyond what single-pass LLM generation can reliably handle. Yet what constitutes a good workflow depends heavily on the task distribution and the available operators. Under domain shift, current systems typically rely on iterative workflow refinement to discover a feasible workflow from a large workflow space, incurring high iteration costs and yielding unstable, domain-specific behavior. In response, we internalize a decompose-recompose-decide mechanism into an open-source LLM for cross-domain workflow generation. To decompose, we learn a compact set of reusable workflow capabilities across diverse domains. To recompose, we map each input task to a sparse composition over these bases to generate a task-specific workflow in a single pass. To decide, we attribute the success or failure of workflow generation to counterfactual contributions from learned capabilities, thereby capturing which capabilities actually drive success by their marginal effects. Across stringent multi-domain, cross-domain, and unseen-domain evaluations, our 1-pass generator surpasses SOTA refinement baselines that consume 20 iterations, while substantially reducing generation latency and cost. Read More