TIDE enables the first cross-architecture distillation of dLLMs, improving a 0.6B student by 1.53 average points over baselines when trained from 8B dense and 16B MoE teachers.
super hub Mixed citations
write newline
Mixed citation behavior. Most common role is unclear (62%).
301
Pith papers citing it
unclear
62% of classified citations
hub tools
citation-role summary
background 8
other 4
method 1
citation-polarity summary
claims ledger
- background Table A1: Comparison of BAS for frontier models across tasks when varying the risk-prior w(t). Higher scores indicate better alignment with expressed uncertainty. The standardBAS (Uniform: w(t) = 1) serves as the baseline, while Linear and Quadratic weights simulate increasingly safety-critical environments. Identical ECE, different BAS.Consider two models evaluated on four examples with correctness labelsZ= [1, 1, 0, 0]. The models produce the following confidence values: Example 1 2 3 4 Z1 1 0
authors
co-cited works
representative citing papers
JumpLoRA uses JumpReLU gating to induce adaptive sparsity in LoRA blocks, achieving dynamic parameter isolation that prevents task interference and improves continual learning performance over IncLoRA and ELLA.
LLM judges exhibit up to 9.8 percentage point leniency bias from stakes signaling in prompts, acting implicitly without mentioning it in chain-of-thought.
InfiniteScienceGym procedurally generates unbounded scientific repositories with exact ground-truth QA pairs to benchmark LLMs on data reasoning, abstention, and tool use without static datasets.
EnsembleCert and ScaLabelCert enable tighter and exact certificates for neural network robustness against label-flipping attacks by leveraging white-box information and neural tangent kernel equivalence.
Steered LLM activations are non-surjective: under practical assumptions, they lie outside the set of states reachable from any discrete prompt.
AgentSocialBench demonstrates that privacy preservation is fundamentally harder in human-centered agentic social networks than in single-agent cases due to cross-domain coordination pressures and an abstraction paradox where privacy instructions increase discussion of sensitive information.
MiCP is the first conformal prediction method for multi-turn LLM pipelines that allocates per-turn error budgets to enable adaptive stopping with an overall coverage guarantee, shown to reduce turns and cost on RAG and ReAct benchmarks.
The paper proves W[1]-hardness parameterized by dimension d for positivity, zonotope containment, max approximation, and L_p-Lipschitz constants in 2- and 3-layer ReLU networks, showing enumeration methods are optimal under ETH.
RLCracker is a reinforcement learning attack that erases LLM watermarks at 98.5% success rate with minimal data and generalizes across ten schemes and multiple model sizes.
Establishes an unconditional robustness threshold of 1-1/q for zero-bit tamper-detection codes in watermarking, with matching constructions and experimental confirmation on image models.
ErrorRadar is a new benchmark of 2,500 multimodal K-12 math problems for MLLM error step identification and categorization, where GPT-4o trails human experts by ~10%.
BEAVER is the first text-to-SQL benchmark from private enterprise data warehouses, revealing SOTA agentic frameworks achieve only 10.8% accuracy on complex real-world queries.
Introduces an SDE-based framework for score-based generative modeling that unifies prior methods, enables predictor-corrector sampling and neural ODE likelihoods, and achieves SOTA unconditional image generation on CIFAR-10.
A noisy top-k gated mixture-of-experts layer between LSTMs scales neural networks to 137B parameters with sub-linear compute, beating SOTA on language modeling and machine translation.
A first-order stochastic optimizer that maintains bias-corrected exponential moving averages of the gradient and its square, dividing the former by the square root of the latter to set per-parameter step sizes.
AutoSP automates sequence parallelism and long-context activation checkpointing via compilation, enabling up to 2.7x longer training contexts on NVIDIA hardware with negligible throughput loss.
C2C is a new testbed where LM agents negotiate differently from humans and targeted prompting raises their win rate from 22.2% to 32.7% across 1,100+ games.
XGRAG uses graph perturbations to quantify component contributions in GraphRAG and achieves 14.81% better explanation quality than text-based baselines on QA datasets, with correlations to graph centrality.
GraphPlanner augments multi-agent LLM routing with a heterogeneous graph memory and RL-optimized MDP workflow generation, delivering up to 9.3% higher accuracy and over 99% lower GPU cost than prior routers while supporting zero-shot generalization.
MMEB-V3 benchmark shows omni-modality embedding models fail to enforce instruction-specified modality constraints and exhibit asymmetric, query-biased retrieval.
A new SFT framework for MoE models combines bias-driven sparsification with gated condenser experts to retain long-tailed expert information, outperforming DenseMixer and ESFT by over 2.5% on math reasoning and commonsense QA benchmarks.
Pliable rejection sampling learns a kernel-based proposal to enable efficient i.i.d. sampling from target distributions f with high-probability correctness and a guarantee on accepted samples.
Stimuli with low intra-modal dispersion among vision models elicit up to twice the cross-modal alignment with language models compared to high-dispersion stimuli.
citing papers explorer
-
Beyond Static Vision: Scene Dynamic Field Unlocks Intuitive Physics Understanding in Multi-modal Large Language Models
Scene Dynamic Field integrates physics simulators into MLLM fine-tuning to boost intuitive physics understanding, delivering up to 20.7% gains on fluid tasks with generalization to unseen domains.
-
From Broad Exploration to Stable Synthesis: Entropy-Guided Optimization for Autoregressive Image Generation
EG-GRPO improves autoregressive text-to-image models by reallocating RL updates according to token entropy, excluding low-entropy tokens from reward signals while adding entropy bonuses to high-entropy ones, yielding state-of-the-art results on standard benchmarks.
-
Robust LLM Performance Certification via Constrained Maximum Likelihood Estimation
Constrained MLE fuses human calibration data, LLM judge labels, and judge performance bounds to yield accurate low-variance estimates of LLM failure rates.
-
GNN-as-Judge: Unleashing the Power of LLMs for Graph Learning with GNN Feedback
GNN-as-Judge combines GNN structural inductive bias with LLM semantics via collaborative pseudo-labeling and weakly-supervised fine-tuning to improve performance on text-attributed graphs in low-resource regimes.
-
OPRIDE: Offline Preference-based Reinforcement Learning via In-Dataset Exploration
OPRIDE improves query efficiency in offline PbRL via a principled in-dataset exploration strategy and discount scheduling, outperforming prior methods with fewer queries and providing theoretical guarantees.
-
Generalised Linear Models in Deep Bayesian RL with Learnable Basis Functions
GLiBRL uses GLMs with learnable basis functions for exact Bayesian inference in deep BRL, derives a closed-form link between L2 task distances and kernel task similarity, and reports up to 1.8x gains over prior meta-RL on MuJoCo and MetaWorld.
-
FlowBind: Efficient Any-to-Any Generation with Bidirectional Flows
FlowBind enables efficient any-to-any multimodal generation via a shared latent space bridged by modality-specific invertible flows, matching prior quality with up to 6x fewer parameters and 10x faster training.
-
RAST-MoE-RL: A Regime-Aware Spatio-Temporal MoE Framework for Deep Reinforcement Learning in Ride-Hailing
RAST-MoE-RL equips RL agents with a regime-aware spatio-temporal MoE encoder that reduces matching delay by 10% and pickup delay by 15% on real Uber data from San Francisco while showing robustness to unseen regimes.
-
Don't Throw Away Your Beams: Improving Consistency-based Uncertainties in LLMs via Beam Search
Beam search for candidate generation in consistency-based UQ for LLMs reduces variance and improves performance over multinomial sampling on six QA datasets, supported by a theoretical lower bound on beam-set probability mass.
-
Greedy Alignment Principle for Optimizer Selection
The greedy alignment principle formulates optimizer selection as maximizing expected loss drop via inner product with gradient autocorrelation, yielding dynamic momentum rules for SGD and Adam that match or exceed best fixed hyperparameters.
-
Mitigating Catastrophic Forgetting in Target Language Adaptation of LLMs via Source-Shielded Updates
SSU mitigates catastrophic forgetting in low-resource LLM target-language adaptation by scoring and column-wise freezing source-critical parameters, reducing source degradation to ~3% versus ~20% for full fine-tuning while matching target performance.
-
Two-Dimensional Quantization for Geometry-Aware Audio Coding
Q2D2 uses 2D geometric grid projections to quantize feature pairs in neural audio codecs, yielding implicit codebooks that improve efficiency and utilization over RVQ, VQ, and FSQ while maintaining reconstruction quality.
-
Adaptive Residual-Update Steering for Low-Overhead Hallucination Mitigation in Large Vision Language Models
RUDDER creates a persistent visual anchor by extracting CARD from prefill residuals and modulating its injection via an adaptive Beta Gate, cutting CHAIR_S by 24.4% and CHAIR_i by 23.6% on average across LLaVA, Idefics2, InstructBLIP and Qwen2.5-VL with >96% throughput.
-
Structured Uncertainty guided Clarification for LLM Agents
Structured uncertainty with EVPI enables more efficient clarification and better training for tool-calling LLM agents on ambiguous tasks.
-
Turbo-DDCM: Fast and Flexible Zero-Shot Diffusion-Based Image Compression
Turbo-DDCM accelerates DDCM-based zero-shot image compression by batching noise vectors per step while preserving performance and adding priority-aware and PSNR-targeted variants.
-
SPECTRA: Spectral Domain-Aware Graph Generation for Imbalanced Molecular Property Regression
SPECTRA improves molecular property regression on underrepresented targets via spectral graph generation with rarity-aware budgeting and Laplacian interpolation, paired with edge-aware Chebyshev GNNs, yielding competitive benchmark performance at lower compute cost.
-
The Realignment Problem: When Right becomes Wrong in LLMs
TRACE is a three-stage optimization framework that realigns LLMs to new policies by categorizing preference conflicts, scoring impact via bi-level optimization, and applying hybrid losses without new human annotations.
-
Graph-Based Alternatives to LLMs for Human Simulation
GEMS formulates close-ended human-behavior simulation as link prediction on a heterogeneous graph and matches or exceeds LLM performance with three orders of magnitude fewer parameters across three datasets and three evaluation settings.
-
Diff4Splat: Controllable 4D Scene Generation with Latent Dynamic Reconstruction Models
A feed-forward video latent transformer that predicts time-varying 3D Gaussian primitives from one image to produce controllable 4D scenes with appearance, geometry, and motion.
-
DeepThinkVLA: Enhancing Reasoning Capability of Vision-Language-Action Models
DeepThinkVLA shows CoT improves VLA models only under decoding and causal alignment, delivering 97% success on LIBERO and 21.7-point gains via hybrid attention and SFT-RL training.
-
Efficient and Transferable Agentic Knowledge Graph RAG via Reinforcement Learning
KG-R1 trains a single RL agent to retrieve from and reason over knowledge graphs in one loop, achieving higher accuracy with fewer tokens than multi-module baselines and transferring to unseen graphs.
-
Beyond Linear Probes: Dynamic Safety Monitoring for Language Models
TPCs allow term-by-term progressive polynomial evaluation on LLM activations for flexible safety monitoring that supports both stronger guardrails and low-cost adaptive cascades.
-
SeMoBridge: Semantic Modality Bridge for Efficient Few-Shot Adaptation of CLIP
SeMoBridge projects images into the text modality via a semantic bridge to reduce CLIP's intra-modal misalignment and improve few-shot performance.
-
Chain-in-Tree: Back to Sequential Reasoning in LLM Tree Search
Chain-in-Tree cuts token use, model calls, and runtime by 75-85% in LLM tree search on GSM8K and Math500 by using simple branching-necessity checks, with little accuracy loss in most cases.
-
Thinking Sparks!: Emergent Attention Heads in Reasoning Models During Post Training
Post-training on reasoning tasks sparks the emergence of specialized attention heads that enable structured computation, with SFT adding stable heads while GRPO uses dynamic activation and pruning tied to reward signals, and controllable think models relying on compensatory heads instead of specific
-
SynthPert: Enhancing LLM Biological Reasoning via Synthetic Reasoning Traces for Cellular Perturbation Prediction
SynthPert fine-tunes LLMs using synthetic reasoning traces to reach state-of-the-art on the PerturbQA benchmark for cellular perturbation prediction, surpassing the generating frontier model while generalizing to unseen cell types with only 2% of filtered data.
-
Perceive, Verify and Understand Long Video: Multi-Granular Perception and Active Verification via Interactive Agents
CogniGPT uses an interactive loop between a Multi-Granular Perception Agent and an Active Verification Agent to identify reliable clues in long videos with high accuracy and low frame usage.
-
Causal-Adapter: Taming Text-to-Image Diffusion for Faithful Counterfactual Generation
Causal-Adapter adapts frozen diffusion backbones via structural causal modeling, prompt-aligned injection, and conditioned token contrastive loss to achieve faithful counterfactual generation with strong attribute control and identity preservation.
-
Localizing Task Recognition and Task Learning in In-Context Learning via Attention Head Analysis
A new framework using Task Subspace Logit Attribution localizes attention heads specialized for task recognition and task learning in in-context learning, showing they align and rotate hidden states within a task subspace.
-
From Past To Path: Masked History Learning for Next-Item Prediction in Generative Recommendation
Masked History Learning augments autoregressive training in generative recommenders with an auxiliary masked historical item reconstruction task using entropy-guided masking and curriculum learning.
-
Emergent Slow Thinking in LLMs as Inverse Tree Freezing
RLVR drives a concept network in LLMs through nucleation and freezing into inverse trees that support slow thinking, and intervening with brief SFT at peak frustration outperforms standard RLVR while post-freeze SFT causes forgetting.
-
On the Shelf Life of Fine-Tuned LLM-Judges: Future-Proofing, Backward-Compatibility, and Question Generalization
Fine-tuned LLM judges struggle with future-proofing to newer generators but maintain backward-compatibility more easily; DPO training and continual learning improve adaptation while all models degrade on unseen questions.
-
Mitigating Visual Context Degradation in Large Multimodal Models: A Training-Free Decoupled Agentic Framework
DRP decouples reasoning from perception in LMMs by using an LLM reasoner to query an LMM observer for visual details as needed, reducing visual grounding loss.
-
Artificial Phantasia: Emergent Mental Imagery in Large Language Models
LLMs achieve higher accuracy than humans on compositional imagery tasks previously argued to require pictorial representations, supporting emergent propositional mental imagery in AI.
-
Sparse Deep Additive Model with Interactions: Enhancing Interpretability and Predictability
SDAMI detects interactions in high-dimensional data via an Effect Footprint principle and models them using sparsity, group lasso, and dedicated deep subnetworks for improved interpretability.
-
Reinforcement Learning with Discrete Diffusion Policies for Combinatorial Action Spaces
A method trains discrete diffusion policies for combinatorial RL by matching to a PMD-regularized target distribution, reporting SOTA performance and sample efficiency on DNA generation, macro-action, and multi-agent benchmarks.
-
MoveFM-R: Advancing Mobility Foundation Models via Language-driven Semantic Reasoning
MoveFM-R is a framework that bridges mobility foundation models and LLMs using semantically enhanced location encoding, progressive curriculum alignment, and interactive self-reflection to generate plausible trajectories from language inputs.
-
StableToken: A Noise-Robust Semantic Speech Tokenizer for Resilient SpeechLLMs
StableToken introduces a multi-branch architecture with bit-wise voting to create noise-robust semantic speech tokens, achieving lower Unit Edit Distance and better SpeechLLM robustness than prior single-path tokenizers.
-
Guidance Watermarking for Diffusion Models
Guidance watermarking steers diffusion denoising steps via gradients from an off-the-shelf watermark decoder to embed marks during generation, converting post-hoc schemes into in-generation ones while remaining complementary to VAE modifications.
-
AEGIS: Authentic Edge Growth In Sparsity for Link Prediction in Edge-Sparse Bipartite Knowledge Graphs
AEGIS is an edge resampling framework that enhances link prediction in edge-sparse bipartite graphs, showing benefits from semantic augmentation on text-rich data.
-
Elastic MoE: Unlocking the Inference-Time Scalability of Mixture-of-Experts
EMoE trains MoE models so they maintain performance when the number of activated experts changes at inference, expanding the usable range to 2-3 times the training k with higher peak results.
-
RLBFF: Binary Flexible Feedback to bridge between Human Feedback & Verifiable Rewards
RLBFF extracts binary principles from human feedback to train reward models that outperform Bradley-Terry models on RM-Bench and JudgeBench and enable customizable inference-time focus for LLM alignment.
-
Differential-Integral Neural Operator for Long-Term Turbulence Forecasting
DINO decomposes turbulent evolution into parallel local differential and global integral operators to achieve stable autoregressive forecasting on 2D Kolmogorov flow.
-
Model-Based Reinforcement Learning under Random Observation Delays
A delay-aware model-based RL framework with sequential belief filtering handles random out-of-sequence observations in POMDPs and outperforms MDP baselines while showing robustness to delay shifts.
-
Steerable Adversarial Scenario Generation through Test-Time Preference Alignment
SAGE reframes adversarial scenario generation as multi-objective preference alignment, using hierarchical group-based optimization and test-time linear interpolation of two expert policies to enable steerable control over adversariality-realism trade-offs.
-
Flow marching for a generative PDE foundation model
Flow Marching jointly samples noise and physical time to learn a velocity field for generative PDE modeling, paired with a latent autoencoder and efficient transformer for large-scale pretraining on 2.5M trajectories.
-
EpiCache: Episodic KV Cache Management for Long-Term Conversation on Resource-Constrained Environments
EpiCache clusters long conversation history into coherent episodes for per-episode KV cache eviction, delivering up to 30% accuracy gains and 3.7x peak memory reduction on LongConvQA tasks under fixed budgets.
-
Dual-Timescale Hebbian Accumulators for Online Spiking Neural Network Decoding in Intracortical Brain Machine Interfaces
A dual-timescale Hebbian accumulator enables online SNN decoding for BMIs with constant memory, no BPTT, and reported correlations of R >= 0.81 and 0.63 on two primate datasets plus 63-86% memory savings.
-
Empowering Multi-Robot Cooperation via Sequential World Models
SeqWM introduces sequential autoregressive agent-wise world models for multi-robot MBRL, outperforming baselines in performance and sample efficiency on Bi-DexHands and Multi-Quadruped tasks with physical robot deployment.
-
Causal Discovery via Quantile Partial Effect
The paper demonstrates that assuming the quantile partial effect lies in a finite linear span enables causal identifiability from observational data, with applications to bivariate and multivariate causal discovery using basis tests and Fisher information.